Merge origin/main into ethie/oh-god (pluginify refactor reconciliation)

Reconciles the "pluginify everything" refactor (moving provider adapters,
platform adapters, and terminal backends out of core into plugins/) with
267 commits of main. main had 515 edits across 635 files; our branch moved
98 files into plugins/. The dangerous class was main editing files at OLD
paths that we relocated — handled below.

STRUCTURAL DECISIONS
- ai-gateway + vercel_sandbox: honored main's PR #33067 deletion. Dropped our
  orphaned plugins/terminals/vercel/ dir and all 3 stale vercel refs that
  survived in pyproject (workspace member, [all] entry, uv source).
- tools/lazy_deps.py: kept main's version. Our branch deleted it incompletely
  (WIP) while main has 30 live callers + active maintenance. main's intent won.
- agent/agent_runtime_helpers.py: COMBINED — main's atomic swap+rollback
  snapshot envelope wraps our pluginified registries-based anthropic imports.
- agent/credential_pool.py: took our plugin-hook indirection AND ported main's
  api_key_path_explicit OAuth-masquerade security fix INTO the anthropic
  credential_pool_hook (it was pluginified from a pre-fix base and would have
  been silently dropped otherwise).
- hermes_cli/model_switch.py, hermes_cli/models.py: took main's logic
  (cached_provider_model_ids, AI-gateway removal) then re-applied our pluginify
  import rewrites (agent.bedrock_adapter/anthropic_adapter -> registries
  namespace lookups) since those modules moved to plugins.
- tools/terminal_tool.py: took main's version (vercel_sandbox deletion) then
  restored our lazy registry resolution for modal + daytona environments
  (both moved to plugins; main's direct imports would crash at runtime).
- nix/checks.nix: kept both — our hermetic-boundary checks + main's
  messaging-variant discord.py guard.
- pyproject.toml: plugin extras as workspace members (ours) + main's new wecom
  extra; vercel removed throughout.
- uv.lock: regenerated with `uv lock` (not hand-merged); 233 packages.

VERIFICATION
- Zero conflict markers anywhere.
- Exhaustive 17-moved-module grep: no dead imports of relocated modules in core.
- Import smoke test: all hot core modules import clean.
- Targeted tests (21 files incl. credential_pool, anthropic plugin,
  run_agent, project_metadata): pass.
- 3 credential_pool security tests rewired to register the real plugin hook
  (core tests don't trigger plugin discovery): pass.
- Full suite: remaining failures are pre-existing on premerge-oh-god (telegram
  collection error: setUpModule MagicMock __code__) or environmental (matrix
  DNS/e2ee-deps, network) — NOT introduced by this merge. See PR notes.

.github/workflows/docker-publish.yml

@@ -196,26 +196,10 @@ jobs:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f  # v3
 
-      # Build once, load into the local daemon for smoke testing. PR arm64
-      # builds deliberately avoid the gha cache: cold-cache arm64 builds can
-      # outlive GitHub's short-lived Azure cache SAS token, then fail while
-      # reading or writing cache blobs before the smoke test can run.
-      - name: Build image (arm64, smoke test, uncached PR)
-        if: github.event_name == 'pull_request'
-        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f  # v7.1.0
-        with:
-          context: .
-          file: Dockerfile
-          load: true
-          platforms: linux/arm64
-          tags: ${{ env.IMAGE_NAME }}:test
-          build-args: |
-            HERMES_GIT_SHA=${{ github.sha }}
-
-      # Main/release builds still use the per-arch gha cache so the digest
-      # push below can reuse layers from this smoke-test build.
-      - name: Build image (arm64, smoke test, cached publish)
-        if: github.event_name != 'pull_request'
+      # Build once, load into the local daemon for smoke testing.  Cached
+      # to gha with a per-arch scope; the push step below reuses every
+      # layer from this build.
+      - name: Build image (arm64, smoke test)
         uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f  # v7.1.0
         with:
           context: .

.github/workflows/lint.yml

@@ -200,3 +200,22 @@ jobs:
 
       - name: Run footgun checker
         run: python scripts/check-windows-footguns.py --all
+
+  plugin-isolation:
+    # Enforce that core code and core tests never import from plugin packages.
+    # Core must interact with plugins exclusively through the registry layer.
+    # See scripts/check_no_plugin_imports_in_core.py for the rule list.
+    name: Plugin isolation (blocking)
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+
+      - name: Set up Python
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v5
+        with:
+          python-version: "3.11"
+
+      - name: Run plugin isolation checker
+        run: python scripts/check_no_plugin_imports_in_core.py

.gitignore

@@ -48,7 +48,7 @@ agent-browser/
 privvy*
 images/
 __pycache__/
-hermes_agent.egg-info/
+*.egg-info
 wandb/
 testlogs
 
@@ -87,12 +87,7 @@ website/static/api/skills-meta.json
 models-dev-upstream/
 hermes_cli/tui_dist/*
 hermes_cli/scripts/
-docs/superpowers/*
-# Working directory for the Hermes Agent's session state (~/.hermes/ at runtime;
+docs/superpowers/*# Working directory for the Hermes Agent's session state (~/.hermes/ at runtime;
 # also created in-repo when an agent operates in this checkout). Plans, audit
 # logs, and per-session caches are never artifacts of the codebase.
 .hermes/
-
-# Tool Search live-test harness output — non-deterministic model transcripts,
-# regenerated by scripts/tool_search_livetest.py. Never an artifact of the repo.
-scripts/out/

AGENTS.md

@@ -29,7 +29,9 @@ hermes-agent/
 ├── hermes_constants.py   # get_hermes_home(), display_hermes_home() — profile-aware paths
 ├── hermes_logging.py     # setup_logging() — agent.log / errors.log / gateway.log (profile-aware)
 ├── batch_runner.py       # Parallel batch processing
+├── _build_backend.py     # Custom PEP 517 build backend — inlines plugin deps at wheel build time
 ├── agent/                # Agent internals (provider adapters, memory, caching, compression, etc.)
+│   └── plugin_registries.py  # Typed capability registries (auth, transport, platform, tool, model_metadata)
 ├── hermes_cli/           # CLI subcommands, setup wizard, plugins loader, skin engine
 ├── tools/                # Tool implementations — auto-discovered via tools/registry.py
 │   └── environments/     # Terminal backends (local, docker, ssh, modal, daytona, singularity)
@@ -39,16 +41,20 @@ hermes-agent/
 │   │                     #   dingtalk, wecom, weixin, feishu, qqbot, bluebubbles,
 │   │                     #   yuanbao, webhook, api_server, ...). See ADDING_A_PLATFORM.md.
 │   └── builtin_hooks/    # Extension point for always-registered gateway hooks (none shipped)
-├── plugins/              # Plugin system (see "Plugins" section below)
+├── plugins/              # Plugin packages — uv workspace members (see "Plugins" section)
+│   ├── model-providers/  # anthropic, bedrock, azure-foundry (own pyproject.toml each)
+│   ├── platforms/        # telegram, slack, discord, feishu, dingtalk, matrix
+│   ├── tts/              # Text-to-speech plugin
+│   ├── stt/              # Speech-to-text plugin
+│   ├── image_gen/        # FAL image generation
+│   ├── terminals/        # daytona, modal, vercel
+│   ├── web/              # exa, firecrawl, parallel
 │   ├── memory/           # Memory-provider plugins (honcho, mem0, supermemory, ...)
 │   ├── context_engine/   # Context-engine plugins
-│   ├── model-providers/  # Inference backend plugins (openrouter, anthropic, gmi, ...)
 │   ├── kanban/           # Multi-agent board dispatcher + worker plugin
 │   ├── hermes-achievements/  # Gamified achievement tracking
 │   ├── observability/    # Metrics / traces / logs plugin
-│   ├── image_gen/        # Image-generation providers
-│   └── <others>/         # disk-cleanup, example-dashboard, google_meet, platforms,
-│                         #   spotify, strike-freedom-cockpit, ...
+│   └── <others>/         # dashboard, google_meet, spotify, strike-freedom-cockpit, ...
 ├── optional-skills/      # Heavier/niche skills shipped but NOT active by default
 ├── skills/               # Built-in skills bundled with the repo
 ├── ui-tui/               # Ink (React) terminal UI — `hermes --tui`
@@ -486,9 +492,102 @@ Activate with `/skin cyberpunk` or `display.skin: cyberpunk` in config.yaml.
 
 ## Plugins
 
-Hermes has two plugin surfaces. Both live under `plugins/` in the repo so
-repo-shipped plugins can be discovered alongside user-installed ones in
-`~/.hermes/plugins/` and pip-installed entry points.
+Hermes uses a **plugin-first architecture**: every optional capability (model
+providers, platform adapters, TTS/STT, terminal backends, image generation)
+lives in its own installable Python package under `plugins/`. The core
+codebase (`agent/`, `hermes_cli/`, `gateway/`, `tools/`) **never** imports
+from a `hermes_agent_*` plugin package directly. Instead, plugins register
+their capabilities into typed registries during `register()`, and the core
+queries those registries at runtime.
+
+Full architecture doc: `website/docs/developer-guide/plugin-architecture.md`
+
+### Workspace layout
+
+All 21 builtin plugins are uv workspace members — each has its own
+`pyproject.toml` (single source of truth for deps), `plugin.yaml`
+(directory-scanner manifest for dev mode), and `hermes_agent_<name>/` package
+with `register(ctx)`:
+
+```
+plugins/
+├── model-providers/        # anthropic, bedrock, azure-foundry
+├── platforms/              # telegram, slack, discord, feishu, dingtalk, matrix
+├── tts/                    # text-to-speech (Edge TTS + ElevenLabs)
+├── stt/                    # speech-to-text
+├── image_gen/fal_pkg/      # FAL image generation
+├── terminals/              # daytona, modal, vercel
+├── web/                    # exa, firecrawl, parallel
+├── memory/                 # honcho, hindsight
+├── dashboard/              # streamlit dashboard
+└── hermes-achievements/    # gamified achievement tracking
+```
+
+### The hermetic core boundary
+
+Core code MUST NOT import from `hermes_agent_*` packages. Instead it queries
+typed registries in `agent/plugin_registries.py`:
+
+```python
+# ❌ BAD — core directly imports plugin
+from hermes_agent_bedrock import has_aws_credentials
+
+# ✅ GOOD — core queries the registry
+from agent.plugin_registries import registries
+bedrock_auth = registries.get_auth_provider("bedrock")
+```
+
+Registry types: `auth_providers`, `transport_builders`, `platform_adapters`,
+`tool_providers`, `model_metadata`, `credential_pools`.
+
+Each plugin's `register(ctx)` populates the registries via `ctx.register_*()`:
+- `ctx.register_auth_provider(name, provider, ...)`
+- `ctx.register_transport(name, builder, ...)`
+- `ctx.register_platform(name, label, adapter_factory, check_fn, ...)`
+- `ctx.register_tool_provider(entry, ...)`
+- `ctx.register_model_metadata(entry, ...)`
+- `ctx.register_credential_pool(entry, ...)`
+- Plus existing: `register_tool()`, `register_hook()`, `register_cli_command()`,
+  `register_tts_provider()`, `register_transcription_provider()`,
+  `register_image_gen_provider()`, `register_video_gen_provider()`,
+  `register_context_engine()`
+
+### Plugin discovery
+
+Three discovery paths (same as before, now workspace-aware):
+1. **Directory scanner** — `plugins/`, `~/.hermes/plugins/`, `.hermes/plugins/`
+   (looks for `plugin.yaml`)
+2. **Entry points** — `[project.entry-points."hermes_agent.plugins"]`
+3. **uv workspace** — `uv sync --extra <name>` installs the plugin into venv
+
+### Dependency management
+
+- Each plugin's `pyproject.toml` is the **only** place its deps are declared
+- Root `pyproject.toml` maps extras to workspace members:
+  `telegram = ["hermes-agent-telegram"]`
+- `uv.lock` resolves the whole workspace (236 packages)
+- No `LAZY_DEPS`, no `ensure()`, no runtime `pip install`
+- Custom PEP 517 build backend (`_build_backend.py`) inlines plugin deps
+  at wheel build time for PyPI publishing
+
+### NixOS
+
+`loadWorkspace` discovers all workspace members from `uv.lock` automatically.
+`mkVirtualEnv { hermes-agent = ["all"] }` installs all plugins. Select specific
+plugins with `extraDependencyGroups = ["telegram", "anthropic"]`.
+
+### Tests
+
+Plugin tests live in `plugins/<category>/<name>/tests/`. The test runner
+discovers both `tests/` and `plugins/`. Running plugin tests requires the
+plugin to be installed (`uv sync --extra <name>`).
+
+### The rule
+
+**If it can be a plugin, it must be a plugin.** Adding optional capabilities
+to core files is a code review rejection. If the plugin surface doesn't
+support what you need, extend the surface (new registry type, new hook, new
+`ctx` method) — don't inline the capability.
 
 ### General plugins (`hermes_cli/plugins.py` + `plugins/<name>/`)
 
@@ -531,9 +630,14 @@ providers don't clutter `hermes --help`.
 **Rule (Teknium, May 2026):** plugins MUST NOT modify core files
 (`run_agent.py`, `cli.py`, `gateway/run.py`, `hermes_cli/main.py`, etc.).
 If a plugin needs a capability the framework doesn't expose, expand the
-generic plugin surface (new hook, new ctx method) — never hardcode
-plugin-specific logic into core. PR #5295 removed 95 lines of hardcoded
-honcho argparse from `main.py` for exactly this reason.
+generic plugin surface (new hook, new ctx method, new registry type) — never
+hardcode plugin-specific logic into core. PR #5295 removed 95 lines of
+hardcoded honcho argparse from `main.py` for exactly this reason.
+
+**Hermetic core boundary (May 2026):** core code (`agent/`, `hermes_cli/`,
+`gateway/`, `tools/`) MUST NOT import from `hermes_agent_*` plugin packages.
+Use the typed registries in `agent/plugin_registries.py` instead. See the
+**Plugins** section below for the full list of registry types.
 
 **No new in-tree memory providers (policy, May 2026):** the set of
 built-in memory providers under `plugins/memory/` is closed. New memory
@@ -1011,40 +1115,41 @@ def profile_env(tmp_path, monkeypatch):
 
 ## Testing
 
-**ALWAYS use `scripts/run_tests.sh`** — do not call `pytest` directly. The script enforces
-hermetic environment parity with CI (unset credential vars, TZ=UTC, LANG=C.UTF-8,
-`-n auto` xdist workers, in-tree subprocess-isolation plugin). Direct `pytest`
-on a 16+ core developer machine with API keys set diverges from CI in ways
-that have caused multiple "works locally, fails in CI" incidents (and the reverse).
+**ALWAYS use `scripts/run_tests.sh`** — do NOT call `pytest` directly on a directory.
+The script enforces hermetic environment parity with CI and provides per-file
+process isolation that prevents registry singleton / module-level state leakage
+between test files.
 
 ```bash
 scripts/run_tests.sh                                  # full suite, CI-parity
 scripts/run_tests.sh tests/gateway/                   # one directory
+scripts/run_tests.sh tests/agent/test_foo.py          # one file
 scripts/run_tests.sh tests/agent/test_foo.py::test_x  # one test
 scripts/run_tests.sh -v --tb=long                     # pass-through pytest flags
-scripts/run_tests.sh --no-isolate tests/foo/          # disable subprocess isolation (faster, for debugging)
 ```
 
-### Subprocess-per-test isolation
+For a **single test file or specific test**, bare `pytest` is fine:
 
-Every test runs in a freshly-spawned Python subprocess via the in-tree plugin
-at `tests/_isolate_plugin.py`. This means module-level dicts/sets and
-ContextVars from one test cannot leak into the next — the historic
-`_reset_module_state` autouse fixture is gone.
+```bash
+nix run nixpkgs#uv -- run python -m pytest tests/agent/test_foo.py -q
+nix run nixpkgs#uv -- run python -m pytest tests/agent/test_foo.py::test_x --tb=short
+```
 
-Implementation notes:
+Running bare `pytest` on a directory (e.g. `pytest tests/`) will print a warning
+from `conftest.py` telling you to use the script instead.
 
-- The plugin uses `multiprocessing.get_context("spawn")`, which works on
-  Linux, macOS, and Windows alike (POSIX `fork` is not used).
-- Per-test overhead is ~0.5–1.0s (Python startup + pytest collection). xdist
-  parallelism amortizes this across cores; on a 20-core box the full suite
-  finishes in roughly the same wall time as before, but flake-free.
-- `isolate_timeout` (configured in `pyproject.toml`) caps each test at 30s.
-  Hangs are killed and surfaced as a failure report.
-- Pass `--no-isolate` to disable isolation — useful when debugging a single
-  test interactively, or when you specifically want to verify state leakage.
-- The plugin disables itself in child processes (sentinel envvar
-  `HERMES_ISOLATE_CHILD=1`), so there's no fork-bomb risk.
+### Per-file process isolation
+
+`scripts/run_tests.sh` calls `scripts/run_tests_parallel.py`, which spawns one
+`python -m pytest <file>` subprocess per test **file** (not per test), giving each
+a fresh Python interpreter. This means module-level dicts/sets, ContextVars, and
+registry singletons from one test file cannot leak into another — no shared state
+between files, no xdist required.
+
+`HERMES_PARALLEL_RUNNER=1` is set in each subprocess so `conftest.py` knows tests
+are running under the managed runner. If you need to suppress the bare-pytest
+directory warning in a special case, set this variable yourself — but prefer the
+script.
 
 ### Why the wrapper (and why the old "just call pytest" doesn't work)
 
@@ -1056,31 +1161,13 @@ Five real sources of local-vs-CI drift the script closes:
 | HOME / `~/.hermes/` | Your real config+auth.json | Temp dir per test |
 | Timezone | Local TZ (PDT etc.) | UTC |
 | Locale | Whatever is set | C.UTF-8 |
-| xdist workers | `-n auto` = all cores | `-n auto` (safe — subprocess isolation prevents cross-worker flakes) |
+| File isolation | Shared interpreter — state leaks between files | One subprocess per file |
 
-`tests/conftest.py` also enforces points 1-4 as an autouse fixture so ANY pytest
-invocation (including IDE integrations) gets hermetic behavior — but the wrapper
-is belt-and-suspenders.
+`tests/conftest.py` also enforces the credential/TZ/locale points as an autouse
+fixture so ANY pytest invocation (including IDE integrations) gets hermetic
+behavior — but the wrapper adds per-file process isolation on top.
 
-### Running without the wrapper (only if you must)
-
-If you can't use the wrapper (e.g. inside an IDE that shells pytest directly),
-at minimum activate the venv. The isolation plugin loads automatically from
-`addopts` in `pyproject.toml`, so you get the same per-test process isolation
-either way.
-
-```bash
-source .venv/bin/activate   # or: source venv/bin/activate
-python -m pytest tests/ -q
-```
-
-If you need to bypass isolation for fast feedback while debugging:
-
-```bash
-python -m pytest tests/agent/test_foo.py -q --no-isolate
-```
-
-Always run the full suite before pushing changes.
+Always run the full suite via `scripts/run_tests.sh` before pushing changes.
 
 ### Don't write change-detector tests
 

CONTRIBUTING.md

@@ -121,12 +121,11 @@ hermes chat -q "Hello"
 ### Run tests
 
 ```bash
-# Preferred — matches CI (hermetic env, 4 xdist workers); see AGENTS.md
+# Preferred — matches CI (hermetic env, per-file process isolation); see AGENTS.md
 scripts/run_tests.sh
 
-# Alternative (activate the venv first). The wrapper is still recommended
-# for parity with GitHub Actions before you open a PR:
-pytest tests/ -v
+# For a single file or specific test, bare pytest is also fine:
+# python -m pytest tests/agent/test_foo.py -q
 ```
 
 ---
@@ -857,7 +856,7 @@ refactor/description   # Code restructuring
 
 ### Before submitting
 
-1. **Run tests**: `scripts/run_tests.sh` (recommended; same as CI) or `pytest tests/ -v` with the project venv activated
+1. **Run tests**: `scripts/run_tests.sh` (recommended; same as CI — hermetic env + per-file process isolation)
 2. **Test manually**: Run `hermes` and exercise the code path you changed
 3. **Check cross-platform impact**: If you touch file I/O, process management, or terminal handling, consider macOS, Linux, and WSL2
 4. **Keep PRs focused**: One logical change per PR. Don't mix a bug fix with a refactor with a new feature.

Dockerfile

@@ -25,7 +25,7 @@ ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
 # hermes process, the dashboard, and per-profile gateways.
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-    ca-certificates curl iputils-ping python3 python-is-python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli xz-utils && \
+    ca-certificates curl python3 python-is-python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli xz-utils && \
     rm -rf /var/lib/apt/lists/*
 
 # ---------- s6-overlay install ----------

MANIFEST.in

@@ -1,9 +1,4 @@
 graft skills
 graft optional-skills
-# Bundled plugin manifests (plugin.yaml / plugin.yml). Without these the
-# PluginManager scan (hermes_cli/plugins.py) finds zero plugins on installs
-# built from the sdist (e.g. Homebrew, downstream packagers). package-data
-# below covers the wheel; this covers the sdist. See #34034 / #28149.
-recursive-include plugins plugin.yaml plugin.yml
 global-exclude __pycache__
 global-exclude *.py[cod]

README.zh-CN.md

@@ -179,7 +179,7 @@ curl -LsSf https://astral.sh/uv/install.sh | sh
 uv venv venv --python 3.11
 source venv/bin/activate
 uv pip install -e ".[all,dev]"
-python -m pytest tests/ -q
+scripts/run_tests.sh
 ```
 
 ---

RELEASE_v0.15.1.md

@@ -1,110 +0,0 @@
-# Hermes Agent v0.15.1 (v2026.5.29)
-
-**Release Date:** May 29, 2026
-**Since v0.15.0:** 28 commits · 21 merged PRs · hotfix release · 9 contributors
-
-> **The Patch Release.** A same-day hotfix for v0.15.0. Headline fix: the dashboard infinite-reload loop that hit anyone running v0.15.0 in loopback mode (Docker, hosted Hermes, fresh installs). A handful of other v0.15.0 follow-ups go along for the ride — kanban worker SIGTERM, `/model` picker unification, `/yolo` session bypass, the full 19,932-entry skills.sh catalog, `.md` media delivery restoration, gateway probe-stepdown safety, web-URL redaction passthrough, kanban worker vision on referenced images, hindsight observation-default. Docker users get an explicit `--insecure` opt-in env var (no more bind-host inference), MCP server bare-command PATH resolution, and arm64 PR-build cache fixes.
-
----
-
-## ✨ Highlights
-
-- **Dashboard 401 reload loop fixed** — In loopback mode the dashboard's identity probe (`/api/auth/me`) returns 401 by design, but v0.15.0's stale-token reload guard treated every 401 as a rotated session token and full-page-reloaded to pick up a fresh one. Every successful sibling call cleared the one-shot reload guard, so the page reload-looped forever (Firefox: "Navigated to /sessions" storm; Chrome: React re-render storm). Fix adds an `allowUnauthorized` opt-out to `fetchJSON` that skips only the loopback stale-token reload — 401 still throws so `AuthWidget` swallows it, gated-mode `login_url` redirects are unaffected. Closes [#34206](https://github.com/NousResearch/hermes-agent/issues/34206), [#34202](https://github.com/NousResearch/hermes-agent/issues/34202). ([#30698](https://github.com/NousResearch/hermes-agent/pull/30698) — @austinpickett)
-
-- **Docker dashboard `--insecure` is now an explicit env opt-in, never derived from bind host** — Previously the Docker entrypoint inferred `--insecure` when the dashboard bound to a non-loopback host. That conflated "I want LAN access" with "I want to disable the same-origin guard." The fix splits them: bind host is bind host, and disabling the dashboard's loopback auth requires an explicit `HERMES_DASHBOARD_INSECURE=1`. Existing setups that genuinely wanted insecure binding must now set the env var. ([#34188](https://github.com/NousResearch/hermes-agent/pull/34188), [#34204](https://github.com/NousResearch/hermes-agent/pull/34204) — @benbarclay)
-
-- **MCP bare command resolution under Docker** — MCP servers configured with bare commands (`npx`, `npm`, `node`) now resolve against `/usr/local/bin` so they actually launch inside the Docker image where those binaries live. v0.15.0 left these failing silently in containers when the agent's effective PATH didn't include the Node toolchain location. ([#34186](https://github.com/NousResearch/hermes-agent/pull/34186) — @benbarclay)
-
-- **Skills page sidebar / source pills restored** — A stale `useMemo` dependency in the new dashboard skills page collapsed the source pills and category sidebar to "All" only. Fixed; both surfaces now reflect the live catalog state. ([#34194](https://github.com/NousResearch/hermes-agent/pull/34194))
-
-- **Kanban worker can be killed again** — `SIGTERM` on a kanban worker was being absorbed by an intermediate process and the worker stayed running. Closes [#28181](https://github.com/NousResearch/hermes-agent/issues/28181). ([#34045](https://github.com/NousResearch/hermes-agent/pull/34045))
-
-- **Full skills.sh catalog (858 → 19,932 entries)** — The skills hub page was pulling a partial paginated catalog. The fetch now walks the sitemap, so all 19,932 skills.sh entries surface in the picker instead of just the first 858. ([#34025](https://github.com/NousResearch/hermes-agent/pull/34025))
-
----
-
-## 🐛 Bug Fixes
-
-### Dashboard / Web
-
-- **`/api/auth/me` 401 no longer triggers reload loop** in loopback mode — ([#30698](https://github.com/NousResearch/hermes-agent/pull/30698) — @austinpickett)
-- **Skills page source pills + category sidebar restored** — stale `useMemo` dep ([#34194](https://github.com/NousResearch/hermes-agent/pull/34194))
-
-### Docker
-
-- **`--insecure` is now explicit opt-in via env var**, not derived from bind host ([#34188](https://github.com/NousResearch/hermes-agent/pull/34188) — @benbarclay)
-- **Dashboard test suite repaired** to match the insecure-opt-in fix ([#34204](https://github.com/NousResearch/hermes-agent/pull/34204) — @benbarclay)
-- **arm64 PR builds skip the GHA cache** to avoid cache-thrash on cross-arch builders ([#33704](https://github.com/NousResearch/hermes-agent/pull/33704) — @BROCCOLO1D)
-
-### MCP
-
-- **Bare `npx`/`npm`/`node` resolve against `/usr/local/bin`** for Docker compatibility ([#34186](https://github.com/NousResearch/hermes-agent/pull/34186) — @benbarclay)
-
-### Kanban
-
-- **Worker SIGTERM actually terminates the process** ([#34045](https://github.com/NousResearch/hermes-agent/pull/34045))
-- **Workers receive images referenced in task bodies** for vision-capable models ([#34210](https://github.com/NousResearch/hermes-agent/pull/34210))
-
-### Gateway
-
-- **`.md` files deliver again** — media-delivery validation defaults to denylist-only instead of an overly-narrow allowlist ([#34022](https://github.com/NousResearch/hermes-agent/pull/34022))
-- **Probe stepdown safety** — on a context-overflow without an explicit provider context limit, the agent no longer steps down to a smaller model based on an unknown ceiling (salvage of [#33673](https://github.com/NousResearch/hermes-agent/pull/33673)) ([#33826](https://github.com/NousResearch/hermes-agent/pull/33826))
-
-### CLI
-
-- **`/yolo` mid-session enables the per-session bypass** instead of just toggling the env var (which the running agent had already snapshotted) ([#33931](https://github.com/NousResearch/hermes-agent/pull/33931) — @kshitijk4poor)
-- **`/model` and `hermes model` show the same list**, plus disk cache for picker startup ([#33867](https://github.com/NousResearch/hermes-agent/pull/33867))
-
-### Skills
-
-- **Full skills.sh catalog via sitemap** — 858 → 19,932 entries ([#34025](https://github.com/NousResearch/hermes-agent/pull/34025))
-
-### Redaction
-
-- **Web URLs pass through unchanged** — the redactor was eating query parameters that looked credential-shaped ([#34029](https://github.com/NousResearch/hermes-agent/pull/34029))
-
----
-
-## ✨ Small Features
-
-- **Hindsight default narrowed to observation-only** for `recall_types` — tool path is also narrowed ([#34079](https://github.com/NousResearch/hermes-agent/pull/34079) — @nicoloboschi, follow-up [#34091](https://github.com/NousResearch/hermes-agent/pull/4df62d239e38bf8c212a595721c9c01e176f6c3a) — @kshitijk4poor)
-- **Memory providers receive completed-turn message context** — salvage of [#28065](https://github.com/NousResearch/hermes-agent/pull/28065) ([#34097](https://github.com/NousResearch/hermes-agent/pull/34097) — @kshitijk4poor, credit to @devwdave)
-
----
-
-## 📚 Documentation
-
-- **`--no-supervise` / `HERMES_GATEWAY_NO_SUPERVISE` documented** in the reference docs (follow-up to [#33583](https://github.com/NousResearch/hermes-agent/pull/33583)) ([#33751](https://github.com/NousResearch/hermes-agent/pull/33751) — @r266-tech)
-
----
-
-## 🛠️ Infrastructure
-
-- **Vercel deploy workflow accepts `workflow_dispatch`** so docs deploys can be manually triggered ([#34081](https://github.com/NousResearch/hermes-agent/pull/34081))
-- **`@nous-research/ui` bumped to 0.18.2** (Nix `npmDepsHash` also updated to match) ([#34193](https://github.com/NousResearch/hermes-agent/pull/34193) follow-ups — @austinpickett)
-
----
-
-## 👥 Contributors
-
-### Core
-- @teknium1
-
-### Community
-- @austinpickett — dashboard 401 reload-loop fix (the headline), `@nous-research/ui` bump, Nix `npmDepsHash` updates
-- @benbarclay — Docker `--insecure` opt-in, MCP bare-command resolution, dashboard test repair
-- @kshitijk4poor — `/yolo` session bypass, completed-turn memory context salvage, hindsight follow-up docs
-- @nicoloboschi — hindsight `recall_types` observation default
-- @BROCCOLO1D — arm64 PR build cache fix
-- @r266-tech — `--no-supervise` reference docs
-- @yangguangjin — probe stepdown safety (salvage of @yanghd's #33673)
-- @devwdave — completed-turn memory context (credited via salvage)
-- @andrewhosf — co-author
-
-### Issue Reporters (the 401 loop)
-- @routesmith ([#34206](https://github.com/NousResearch/hermes-agent/issues/34206))
-- @beeaton ([#34202](https://github.com/NousResearch/hermes-agent/issues/34202))
-
----
-
-**Full Changelog**: [v2026.5.28...v2026.5.29](https://github.com/NousResearch/hermes-agent/compare/v2026.5.28...v2026.5.29)

_build_backend.py

@@ -0,0 +1,183 @@
+"""Custom PEP 517 build backend for hermes-agent.
+
+At wheel build time, rewrites [project.optional-dependencies] so that
+plugin extras (e.g. ``anthropic = ["hermes-agent-anthropic"]``) are
+inlined with the actual deps from each plugin's pyproject.toml.
+
+In the source repo (and on Nix), uv resolves workspace members natively
+so this backend is NOT used — it's only invoked when building a wheel
+for PyPI publication.
+
+Usage in pyproject.toml::
+
+    [build-system]
+    requires = ["setuptools>=61.0"]
+    build-backend = "_build_backend"
+    backend-path = ["."]
+
+How it works:
+1.  ``build_wheel`` intercepts the call before setuptools sees pyproject.toml.
+2.  It reads the workspace member dirs from [tool.uv.workspace].members.
+3.  For each member, it reads the member's pyproject.toml and extracts
+    ``project.dependencies`` (excluding the ``hermes-agent`` base dep).
+4.  It rewrites the main pyproject.toml's optional-dependencies to inline
+    those deps instead of the workspace member references.
+5.  It writes a temporary pyproject.toml, delegates to
+    ``setuptools.build_meta.build_wheel``, then restores the original.
+"""
+
+from __future__ import annotations
+
+import os
+import shutil
+import tempfile
+from pathlib import Path
+from typing import Any
+
+import tomllib
+
+# The original setuptools backend we delegate to.
+_BACKEND = "setuptools.build_meta"
+
+
+def _load_pyproject(path: Path) -> dict:
+    with path.open("rb") as f:
+        return tomllib.load(f)
+
+
+def _save_pyproject(path: Path, data: dict) -> None:
+    """Write a pyproject.toml. Uses a simple serializer since we only
+    need to preserve the structure enough for setuptools to parse."""
+    import tomli_w
+    with path.open("wb") as f:
+        tomli_w.dump(data, f)
+
+
+def _inline_plugin_deps(root: Path, data: dict) -> dict:
+    """Rewrite optional-dependencies to inline plugin deps.
+
+    Maps each plugin extra (e.g. ``anthropic = ["hermes-agent-anthropic"]``)
+    to the actual deps from that plugin's pyproject.toml, minus the
+    ``hermes-agent`` base dependency.
+    """
+    opt_deps = data.get("project", {}).get("optional-dependencies", {})
+    workspace = data.get("tool", {}).get("uv", {}).get("workspace", {})
+    members = workspace.get("members", [])
+
+    # Build a map: package name → (member_dir, pyproject_data)
+    pkg_to_deps: dict[str, list[str]] = {}
+    for member_glob in members:
+        for member_dir in sorted(root.glob(member_glob)):
+            pptoml = member_dir / "pyproject.toml"
+            if not pptoml.exists():
+                continue
+            member_data = _load_pyproject(pptoml)
+            pkg_name = member_data.get("project", {}).get("name", "")
+            if not pkg_name:
+                continue
+            # Extract deps, excluding the base hermes-agent dependency
+            raw_deps = member_data.get("project", {}).get("dependencies", [])
+            filtered = [
+                d for d in raw_deps
+                if not d.replace(" ", "").startswith("hermes-agent")
+            ]
+            pkg_to_deps[pkg_name] = filtered
+
+    # Rewrite optional-dependencies
+    new_opt_deps = {}
+    for extra_name, specs in opt_deps.items():
+        new_specs = []
+        for spec in specs:
+            # Check if this spec references a workspace member package
+            if spec in pkg_to_deps:
+                # Inline the plugin's deps
+                new_specs.extend(pkg_to_deps[spec])
+            else:
+                new_specs.append(spec)
+        new_opt_deps[extra_name] = new_specs
+
+    data["project"]["optional-dependencies"] = new_opt_deps
+
+    # Remove [tool.uv] section — it's not valid in a published wheel
+    if "uv" in data.get("tool", {}):
+        del data["tool"]["uv"]
+
+    return data
+
+
+# ---------------------------------------------------------------------------
+# PEP 517 hooks
+# ---------------------------------------------------------------------------
+
+def build_wheel(wheel_directory: str, config_settings: dict[str, Any] | None = None, metadata_directory: str | None = None) -> str:
+    """Build a wheel with inlined plugin deps."""
+    root = Path.cwd()
+    pyproject_path = root / "pyproject.toml"
+
+    # Read and rewrite
+    data = _load_pyproject(pyproject_path)
+    data = _inline_plugin_deps(root, data)
+
+    # Write a temporary pyproject.toml, build, then restore
+    backup = pyproject_path.with_suffix(".toml.bak")
+    shutil.copy2(pyproject_path, backup)
+    try:
+        _save_pyproject(pyproject_path, data)
+
+        # Delegate to setuptools
+        import importlib
+        backend = importlib.import_module(_BACKEND)
+        return backend.build_wheel(wheel_directory, config_settings)
+    finally:
+        shutil.copy2(backup, pyproject_path)
+        backup.unlink()
+
+
+def build_sdist(sdist_directory: str, config_settings: dict[str, Any] | None = None) -> str:
+    """Build an sdist — no rewriting needed."""
+    import importlib
+    backend = importlib.import_module(_BACKEND)
+    return backend.build_sdist(sdist_directory, config_settings)
+
+
+def get_requires_for_build_wheel(config_settings: dict[str, Any] | None = None) -> list[str]:
+    return ["setuptools>=61.0", "tomli_w"]
+
+
+def get_requires_for_build_sdist(config_settings: dict[str, Any] | None = None) -> list[str]:
+    return ["setuptools>=61.0"]
+
+
+def prepare_metadata_for_build_wheel(metadata_directory: str, config_settings: dict[str, Any] | None = None) -> str:
+    """Prepare metadata with inlined plugin deps."""
+    root = Path.cwd()
+    pyproject_path = root / "pyproject.toml"
+
+    data = _load_pyproject(pyproject_path)
+    data = _inline_plugin_deps(root, data)
+
+    backup = pyproject_path.with_suffix(".toml.bak")
+    shutil.copy2(pyproject_path, backup)
+    try:
+        _save_pyproject(pyproject_path, data)
+
+        import importlib
+        backend = importlib.import_module(_BACKEND)
+        return backend.prepare_metadata_for_build_wheel(metadata_directory, config_settings)
+    finally:
+        shutil.copy2(backup, pyproject_path)
+        backup.unlink()
+
+
+def build_editable(wheel_directory: str, config_settings: dict[str, Any] | None = None, metadata_directory: str | None = None) -> str:
+    """Build an editable install — no rewriting needed (dev mode)."""
+    import importlib
+    backend = importlib.import_module(_BACKEND)
+    kwargs: dict[str, Any] = {"config_settings": config_settings}
+    if metadata_directory is not None:
+        kwargs["metadata_directory"] = metadata_directory
+    return backend.build_editable(wheel_directory, **kwargs)
+
+
+def get_requires_for_build_editable(config_settings: dict[str, Any] | None = None) -> list[str]:
+    return ["setuptools>=61.0"]

acp_adapter/tools.py

@@ -907,6 +907,72 @@ def _build_polished_completion_content(
     return [_text(text)]
 
 
+def _build_patch_mode_content(patch_text: str) -> List[Any]:
+    """Parse V4A patch mode input into ACP diff blocks when possible."""
+    if not patch_text:
+        return [acp.tool_content(acp.text_block(""))]
+
+    try:
+        from tools.patch_parser import OperationType, parse_v4a_patch
+
+        operations, error = parse_v4a_patch(patch_text)
+        if error or not operations:
+            return [acp.tool_content(acp.text_block(patch_text))]
+
+        content: List[Any] = []
+        for op in operations:
+            if op.operation == OperationType.UPDATE:
+                old_chunks: list[str] = []
+                new_chunks: list[str] = []
+                for hunk in op.hunks:
+                    old_lines = [line.content for line in hunk.lines if line.prefix in {" ", "-"}]
+                    new_lines = [line.content for line in hunk.lines if line.prefix in {" ", "+"}]
+                    if old_lines or new_lines:
+                        old_chunks.append("\n".join(old_lines))
+                        new_chunks.append("\n".join(new_lines))
+
+                old_text = "\n...\n".join(chunk for chunk in old_chunks if chunk)
+                new_text = "\n...\n".join(chunk for chunk in new_chunks if chunk)
+                if old_text or new_text:
+                    content.append(
+                        acp.tool_diff_content(
+                            path=op.file_path,
+                            old_text=old_text or None,
+                            new_text=new_text or "",
+                        )
+                    )
+                continue
+
+            if op.operation == OperationType.ADD:
+                added_lines = [line.content for hunk in op.hunks for line in hunk.lines if line.prefix == "+"]
+                content.append(
+                    acp.tool_diff_content(
+                        path=op.file_path,
+                        new_text="\n".join(added_lines),
+                    )
+                )
+                continue
+
+            if op.operation == OperationType.DELETE:
+                content.append(
+                    acp.tool_diff_content(
+                        path=op.file_path,
+                        old_text=f"Delete file: {op.file_path}",
+                        new_text="",
+                    )
+                )
+                continue
+
+            if op.operation == OperationType.MOVE:
+                content.append(
+                    acp.tool_content(acp.text_block(f"Move file: {op.file_path} -> {op.new_path}"))
+                )
+
+        return content or [acp.tool_content(acp.text_block(patch_text))]
+    except Exception:
+        return [acp.tool_content(acp.text_block(patch_text))]
+
+
 def _strip_diff_prefix(path: str) -> str:
     raw = str(path or "").strip()
     if raw.startswith(("a/", "b/")):

acp_registry/agent.json

@@ -1,7 +1,7 @@
 {
   "id": "hermes-agent",
   "name": "Hermes Agent",
-  "version": "0.15.1",
+  "version": "0.15.0",
   "description": "Self-improving open-source AI agent by Nous Research with ACP editor integration, persistent memory, skills, and rich tool support.",
   "repository": "https://github.com/NousResearch/hermes-agent",
   "website": "https://hermes-agent.nousresearch.com/docs/user-guide/features/acp",
@@ -9,7 +9,7 @@
   "license": "MIT",
   "distribution": {
     "uvx": {
-      "package": "hermes-agent[acp]==0.15.1",
+      "package": "hermes-agent[acp]==0.15.0",
       "args": ["hermes-acp"]
     }
   }

agent/account_usage.py

@@ -6,7 +6,9 @@ from typing import Any, Optional
 
 import httpx
 
-from agent.anthropic_adapter import _is_oauth_token, resolve_anthropic_token
+from agent.plugin_registries import registries
+_is_oauth_token = registries.get_provider_service("anthropic", "_is_oauth_token")
+resolve_anthropic_token = registries.get_provider_service("anthropic", "resolve_anthropic_token")
 from hermes_cli.auth import _read_codex_tokens, resolve_codex_runtime_credentials
 from hermes_cli.runtime_provider import resolve_runtime_provider
 
@@ -176,7 +178,7 @@ def _fetch_anthropic_account_usage() -> Optional[AccountUsageSnapshot]:
     token = (resolve_anthropic_token() or "").strip()
     if not token:
         return None
-    if not _is_oauth_token(token):
+    if _is_oauth_token is not None and not _is_oauth_token(token):
         return AccountUsageSnapshot(
             provider="anthropic",
             source="oauth_usage_api",

agent/agent_init.py

@@ -27,6 +27,7 @@ import threading
 import time
 import uuid
 from datetime import datetime
+from pathlib import Path
 from typing import Any, Dict, List, Optional
 from urllib.parse import urlparse, parse_qs, urlunparse
 
@@ -36,6 +37,7 @@ from agent.memory_manager import StreamingContextScrubber
 from agent.model_metadata import (
     MINIMUM_CONTEXT_LENGTH,
     fetch_model_metadata,
+    get_model_context_length,
     is_local_endpoint,
     query_ollama_num_ctx,
 )
@@ -50,6 +52,7 @@ from agent.tool_guardrails import (
 from hermes_cli.config import cfg_get
 from hermes_cli.timeouts import get_provider_request_timeout
 from hermes_constants import get_hermes_home
+from model_tools import check_toolset_requirements, get_tool_definitions
 from utils import base_url_host_matches
 
 # Use the same logger name as run_agent so tests patching ``run_agent.logger``
@@ -401,7 +404,7 @@ def init_agent(
     agent.status_callback = status_callback
     agent.tool_gen_callback = tool_gen_callback
 
-    
+
     # Tool execution state — allows _vprint during tool execution
     # even when stream consumers are registered (no tokens streaming then)
     agent._executing_tools = False
@@ -434,12 +437,12 @@ def init_agent(
     # their tids explicitly.
     agent._tool_worker_threads: set[int] = set()
     agent._tool_worker_threads_lock = threading.Lock()
-    
+
     # Subagent delegation state
     agent._delegate_depth = 0        # 0 = top-level agent, incremented for children
     agent._active_children = []      # Running child AIAgents (for interrupt propagation)
     agent._active_children_lock = threading.Lock()
-    
+
     # Store OpenRouter provider preferences
     agent.providers_allowed = providers_allowed
     agent.providers_ignored = providers_ignored
@@ -452,7 +455,7 @@ def init_agent(
     # Store toolset filtering options
     agent.enabled_toolsets = enabled_toolsets
     agent.disabled_toolsets = disabled_toolsets
-    
+
     # Model response configuration
     agent.max_tokens = max_tokens  # None = use model default
     agent.reasoning_config = reasoning_config  # None = use default (medium for OpenRouter)
@@ -460,7 +463,7 @@ def init_agent(
     agent.request_overrides = dict(request_overrides or {})
     agent.prefill_messages = prefill_messages or []  # Prefilled conversation turns
     agent._force_ascii_payload = False
-    
+
     # Anthropic prompt caching: auto-enabled for Claude models on native
     # Anthropic, OpenRouter, and third-party gateways that speak the
     # Anthropic protocol (``api_mode == 'anthropic_messages'``). Reduces
@@ -532,7 +535,7 @@ def init_agent(
         # console. Any future noise reduction belongs at the
         # handler level inside hermes_logging.py, not here.
         pass
-    
+
     # Internal stream callback (set during streaming TTS).
     # Initialized here so _vprint can reference it before run_conversation.
     agent._stream_callback = None
@@ -582,12 +585,14 @@ def init_agent(
     _provider_timeout = get_provider_request_timeout(agent.provider, agent.model)
 
     if agent.api_mode == "anthropic_messages":
-        from agent.anthropic_adapter import build_anthropic_client, resolve_anthropic_token
+        from agent.plugin_registries import registries
+        build_anthropic_client = registries.get_provider_service("anthropic", "build_anthropic_client")
+        resolve_anthropic_token = registries.get_provider_service("anthropic", "resolve_anthropic_token")
         # Bedrock + Claude → use AnthropicBedrock SDK for full feature parity
         # (prompt caching, thinking budgets, adaptive thinking).
         _is_bedrock_anthropic = agent.provider == "bedrock"
         if _is_bedrock_anthropic:
-            from agent.anthropic_adapter import build_anthropic_bedrock_client
+            build_anthropic_bedrock_client = registries.get_provider_service("anthropic", "build_anthropic_bedrock_client")
             _region_match = re.search(r"bedrock-runtime\.([a-z0-9-]+)\.", base_url or "")
             _br_region = _region_match.group(1) if _region_match else "us-east-1"
             agent._bedrock_region = _br_region
@@ -641,8 +646,8 @@ def init_agent(
             # so injects Claude-Code identity headers and system prompts
             # that cause 401/403 on their endpoints.  Guards #1739 and
             # the third-party identity-injection bug.
-            from agent.anthropic_adapter import _is_oauth_token as _is_oat
-            agent._is_anthropic_oauth = _is_oat(effective_key) if (_is_native_anthropic and isinstance(effective_key, str)) else False
+            _is_oauth_token = registries.get_provider_service("anthropic", "_is_oauth_token")
+            agent._is_anthropic_oauth = _is_oauth_token(effective_key) if (_is_oauth_token is not None and _is_native_anthropic and isinstance(effective_key, str)) else False
             agent._anthropic_client = build_anthropic_client(effective_key, base_url, timeout=_provider_timeout)
             # No OpenAI client needed for Anthropic mode
             agent.client = None
@@ -654,9 +659,10 @@ def init_agent(
                 # The Anthropic adapter installs an httpx event hook
                 # that mints a fresh JWT per request — we never
                 # invoke or inspect the callable in the banner.
-                from agent.azure_identity_adapter import is_token_provider
+                from agent.plugin_registries import registries
+                is_token_provider = registries.get_provider_service("azure", "is_token_provider")
 
-                if is_token_provider(effective_key):
+                if is_token_provider and is_token_provider(effective_key):
                     print("🔑 Using credentials: Microsoft Entra ID")
                 elif isinstance(effective_key, str) and len(effective_key) > 12:
                     print(f"🔑 Using token: {effective_key[:8]}...{effective_key[-4:]}")
@@ -866,10 +872,11 @@ def init_agent(
                 # provider (Azure Foundry). The OpenAI SDK mints a
                 # fresh JWT per request internally — the banner
                 # never invokes or inspects the callable.
-                from agent.azure_identity_adapter import is_token_provider
+                from agent.plugin_registries import registries
+                is_token_provider = registries.get_provider_service("azure", "is_token_provider")
 
                 key_used = client_kwargs.get("api_key", "none")
-                if is_token_provider(key_used):
+                if is_token_provider and is_token_provider(key_used):
                     print("🔑 Using credentials: Microsoft Entra ID")
                 elif isinstance(key_used, str) and key_used and key_used != "dummy-key" and len(key_used) > 12:
                     print(f"🔑 Using API key: {key_used[:8]}...{key_used[-4:]}")
@@ -877,7 +884,7 @@ def init_agent(
                     print("⚠️  Warning: API key appears invalid or missing")
         except Exception as e:
             raise RuntimeError(f"Failed to initialize OpenAI client: {e}")
-    
+
     # Provider fallback chain — ordered list of backup providers tried
     # when the primary is exhausted (rate-limit, overload, connection
     # failure).  Supports both legacy single-dict ``fallback_model`` and
@@ -909,7 +916,7 @@ def init_agent(
         disabled_toolsets=disabled_toolsets,
         quiet_mode=agent.quiet_mode,
     )
-    
+
     # Show tool configuration and store valid tool names for validation
     agent.valid_tool_names = set()
     if agent.tools:
@@ -942,16 +949,16 @@ def init_agent(
         missing_reqs = [name for name, available in requirements.items() if not available]
         if missing_reqs:
             print(f"⚠️  Some tools may not work due to missing requirements: {missing_reqs}")
-    
+
     # Show trajectory saving status
     if agent.save_trajectories and not agent.quiet_mode:
         print("📝 Trajectory saving enabled")
-    
+
     # Show ephemeral system prompt status
     if agent.ephemeral_system_prompt and not agent.quiet_mode:
         prompt_preview = agent.ephemeral_system_prompt[:60] + "..." if len(agent.ephemeral_system_prompt) > 60 else agent.ephemeral_system_prompt
         print(f"🔒 Ephemeral system prompt: '{prompt_preview}' (not saved to trajectories)")
-    
+
     # Show prompt caching status
     if agent._use_prompt_caching and not agent.quiet_mode:
         if agent._use_native_cache_layout and agent.provider == "anthropic":
@@ -961,7 +968,7 @@ def init_agent(
         else:
             source = "Claude via OpenRouter"
         print(f"💾 Prompt caching: ENABLED ({source}, {agent._cache_ttl} TTL)")
-    
+
     # Session logging setup - auto-save conversation trajectories for debugging
     agent.session_start = datetime.now()
     if session_id:
@@ -1001,7 +1008,7 @@ def init_agent(
         pass
     # logs_dir is retained unconditionally for request_dump_*.json (debug
     # breadcrumb path written by agent_runtime_helpers.dump_api_request_debug).
-    
+
     # Track conversation messages for session logging
     agent._session_messages: List[Dict[str, Any]] = []
     # Responses encrypted reasoning replay state.  Some OpenAI-compatible
@@ -1013,10 +1020,10 @@ def init_agent(
     agent._codex_reasoning_replay_enabled = True
     agent._memory_write_origin = "assistant_tool"
     agent._memory_write_context = "foreground"
-    
+
     # Cached system prompt -- built once per session, only rebuilt on compression
     agent._cached_system_prompt: Optional[str] = None
-    
+
     # Filesystem checkpoint manager (transparent — not a tool)
     from tools.checkpoint_manager import CheckpointManager
     agent._checkpoint_mgr = CheckpointManager(
@@ -1025,7 +1032,7 @@ def init_agent(
         max_total_size_mb=checkpoint_max_total_size_mb,
         max_file_size_mb=checkpoint_max_file_size_mb,
     )
-    
+
     # SQLite session store (optional -- provided by CLI or gateway)
     agent._session_db = session_db
     agent._parent_session_id = parent_session_id
@@ -1036,11 +1043,11 @@ def init_agent(
         "reasoning_config": reasoning_config,
         "max_tokens": max_tokens,
     }
-    
+
     # In-memory todo list for task planning (one per agent/session)
     from tools.todo_tool import TodoStore
     agent._todo_store = TodoStore()
-    
+
     # Load config once for memory, skills, and compression sections
     try:
         from hermes_cli.config import load_config as _load_agent_config
@@ -1082,7 +1089,7 @@ def init_agent(
                 agent._memory_store.load_from_disk()
         except Exception:
             pass  # Memory is optional -- don't break agent init
-    
+
 
 
     # Memory provider plugin (external — one at a time, alongside built-in)
@@ -1198,18 +1205,6 @@ def init_agent(
         _agent_section = {}
     agent._tool_use_enforcement = _agent_section.get("tool_use_enforcement", "auto")
 
-    # Universal task-completion guidance toggle.  Default True.  Surfaced
-    # as a separate flag from tool_use_enforcement because the guidance
-    # applies to ALL models, not just the model families enforcement
-    # targets.
-    agent._task_completion_guidance = bool(_agent_section.get("task_completion_guidance", True))
-
-    # Local Python toolchain probe toggle.  Default True.  When False,
-    # the probe is skipped entirely (no subprocess calls, no system-prompt
-    # line).  Useful for users on exotic setups where the probe heuristics
-    # are noisy.
-    agent._environment_probe = bool(_agent_section.get("environment_probe", True))
-
     # App-level API retry count (wraps each model API call).  Default 3,
     # overridable via agent.api_max_retries in config.yaml.  See #11616.
     try:
@@ -1471,6 +1466,7 @@ def init_agent(
 
     # Reject models whose context window is below the minimum required
     # for reliable tool-calling workflows (64K tokens).
+    from agent.model_metadata import MINIMUM_CONTEXT_LENGTH
     _ctx = getattr(agent.context_compressor, "context_length", 0)
     if _ctx and _ctx < MINIMUM_CONTEXT_LENGTH:
         raise ValueError(
@@ -1553,7 +1549,7 @@ def init_agent(
     agent.session_estimated_cost_usd = 0.0
     agent.session_cost_status = "unknown"
     agent.session_cost_source = "none"
-    
+
     # ── Ollama num_ctx injection ──
     # Ollama defaults to 2048 context regardless of the model's capabilities.
     # When running against an Ollama server, detect the model's max context

agent/agent_runtime_helpers.py

@@ -25,17 +25,24 @@ from __future__ import annotations
 import copy
 import json
 import logging
+import os
 import re
+import threading
 import time
+import uuid
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Tuple
 
 from hermes_cli.timeouts import get_provider_request_timeout
+from agent.message_sanitization import (
+    _repair_tool_call_arguments,
+    _sanitize_surrogates,
+)
 from agent.tool_dispatch_helpers import _trajectory_normalize_msg, make_tool_result_message
 from agent.trajectory import convert_scratchpad_to_think
 from agent.credential_pool import STATUS_EXHAUSTED
-from agent.error_classifier import FailoverReason
+from agent.error_classifier import classify_api_error, FailoverReason
 from utils import base_url_host_matches, base_url_hostname, env_var_enabled, atomic_json_write
 
 logger = logging.getLogger(__name__)
@@ -759,7 +766,8 @@ def try_recover_primary_transport(
         agent.api_key = rt["api_key"]
 
         if agent.api_mode == "anthropic_messages":
-            from agent.anthropic_adapter import build_anthropic_client
+            from agent.plugin_registries import registries
+            build_anthropic_client = registries.get_provider_service("anthropic", "build_anthropic_client")
             agent._anthropic_api_key = rt["anthropic_api_key"]
             agent._anthropic_base_url = rt["anthropic_base_url"]
             agent._anthropic_client = build_anthropic_client(
@@ -923,7 +931,8 @@ def restore_primary_runtime(agent) -> bool:
 
         # ── Rebuild client for the primary provider ──
         if agent.api_mode == "anthropic_messages":
-            from agent.anthropic_adapter import build_anthropic_client
+            from agent.plugin_registries import registries
+            build_anthropic_client = registries.get_provider_service("anthropic", "build_anthropic_client")
             agent._anthropic_api_key = rt["anthropic_api_key"]
             agent._anthropic_base_url = rt["anthropic_base_url"]
             agent._anthropic_client = build_anthropic_client(
@@ -1429,11 +1438,10 @@ def switch_model(agent, new_model, new_provider, api_key='', base_url='', api_mo
 
         # ── Build new client ──
         if api_mode == "anthropic_messages":
-            from agent.anthropic_adapter import (
-                build_anthropic_client,
-                resolve_anthropic_token,
-                _is_oauth_token,
-            )
+            from agent.plugin_registries import registries
+            build_anthropic_client = registries.get_provider_service("anthropic", "build_anthropic_client")
+            resolve_anthropic_token = registries.get_provider_service("anthropic", "resolve_anthropic_token")
+            _is_oauth_token = registries.get_provider_service("anthropic", "_is_oauth_token")
             # Only fall back to ANTHROPIC_TOKEN when the provider is actually Anthropic.
             # Other anthropic_messages providers (MiniMax, Alibaba, etc.) must use their own
             # API key — falling back would send Anthropic credentials to third-party endpoints.
@@ -1692,8 +1700,6 @@ def invoke_tool(agent, function_name: str, function_args: dict, effective_task_i
             session_id=agent.session_id or "",
             enabled_tools=list(agent.valid_tool_names) if agent.valid_tool_names else None,
             skip_pre_tool_call_hook=True,
-            enabled_toolsets=getattr(agent, "enabled_toolsets", None),
-            disabled_toolsets=getattr(agent, "disabled_toolsets", None),
         )
 
 

agent/anthropic_aux.py

@@ -0,0 +1,166 @@
+"""Anthropic auxiliary client wrappers — core module, no SDK dependency.
+
+Provides OpenAI-client-compatible shims over native Anthropic SDK clients,
+so auxiliary tasks (compression, vision, web extract, etc.) can call
+``client.chat.completions.create()`` regardless of the underlying SDK.
+
+The wrapper classes themselves never import the anthropic SDK.  They delegate
+wire-format conversion to :mod:`agent.anthropic_format` and response
+normalization to the ``anthropic_messages`` transport registered in
+:mod:`agent.transports`.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+from types import SimpleNamespace
+from typing import Any, Optional
+
+from agent.anthropic_format import (
+    build_anthropic_kwargs,
+    _forbids_sampling_params,
+)
+
+logger = logging.getLogger(__name__)
+
+
+# ---------------------------------------------------------------------------
+# Adapter: Anthropic SDK → OpenAI-compatible completions.create()
+# ---------------------------------------------------------------------------
+
+class _AnthropicCompletionsAdapter:
+    """OpenAI-client-compatible adapter for Anthropic Messages API."""
+
+    def __init__(self, real_client: Any, model: str, is_oauth: bool = False):
+        self._client = real_client
+        self._model = model
+        self._is_oauth = is_oauth
+
+    def create(self, **kwargs) -> Any:
+        from agent.transports import get_transport
+
+        messages = kwargs.get("messages", [])
+        model = kwargs.get("model", self._model)
+        tools = kwargs.get("tools")
+        tool_choice = kwargs.get("tool_choice")
+        # ZAI's Anthropic-compatible endpoint rejects max_tokens on vision
+        # models (glm-4v-flash etc.) with error code 1210.  When the caller
+        # signals this by setting _skip_zai_max_tokens in kwargs, omit it.
+        _skip_mt = kwargs.pop("_skip_zai_max_tokens", False)
+        if _skip_mt:
+            max_tokens = None
+        else:
+            max_tokens = kwargs.get("max_tokens") or kwargs.get("max_completion_tokens") or 2000
+        temperature = kwargs.get("temperature")
+
+        normalized_tool_choice = None
+        if isinstance(tool_choice, str):
+            normalized_tool_choice = tool_choice
+        elif isinstance(tool_choice, dict):
+            choice_type = str(tool_choice.get("type", "")).lower()
+            if choice_type == "function":
+                normalized_tool_choice = tool_choice.get("function", {}).get("name")
+            elif choice_type in {"auto", "required", "none"}:
+                normalized_tool_choice = choice_type
+
+        anthropic_kwargs = build_anthropic_kwargs(
+            model=model,
+            messages=messages,
+            tools=tools,
+            max_tokens=max_tokens,
+            reasoning_config=None,
+            tool_choice=normalized_tool_choice,
+            is_oauth=self._is_oauth,
+        )
+        # Opus 4.7+ rejects any non-default temperature/top_p/top_k; only set
+        # temperature for models that still accept it. build_anthropic_kwargs
+        # additionally strips these keys as a safety net — keep both layers.
+        if temperature is not None:
+            if not _forbids_sampling_params(model):
+                anthropic_kwargs["temperature"] = temperature
+
+        response = self._client.messages.create(**anthropic_kwargs)
+        _transport = get_transport("anthropic_messages")
+        _nr = _transport.normalize_response(
+            response, strip_tool_prefix=self._is_oauth
+        )
+
+        assistant_message = SimpleNamespace(
+            content=_nr.content,
+            tool_calls=_nr.tool_calls,
+            reasoning=_nr.reasoning,
+        )
+        finish_reason = _nr.finish_reason
+
+        usage = None
+        if hasattr(response, "usage") and response.usage:
+            prompt_tokens = getattr(response.usage, "input_tokens", 0) or 0
+            completion_tokens = getattr(response.usage, "output_tokens", 0) or 0
+            total_tokens = getattr(response.usage, "total_tokens", 0) or (prompt_tokens + completion_tokens)
+            usage = SimpleNamespace(
+                prompt_tokens=prompt_tokens,
+                completion_tokens=completion_tokens,
+                total_tokens=total_tokens,
+            )
+
+        choice = SimpleNamespace(
+            index=0,
+            message=assistant_message,
+            finish_reason=finish_reason,
+        )
+        return SimpleNamespace(
+            choices=[choice],
+            model=model,
+            usage=usage,
+        )
+
+
+class _AnthropicChatShim:
+    def __init__(self, adapter: _AnthropicCompletionsAdapter):
+        self.completions = adapter
+
+
+# ---------------------------------------------------------------------------
+# Public wrappers
+# ---------------------------------------------------------------------------
+
+class AnthropicAuxiliaryClient:
+    """OpenAI-client-compatible wrapper over a native Anthropic client."""
+
+    def __init__(self, real_client: Any, model: str, api_key: str, base_url: str, is_oauth: bool = False):
+        self._real_client = real_client
+        adapter = _AnthropicCompletionsAdapter(real_client, model, is_oauth=is_oauth)
+        self.chat = _AnthropicChatShim(adapter)
+        self.api_key = api_key
+        self.base_url = base_url
+
+    def close(self):
+        close_fn = getattr(self._real_client, "close", None)
+        if callable(close_fn):
+            close_fn()
+
+
+class _AsyncAnthropicCompletionsAdapter:
+    def __init__(self, sync_adapter: _AnthropicCompletionsAdapter):
+        self._sync = sync_adapter
+
+    async def create(self, **kwargs) -> Any:
+        return await asyncio.to_thread(self._sync.create, **kwargs)
+
+
+class _AsyncAnthropicChatShim:
+    def __init__(self, adapter: _AsyncAnthropicCompletionsAdapter):
+        self.completions = adapter
+
+
+class AsyncAnthropicAuxiliaryClient:
+    def __init__(self, sync_wrapper: AnthropicAuxiliaryClient):
+        sync_adapter = sync_wrapper.chat.completions
+        async_adapter = _AsyncAnthropicCompletionsAdapter(sync_adapter)
+        self.chat = _AsyncAnthropicChatShim(async_adapter)
+        self.api_key = sync_wrapper.api_key
+        self.base_url = sync_wrapper.base_url
+        # Mirror _real_client so cache eviction on a poisoned underlying
+        # client also drops this entry.
+        self._real_client = sync_wrapper._real_client

agent/auxiliary_client.py

@@ -106,6 +106,41 @@ from utils import base_url_host_matches, base_url_hostname, normalize_proxy_env_
 
 logger = logging.getLogger(__name__)
 
+# ---------------------------------------------------------------------------
+# Core anthropic wire-format modules (no SDK dependency)
+# ---------------------------------------------------------------------------
+
+from agent.anthropic_aux import (  # noqa: F401
+    AnthropicAuxiliaryClient,
+    AsyncAnthropicAuxiliaryClient,
+)
+
+# ---------------------------------------------------------------------------
+# Plugin-registry helper — access *plugin-provided* anthropic services
+# (resolve.py functions: maybe_wrap_anthropic, is_anthropic_compat_endpoint, etc.)
+# Wire-format code (message conversion, aux client wrappers) lives in core
+# and is imported directly above.
+# ---------------------------------------------------------------------------
+
+def _anthropic_plugin_service(name: str):
+    """Lazy accessor for anthropic plugin resolve services.
+
+    Only the SDK-dependent orchestration (maybe_wrap_anthropic,
+    is_anthropic_compat_endpoint, convert_openai_images_to_anthropic) lives
+    in the plugin.  Core accesses it through
+    ``registries.get_provider_service("anthropic", name)`` so that:
+      - Core never imports from a plugin package directly.
+      - The plugin need only be installed when the user actually uses it.
+    """
+    from agent.plugin_registries import registries
+    svc = registries.get_provider_service("anthropic", name)
+    if svc is None:
+        raise ImportError(
+            f"anthropic plugin service {name!r} not available — "
+            f"the hermes_agent_anthropic package may not be installed"
+        )
+    return svc
+
 
 def _safe_isinstance(obj: Any, maybe_type: Any) -> bool:
     """Return False instead of raising when a patched symbol is not a type."""
@@ -417,7 +452,6 @@ auxiliary_is_nous: bool = False
 _OPENROUTER_MODEL = "google/gemini-3-flash-preview"
 _NOUS_MODEL = "google/gemini-3-flash-preview"
 _NOUS_DEFAULT_BASE_URL = "https://inference-api.nousresearch.com/v1"
-_ANTHROPIC_DEFAULT_BASE_URL = "https://api.anthropic.com"
 _AUTH_JSON_PATH = get_hermes_home() / "auth.json"
 
 # Codex OAuth endpoint used when a caller explicitly requests
@@ -700,20 +734,12 @@ class _CodexCompletionsAdapter:
             # xAI's Responses endpoint rejects ``pattern`` and ``format`` JSON Schema
             # keywords (HTTP 400). Strip them here to match the parity guarantee that
             # chat_completion_helpers.py provides for the main-agent xAI path.
-            #
-            # Deep-copy before sanitizing — ``list(tools)`` is only a shallow
-            # copy of the outer list, but the sanitizers mutate the inner
-            # parameter dicts in place.  Without a deep copy the caller's
-            # tool registry permanently loses its slash-containing enum
-            # constraints after the first auxiliary xAI call.  See #27907.
             try:
-                import copy as _copy
                 from tools.schema_sanitizer import (
                     strip_pattern_and_format,
                     strip_slash_enum,
                 )
-                tools = _copy.deepcopy(list(tools))
-                tools, _ = strip_pattern_and_format(tools)
+                tools, _ = strip_pattern_and_format(list(tools))
                 tools, _ = strip_slash_enum(tools)
             except Exception as exc:
                 logger.warning(
@@ -956,253 +982,6 @@ class AsyncCodexAuxiliaryClient:
         self._real_client = sync_wrapper._real_client
 
 
-class _AnthropicCompletionsAdapter:
-    """OpenAI-client-compatible adapter for Anthropic Messages API."""
-
-    def __init__(self, real_client: Any, model: str, is_oauth: bool = False):
-        self._client = real_client
-        self._model = model
-        self._is_oauth = is_oauth
-
-    def create(self, **kwargs) -> Any:
-        from agent.anthropic_adapter import build_anthropic_kwargs
-        from agent.transports import get_transport
-
-        messages = kwargs.get("messages", [])
-        model = kwargs.get("model", self._model)
-        tools = kwargs.get("tools")
-        tool_choice = kwargs.get("tool_choice")
-        # ZAI's Anthropic-compatible endpoint rejects max_tokens on vision
-        # models (glm-4v-flash etc.) with error code 1210.  When the caller
-        # signals this by setting _skip_zai_max_tokens in kwargs, omit it.
-        _skip_mt = kwargs.pop("_skip_zai_max_tokens", False)
-        if _skip_mt:
-            max_tokens = None
-        else:
-            max_tokens = kwargs.get("max_tokens") or kwargs.get("max_completion_tokens") or 2000
-        temperature = kwargs.get("temperature")
-
-        normalized_tool_choice = None
-        if isinstance(tool_choice, str):
-            normalized_tool_choice = tool_choice
-        elif isinstance(tool_choice, dict):
-            choice_type = str(tool_choice.get("type", "")).lower()
-            if choice_type == "function":
-                normalized_tool_choice = tool_choice.get("function", {}).get("name")
-            elif choice_type in {"auto", "required", "none"}:
-                normalized_tool_choice = choice_type
-
-        anthropic_kwargs = build_anthropic_kwargs(
-            model=model,
-            messages=messages,
-            tools=tools,
-            max_tokens=max_tokens,
-            reasoning_config=None,
-            tool_choice=normalized_tool_choice,
-            is_oauth=self._is_oauth,
-        )
-        # Opus 4.7+ rejects any non-default temperature/top_p/top_k; only set
-        # temperature for models that still accept it. build_anthropic_kwargs
-        # additionally strips these keys as a safety net — keep both layers.
-        if temperature is not None:
-            from agent.anthropic_adapter import _forbids_sampling_params
-            if not _forbids_sampling_params(model):
-                anthropic_kwargs["temperature"] = temperature
-
-        response = self._client.messages.create(**anthropic_kwargs)
-        _transport = get_transport("anthropic_messages")
-        _nr = _transport.normalize_response(
-            response, strip_tool_prefix=self._is_oauth
-        )
-
-        # ToolCall already duck-types as OpenAI shape (.type, .function.name,
-        # .function.arguments) via properties, so no wrapping needed.
-        assistant_message = SimpleNamespace(
-            content=_nr.content,
-            tool_calls=_nr.tool_calls,
-            reasoning=_nr.reasoning,
-        )
-        finish_reason = _nr.finish_reason
-
-        usage = None
-        if hasattr(response, "usage") and response.usage:
-            prompt_tokens = getattr(response.usage, "input_tokens", 0) or 0
-            completion_tokens = getattr(response.usage, "output_tokens", 0) or 0
-            total_tokens = getattr(response.usage, "total_tokens", 0) or (prompt_tokens + completion_tokens)
-            usage = SimpleNamespace(
-                prompt_tokens=prompt_tokens,
-                completion_tokens=completion_tokens,
-                total_tokens=total_tokens,
-            )
-
-        choice = SimpleNamespace(
-            index=0,
-            message=assistant_message,
-            finish_reason=finish_reason,
-        )
-        return SimpleNamespace(
-            choices=[choice],
-            model=model,
-            usage=usage,
-        )
-
-
-class _AnthropicChatShim:
-    def __init__(self, adapter: _AnthropicCompletionsAdapter):
-        self.completions = adapter
-
-
-class AnthropicAuxiliaryClient:
-    """OpenAI-client-compatible wrapper over a native Anthropic client."""
-
-    def __init__(self, real_client: Any, model: str, api_key: str, base_url: str, is_oauth: bool = False):
-        self._real_client = real_client
-        adapter = _AnthropicCompletionsAdapter(real_client, model, is_oauth=is_oauth)
-        self.chat = _AnthropicChatShim(adapter)
-        self.api_key = api_key
-        self.base_url = base_url
-
-    def close(self):
-        close_fn = getattr(self._real_client, "close", None)
-        if callable(close_fn):
-            close_fn()
-
-
-class _AsyncAnthropicCompletionsAdapter:
-    def __init__(self, sync_adapter: _AnthropicCompletionsAdapter):
-        self._sync = sync_adapter
-
-    async def create(self, **kwargs) -> Any:
-        import asyncio
-        return await asyncio.to_thread(self._sync.create, **kwargs)
-
-
-class _AsyncAnthropicChatShim:
-    def __init__(self, adapter: _AsyncAnthropicCompletionsAdapter):
-        self.completions = adapter
-
-
-class AsyncAnthropicAuxiliaryClient:
-    def __init__(self, sync_wrapper: "AnthropicAuxiliaryClient"):
-        sync_adapter = sync_wrapper.chat.completions
-        async_adapter = _AsyncAnthropicCompletionsAdapter(sync_adapter)
-        self.chat = _AsyncAnthropicChatShim(async_adapter)
-        self.api_key = sync_wrapper.api_key
-        self.base_url = sync_wrapper.base_url
-        # See AsyncCodexAuxiliaryClient: mirror _real_client so cache
-        # eviction on a poisoned underlying client also drops this entry.
-        self._real_client = sync_wrapper._real_client
-
-
-def _endpoint_speaks_anthropic_messages(base_url: str) -> bool:
-    """True if the endpoint at ``base_url`` speaks the Anthropic Messages
-    protocol instead of OpenAI chat.completions.
-
-    Mirrors ``hermes_cli.runtime_provider._detect_api_mode_for_url`` so the
-    auxiliary client and the main agent stay in sync on transport selection.
-    Covers:
-
-    - Any URL ending in ``/anthropic`` (MiniMax, Zhipu GLM, LiteLLM proxies,
-      Anthropic-compatible gateways).
-    - ``api.kimi.com/coding`` (Kimi Coding Plan — the /coding route only
-      speaks Claude-Code's native Anthropic shape; ``chat.completions``
-      returns 404 on Anthropic-only model aliases like ``kimi-for-coding``).
-    - ``api.anthropic.com`` (native Anthropic).
-    """
-    normalized = (base_url or "").strip().lower().rstrip("/")
-    if not normalized:
-        return False
-    if normalized.endswith("/anthropic"):
-        return True
-    hostname = base_url_hostname(normalized)
-    if hostname == "api.anthropic.com":
-        return True
-    if hostname == "api.kimi.com" and "/coding" in normalized:
-        return True
-    return False
-
-
-def _maybe_wrap_anthropic(
-    client_obj: Any,
-    model: str,
-    api_key: str,
-    base_url: str,
-    api_mode: Optional[str] = None,
-) -> Any:
-    """Rewrap a plain OpenAI client in ``AnthropicAuxiliaryClient`` when
-    the endpoint actually speaks Anthropic Messages.
-
-    This is the single chokepoint for aux-client transport correction.
-    Runs at the end of every ``resolve_provider_client`` branch so that
-    api_key providers (Kimi Coding Plan), the ``custom`` endpoint, and
-    future /anthropic gateways all land on the right wire format
-    regardless of which branch built the client.
-
-    Returns ``client_obj`` unchanged when:
-
-    - It's already an Anthropic/Codex/Gemini/CopilotACP wrapper.
-    - The endpoint is an OpenAI-wire endpoint.
-    - ``api_mode`` is explicitly set to a non-Anthropic transport.
-    - The ``anthropic`` SDK is not installed (falls back to OpenAI wire).
-    """
-    # Already wrapped — don't double-wrap.
-    if _safe_isinstance(client_obj, AnthropicAuxiliaryClient):
-        return client_obj
-    # Other specialized adapters we should never re-dispatch.
-    if _safe_isinstance(client_obj, CodexAuxiliaryClient):
-        return client_obj
-    try:
-        from agent.gemini_native_adapter import GeminiNativeClient
-        if _safe_isinstance(client_obj, GeminiNativeClient):
-            return client_obj
-    except ImportError:
-        pass
-    try:
-        from agent.copilot_acp_client import CopilotACPClient
-        if _safe_isinstance(client_obj, CopilotACPClient):
-            return client_obj
-    except ImportError:
-        pass
-
-    # Explicit non-anthropic api_mode wins over URL heuristics.
-    if api_mode and api_mode != "anthropic_messages":
-        return client_obj
-
-    should_wrap = (
-        api_mode == "anthropic_messages"
-        or _endpoint_speaks_anthropic_messages(base_url)
-    )
-    if not should_wrap:
-        return client_obj
-
-    try:
-        from agent.anthropic_adapter import build_anthropic_client
-    except ImportError:
-        logger.warning(
-            "Endpoint %s speaks Anthropic Messages but the anthropic SDK is "
-            "not installed — falling back to OpenAI-wire (will likely 404).",
-            base_url,
-        )
-        return client_obj
-
-    try:
-        real_client = build_anthropic_client(api_key, base_url)
-    except Exception as exc:
-        logger.warning(
-            "Failed to build Anthropic client for %s (%s) — falling back to "
-            "OpenAI-wire client.", base_url, exc,
-        )
-        return client_obj
-
-    logger.debug(
-        "Auxiliary transport: wrapping client in AnthropicAuxiliaryClient "
-        "(model=%s, base_url=%s, api_mode=%s)",
-        model, base_url[:60] if base_url else "", api_mode or "auto-detected",
-    )
-    return AnthropicAuxiliaryClient(
-        real_client, model, api_key, base_url, is_oauth=False,
-    )
-
 
 def _read_nous_auth() -> Optional[dict]:
     """Read and validate ~/.hermes/auth.json for an active Nous provider.
@@ -1243,23 +1022,8 @@ def _read_nous_auth() -> Optional[dict]:
 
 
 def _nous_api_key(provider: dict) -> str:
-    """Extract a usable Nous inference JWT from stored auth state."""
-    from hermes_cli.auth import _nous_invoke_jwt_is_usable
-
-    for token_key, expiry_key in (
-        ("agent_key", "agent_key_expires_at"),
-        ("access_token", "expires_at"),
-    ):
-        token = provider.get(token_key)
-        if not isinstance(token, str) or not token.strip():
-            continue
-        if _nous_invoke_jwt_is_usable(
-            token,
-            scope=provider.get("scope"),
-            expires_at=provider.get(expiry_key),
-        ):
-            return token
-    return ""
+    """Extract the Nous runtime credential from the compatibility field."""
+    return provider.get("agent_key") or provider.get("access_token", "")
 
 
 def _nous_base_url() -> str:
@@ -1271,16 +1035,25 @@ def _resolve_nous_runtime_api(*, force_refresh: bool = False) -> Optional[tuple[
     """Return fresh Nous runtime credentials when available.
 
     This mirrors the main agent's 401 recovery path and keeps auxiliary
-    clients aligned with the singleton auth store + JWT refresh flow instead of
+    clients aligned with the singleton auth store + JWT/mint flow instead of
     relying only on whatever raw tokens happen to be sitting in auth.json
     or the credential pool.
     """
     try:
-        from hermes_cli.auth import resolve_nous_runtime_credentials
+        from hermes_cli.auth import (
+            NOUS_INFERENCE_AUTH_MODE_AUTO,
+            NOUS_INFERENCE_AUTH_MODE_LEGACY,
+            resolve_nous_runtime_credentials,
+        )
 
         creds = resolve_nous_runtime_credentials(
+            min_key_ttl_seconds=max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800"))),
             timeout_seconds=float(os.getenv("HERMES_NOUS_TIMEOUT_SECONDS", "15")),
-            force_refresh=force_refresh,
+            inference_auth_mode=(
+                NOUS_INFERENCE_AUTH_MODE_LEGACY
+                if force_refresh
+                else NOUS_INFERENCE_AUTH_MODE_AUTO
+            ),
         )
     except Exception as exc:
         logger.debug("Auxiliary Nous runtime credential resolution failed: %s", exc)
@@ -1419,7 +1192,14 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
                     continue
             except ImportError:
                 pass
-            return _try_anthropic()
+            # Delegate to the anthropic plugin resolver via the registry
+            from agent.plugin_registries import registries as _ar
+            _anthro_resolver = _ar.get_provider_resolver("anthropic")
+            if _anthro_resolver is not None:
+                _ac, _am = _anthro_resolver()
+                if _ac is not None:
+                    return _ac, _am
+            continue
 
         pool_present, entry = _select_pool_entry(provider_id)
         if pool_present:
@@ -1456,7 +1236,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
                 except Exception:
                     pass
             _client = OpenAI(api_key=api_key, base_url=base_url, **extra)
-            _client = _maybe_wrap_anthropic(_client, model, api_key, raw_base_url)
+            _client = _anthropic_plugin_service("maybe_wrap_anthropic")(_client, model, api_key, raw_base_url)
             return _client, model
 
         creds = resolve_api_key_provider_credentials(provider_id)
@@ -1493,7 +1273,7 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
             except Exception:
                 pass
         _client = OpenAI(api_key=api_key, base_url=base_url, **extra)
-        _client = _maybe_wrap_anthropic(_client, model, api_key, raw_base_url)
+        _client = _anthropic_plugin_service("maybe_wrap_anthropic")(_client, model, api_key, raw_base_url)
         return _client, model
 
     return None, None
@@ -1502,7 +1282,6 @@ def _resolve_api_key_provider() -> Tuple[Optional[OpenAI], Optional[str]]:
 # ── Provider resolution helpers ─────────────────────────────────────────────
 
 
-
 def _try_openrouter(explicit_api_key: str = None, model: str = None) -> Tuple[Optional[OpenAI], Optional[str]]:
     pool_present, entry = _select_pool_entry("openrouter")
     if pool_present:
@@ -1564,9 +1343,13 @@ def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
         _mark_provider_unhealthy("nous", ttl=60)
         return None, None
     if runtime is None and nous:
+        # Runtime credential mint failed but stored Nous auth is still present.
+        # Falls back to the raw stored token below; surface a debug line so
+        # operators investigating expired/invalid sessions have a breadcrumb,
+        # without blocking the fallback path the rest of this function relies on.
         logger.debug(
-            "Auxiliary Nous: runtime JWT refresh failed; checking stored "
-            "auth.json token."
+            "Auxiliary Nous: runtime credential mint failed; falling back to "
+            "stored auth.json token."
         )
     global auxiliary_is_nous
     auxiliary_is_nous = True
@@ -1604,13 +1387,6 @@ def _try_nous(vision: bool = False) -> Tuple[Optional[OpenAI], Optional[str]]:
         api_key, base_url = runtime
     else:
         api_key = _nous_api_key(nous or {})
-        if not api_key:
-            logger.warning(
-                "Auxiliary Nous client unavailable: no usable inference JWT found "
-                "(run: hermes auth add nous)."
-            )
-            _mark_provider_unhealthy("nous", ttl=60)
-            return None, None
         base_url = str((nous or {}).get("inference_base_url") or _nous_base_url()).rstrip("/")
     return (
         OpenAI(
@@ -1827,7 +1603,11 @@ def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
         # LiteLLM proxies, etc.).  Must NEVER be treated as OAuth —
         # Anthropic OAuth claims only apply to api.anthropic.com.
         try:
-            from agent.anthropic_adapter import build_anthropic_client
+            from agent.plugin_registries import registries
+            _anthropic = registries.get_provider_namespace("anthropic")
+            build_anthropic_client = _anthropic.get("build_anthropic_client")
+            if build_anthropic_client is None:
+                raise ImportError("anthropic provider not registered")
             real_client = build_anthropic_client(custom_key, custom_base)
         except ImportError:
             logger.warning(
@@ -1842,7 +1622,7 @@ def _try_custom_endpoint() -> Tuple[Optional[Any], Optional[str]]:
     # URL-based anthropic detection for custom endpoints that didn't set
     # api_mode explicitly (e.g. kimi.com/coding reached via custom config).
     _fallback_client = OpenAI(api_key=custom_key, base_url=_clean_base, **_extra)
-    _fallback_client = _maybe_wrap_anthropic(
+    _fallback_client = _anthropic_plugin_service("maybe_wrap_anthropic")(
         _fallback_client, model, custom_key, custom_base, custom_mode,
     )
     return _fallback_client, model
@@ -2020,7 +1800,7 @@ def _try_azure_foundry(
         # for Entra ID it's a callable. ``_maybe_wrap_anthropic`` →
         # ``build_anthropic_client`` detects the callable and installs
         # the bearer-injecting httpx hook.
-        return _maybe_wrap_anthropic(
+        return _anthropic_plugin_service("maybe_wrap_anthropic")(
             client, final_model, api_key,
             base_url, runtime_api_mode,
         ), final_model
@@ -2029,54 +1809,6 @@ def _try_azure_foundry(
     return client, final_model
 
 
-def _try_anthropic(explicit_api_key: str = None) -> Tuple[Optional[Any], Optional[str]]:
-    try:
-        from agent.anthropic_adapter import build_anthropic_client, resolve_anthropic_token
-    except ImportError:
-        return None, None
-
-    pool_present, entry = _select_pool_entry("anthropic")
-    if pool_present:
-        if entry is None:
-            return None, None
-        token = explicit_api_key or _pool_runtime_api_key(entry)
-    else:
-        entry = None
-        token = explicit_api_key or resolve_anthropic_token()
-    if not token:
-        return None, None
-
-    # Allow base URL override from config.yaml model.base_url, but only
-    # when the configured provider is anthropic — otherwise a non-Anthropic
-    # base_url (e.g. Codex endpoint) would leak into Anthropic requests.
-    base_url = _pool_runtime_base_url(entry, _ANTHROPIC_DEFAULT_BASE_URL) if pool_present else _ANTHROPIC_DEFAULT_BASE_URL
-    try:
-        from hermes_cli.config import load_config
-        cfg = load_config()
-        model_cfg = cfg.get("model")
-        if isinstance(model_cfg, dict):
-            cfg_provider = str(model_cfg.get("provider") or "").strip().lower()
-            if cfg_provider == "anthropic":
-                cfg_base_url = (model_cfg.get("base_url") or "").strip().rstrip("/")
-                if cfg_base_url:
-                    base_url = cfg_base_url
-    except Exception:
-        pass
-
-    from agent.anthropic_adapter import _is_oauth_token
-    is_oauth = _is_oauth_token(token)
-    model = _get_aux_model_for_provider("anthropic") or "claude-haiku-4-5-20251001"
-    logger.debug("Auxiliary client: Anthropic native (%s) at %s (oauth=%s)", model, base_url, is_oauth)
-    try:
-        real_client = build_anthropic_client(token, base_url)
-    except ImportError:
-        # The anthropic_adapter module imports fine but the SDK itself is
-        # missing — build_anthropic_client raises ImportError at call time
-        # when _anthropic_sdk is None.  Treat as unavailable.
-        return None, None
-    return AnthropicAuxiliaryClient(real_client, model, token, base_url, is_oauth=is_oauth), model
-
-
 _AUTO_PROVIDER_LABELS = {
     "_try_openrouter": "openrouter",
     "_try_nous": "nous",
@@ -2374,16 +2106,7 @@ def _is_auth_error(exc: Exception) -> bool:
     if status == 401:
         return True
     err_lower = str(exc).lower()
-    if "error code: 401" in err_lower or "authenticationerror" in type(exc).__name__.lower():
-        return True
-    # xAI returns HTTP 403 with "unauthenticated:bad-credentials" when an OAuth2
-    # access token has expired or is invalid — semantically a 401 auth failure,
-    # even though the status code is 403 (PermissionDenied).
-    if status == 403 and "bad-credentials" in err_lower:
-        return True
-    if "unauthenticated" in err_lower and "bad-credentials" in err_lower:
-        return True
-    return False
+    return "error code: 401" in err_lower or "authenticationerror" in type(exc).__name__.lower()
 
 
 def _is_unsupported_parameter_error(exc: Exception, param: str) -> bool:
@@ -2536,8 +2259,6 @@ def _recoverable_pool_provider(
         return "copilot"
     if base_url_host_matches(base, "api.kimi.com"):
         return "kimi-coding"
-    if base_url_host_matches(base, "api.x.ai"):
-        return "xai-oauth"
     # For api_key providers not in the hardcoded list (e.g. opencode-go), match
     # the client base URL against all registered api_key providers so that
     # credential-pool rotation works for any provider the user configured.
@@ -2657,8 +2378,8 @@ def _retry_same_provider_sync(
         extra_body=effective_extra_body,
         base_url=retry_base or resolved_base_url,
     )
-    if _is_anthropic_compat_endpoint(resolved_provider, retry_base):
-        retry_kwargs["messages"] = _convert_openai_images_to_anthropic(retry_kwargs["messages"])
+    if _anthropic_plugin_service("is_anthropic_compat_endpoint")(resolved_provider, retry_base):
+        retry_kwargs["messages"] = _anthropic_plugin_service("convert_openai_images_to_anthropic")(retry_kwargs["messages"])
     return _validate_llm_response(
         retry_client.chat.completions.create(**retry_kwargs), task,
     )
@@ -2714,8 +2435,8 @@ async def _retry_same_provider_async(
         extra_body=effective_extra_body,
         base_url=retry_base or resolved_base_url,
     )
-    if _is_anthropic_compat_endpoint(resolved_provider, retry_base):
-        retry_kwargs["messages"] = _convert_openai_images_to_anthropic(retry_kwargs["messages"])
+    if _anthropic_plugin_service("is_anthropic_compat_endpoint")(resolved_provider, retry_base):
+        retry_kwargs["messages"] = _anthropic_plugin_service("convert_openai_images_to_anthropic")(retry_kwargs["messages"])
     return _validate_llm_response(
         await retry_client.chat.completions.create(**retry_kwargs), task,
     )
@@ -2734,45 +2455,38 @@ def _refresh_provider_credentials(provider: str) -> bool:
             _evict_cached_clients(normalized)
             return True
         if normalized == "nous":
-            from hermes_cli.auth import resolve_nous_runtime_credentials
+            from hermes_cli.auth import (
+                NOUS_INFERENCE_AUTH_MODE_LEGACY,
+                resolve_nous_runtime_credentials,
+            )
 
             creds = resolve_nous_runtime_credentials(
+                min_key_ttl_seconds=max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800"))),
                 timeout_seconds=float(os.getenv("HERMES_NOUS_TIMEOUT_SECONDS", "15")),
-                force_refresh=True,
+                inference_auth_mode=NOUS_INFERENCE_AUTH_MODE_LEGACY,
             )
             if not str(creds.get("api_key", "") or "").strip():
                 return False
             _evict_cached_clients(normalized)
             return True
         if normalized == "anthropic":
-            from agent.anthropic_adapter import read_claude_code_credentials, _refresh_oauth_token, resolve_anthropic_token
+            from agent.plugin_registries import registries
+            _anthropic = registries.get_provider_namespace("anthropic")
+            read_claude_code_credentials = _anthropic.get("read_claude_code_credentials")
+            _refresh_oauth_token = _anthropic.get("_refresh_oauth_token")
+            resolve_anthropic_token = _anthropic.get("resolve_anthropic_token")
+            if read_claude_code_credentials is None:
+                return False
 
             creds = read_claude_code_credentials()
-            token = _refresh_oauth_token(creds) if isinstance(creds, dict) and creds.get("refreshToken") else None
+            token = _refresh_oauth_token(creds) if isinstance(creds, dict) and creds.get("refreshToken") and _refresh_oauth_token else None
             if not str(token or "").strip():
-                token = resolve_anthropic_token()
+                if resolve_anthropic_token is not None:
+                    token = resolve_anthropic_token()
             if not str(token or "").strip():
                 return False
             _evict_cached_clients(normalized)
             return True
-        if normalized == "xai-oauth":
-            # Preference: pool-level refresh (uses refresh_token from pool entry),
-            # then fall back to singleton auth-store resolver.
-            pool = load_pool(normalized)
-            if pool and pool.has_credentials():
-                # Ensure a current entry is selected before trying to refresh.
-                pool.select()
-                refreshed = pool.try_refresh_current()
-                if refreshed is not None and str(getattr(refreshed, "runtime_api_key", "") or "").strip():
-                    _evict_cached_clients(normalized)
-                    return True
-            from hermes_cli.auth import resolve_xai_oauth_runtime_credentials
-
-            creds = resolve_xai_oauth_runtime_credentials(force_refresh=True)
-            if not str(creds.get("api_key", "") or "").strip():
-                return False
-            _evict_cached_clients(normalized)
-            return True
     except Exception as exc:
         logger.debug("Auxiliary provider credential refresh failed for %s: %s", normalized, exc)
         return False
@@ -3089,7 +2803,7 @@ def _to_async_client(sync_client, model: str, is_vision: bool = False):
 
     if isinstance(sync_client, CodexAuxiliaryClient):
         return AsyncCodexAuxiliaryClient(sync_client), model
-    if isinstance(sync_client, AnthropicAuxiliaryClient):
+    if _safe_isinstance(sync_client, AnthropicAuxiliaryClient):
         return AsyncAnthropicAuxiliaryClient(sync_client), model
     try:
         from agent.gemini_native_adapter import GeminiNativeClient, AsyncGeminiNativeClient
@@ -3275,7 +2989,7 @@ def resolve_provider_client(
             return CodexAuxiliaryClient(client_obj, final_model_str)
         # Anthropic-wire endpoints: rewrap plain OpenAI clients so
         # chat.completions.create() is translated to /v1/messages.
-        return _maybe_wrap_anthropic(
+        return _anthropic_plugin_service("maybe_wrap_anthropic")(
             client_obj, final_model_str, api_key_str, base_url_str, api_mode,
         )
 
@@ -3507,7 +3221,11 @@ def resolve_provider_client(
                 # branch in _try_custom_endpoint(). See #15033.
                 if entry_api_mode == "anthropic_messages":
                     try:
-                        from agent.anthropic_adapter import build_anthropic_client
+                        from agent.plugin_registries import registries
+                        _anthropic = registries.get_provider_namespace("anthropic")
+                        build_anthropic_client = _anthropic.get("build_anthropic_client")
+                        if build_anthropic_client is None:
+                            raise ImportError("anthropic provider not registered")
                         real_client = build_anthropic_client(custom_key, custom_base)
                     except ImportError:
                         logger.warning(
@@ -3550,39 +3268,32 @@ def resolve_provider_client(
     except ImportError:
         pass
 
-    # ── Azure Foundry (delegates to runtime resolver for auth_mode-aware routing) ─
-    #
-    # The generic PROVIDER_REGISTRY path below uses
-    # ``resolve_api_key_provider_credentials`` which only knows about the
-    # static ``AZURE_FOUNDRY_API_KEY`` env var. That misses two important
-    # cases for the ``azure-foundry`` provider:
-    #
-    #   1. ``model.auth_mode: entra_id`` — no static key exists; we need
-    #      a callable bearer-token provider from ``azure_identity_adapter``.
-    #   2. Non-default ``model.base_url`` (Foundry projects path) — the
-    #      env-var-only resolver doesn't apply config-yaml-driven URL
-    #      overrides.
-    #
-    # Delegate to the same runtime resolver the main agent uses so
-    # auxiliary tasks (title generation, compression, vision, embedding,
-    # session search) inherit the user's full Azure config.
-    if provider == "azure-foundry":
-        client, default_model = _try_azure_foundry(
+    # ── Plugin-registered resolvers (azure-foundry, etc.) ──────────────
+    # Providers with complex auth (Entra ID, OAuth, etc.) register a
+    # resolver callable so core doesn't need per-provider if/elif branches.
+    from agent.plugin_registries import registries as _reg_early
+    _early_resolver = _reg_early.get_provider_resolver(provider)
+    if _early_resolver is not None:
+        client, default_model = _early_resolver(
             model=model,
             explicit_api_key=explicit_api_key,
             explicit_base_url=explicit_base_url,
+            async_mode=async_mode,
+            is_vision=is_vision,
+            main_runtime=main_runtime,
             api_mode=api_mode,
         )
-        if client is None:
-            logger.warning(
-                "resolve_provider_client: azure-foundry requested but "
-                "runtime resolution failed (run: hermes doctor for "
-                "diagnostics)"
-            )
-            return None, None
-        final_model = _normalize_resolved_model(model or default_model, provider)
-        return (_to_async_client(client, final_model, is_vision=is_vision) if async_mode
-                else (client, final_model))
+        if client is not None:
+            final_model = _normalize_resolved_model(model or default_model, provider)
+            return (_to_async_client(client, final_model, is_vision=is_vision) if async_mode
+                    else (client, final_model))
+        # Resolver returned None — provider unavailable
+        logger.warning(
+            "resolve_provider_client: %s requested but resolver returned "
+            "no client (run: hermes doctor for diagnostics)",
+            provider,
+        )
+        return None, None
 
     # ── API-key providers from PROVIDER_REGISTRY ─────────────────────
     try:
@@ -3601,14 +3312,6 @@ def resolve_provider_client(
         return None, None
 
     if pconfig.auth_type == "api_key":
-        if provider == "anthropic":
-            client, default_model = _try_anthropic(explicit_api_key=explicit_api_key)
-            if client is None:
-                logger.warning("resolve_provider_client: anthropic requested but no Anthropic credentials found")
-                return None, None
-            final_model = _normalize_resolved_model(model or default_model, provider)
-            return (_to_async_client(client, final_model, is_vision=is_vision) if async_mode else (client, final_model))
-
         creds = resolve_api_key_provider_credentials(provider)
         api_key = str(creds.get("api_key", "")).strip()
         # Honour an explicit api_key override (e.g. from a fallback_model entry
@@ -3741,37 +3444,14 @@ def resolve_provider_client(
         return None, None
 
     elif pconfig.auth_type == "aws_sdk":
-        # AWS SDK providers (Bedrock) — use the Anthropic Bedrock client via
-        # boto3's credential chain (IAM roles, SSO, env vars, instance metadata).
-        try:
-            from agent.bedrock_adapter import has_aws_credentials, resolve_bedrock_region
-            from agent.anthropic_adapter import build_anthropic_bedrock_client
-        except ImportError:
-            logger.warning("resolve_provider_client: bedrock requested but "
-                           "boto3 or anthropic SDK not installed")
-            return None, None
-
-        if not has_aws_credentials():
-            logger.debug("resolve_provider_client: bedrock requested but "
-                         "no AWS credentials found")
-            return None, None
-
-        region = resolve_bedrock_region()
-        default_model = "anthropic.claude-haiku-4-5-20251001-v1:0"
-        final_model = _normalize_resolved_model(model or default_model, provider)
-        try:
-            real_client = build_anthropic_bedrock_client(region)
-        except ImportError as exc:
-            logger.warning("resolve_provider_client: cannot create Bedrock "
-                           "client: %s", exc)
-            return None, None
-        client = AnthropicAuxiliaryClient(
-            real_client, final_model, api_key="aws-sdk",
-            base_url=f"https://bedrock-runtime.{region}.amazonaws.com",
+        # AWS SDK providers (e.g. Bedrock) — handled by the early resolver
+        # catch above when a plugin registers one.  If we reach here, no
+        # resolver was registered.
+        logger.warning(
+            "resolve_provider_client: aws_sdk provider %s has no "
+            "registered resolver (plugin not loaded?)", provider,
         )
-        logger.debug("resolve_provider_client: bedrock (%s, %s)", final_model, region)
-        return (_to_async_client(client, final_model, is_vision=is_vision) if async_mode
-                else (client, final_model))
+        return None, None
 
     elif pconfig.auth_type in {"oauth_device_code", "oauth_external"}:
         # OAuth providers — route through their specific try functions
@@ -3895,7 +3575,12 @@ def _resolve_strict_vision_backend(
         # allow-list); callers must specify via auxiliary.<task>.model.
         return resolve_provider_client("openai-codex", model, is_vision=True)
     if provider == "anthropic":
-        return _try_anthropic()
+        from agent.plugin_registries import registries as _reg
+        _resolver = _reg.get_provider_resolver("anthropic")
+        if _resolver is not None:
+            return _resolver(model=model)
+        # Fallback: no resolver registered (plugin not loaded)
+        return None, None
     if provider == "custom":
         return _try_custom_endpoint()
     return None, None
@@ -4625,69 +4310,6 @@ def _get_task_extra_body(task: str) -> Dict[str, Any]:
 
 # Providers that use Anthropic-compatible endpoints (via OpenAI SDK wrapper).
 # Their image content blocks must use Anthropic format, not OpenAI format.
-_ANTHROPIC_COMPAT_PROVIDERS = frozenset({"minimax", "minimax-oauth", "minimax-cn"})
-
-
-def _is_anthropic_compat_endpoint(provider: str, base_url: str) -> bool:
-    """Detect if an endpoint expects Anthropic-format content blocks.
-
-    Returns True for known Anthropic-compatible providers (MiniMax) and
-    any endpoint whose URL contains ``/anthropic`` in the path.
-    """
-    if provider in _ANTHROPIC_COMPAT_PROVIDERS:
-        return True
-    url_lower = (base_url or "").lower()
-    return "/anthropic" in url_lower
-
-
-def _convert_openai_images_to_anthropic(messages: list) -> list:
-    """Convert OpenAI ``image_url`` content blocks to Anthropic ``image`` blocks.
-
-    Only touches messages that have list-type content with ``image_url`` blocks;
-    plain text messages pass through unchanged.
-    """
-    converted = []
-    for msg in messages:
-        content = msg.get("content")
-        if not isinstance(content, list):
-            converted.append(msg)
-            continue
-        new_content = []
-        changed = False
-        for block in content:
-            if block.get("type") == "image_url":
-                image_url_val = (block.get("image_url") or {}).get("url", "")
-                if image_url_val.startswith("data:"):
-                    # Parse data URI: data:<media_type>;base64,<data>
-                    header, _, b64data = image_url_val.partition(",")
-                    media_type = "image/png"
-                    if ":" in header and ";" in header:
-                        media_type = header.split(":", 1)[1].split(";", 1)[0]
-                    new_content.append({
-                        "type": "image",
-                        "source": {
-                            "type": "base64",
-                            "media_type": media_type,
-                            "data": b64data,
-                        },
-                    })
-                else:
-                    # URL-based image
-                    new_content.append({
-                        "type": "image",
-                        "source": {
-                            "type": "url",
-                            "url": image_url_val,
-                        },
-                    })
-                changed = True
-            else:
-                new_content.append(block)
-        converted.append({**msg, "content": new_content} if changed else msg)
-    return converted
-
-
-
 def _build_call_kwargs(
     provider: str,
     model: str,
@@ -4717,8 +4339,10 @@ def _build_call_kwargs(
     # structured-JSON extraction) don't 400 the moment
     # the aux model is flipped to 4.7.
     if temperature is not None:
-        from agent.anthropic_adapter import _forbids_sampling_params
-        if _forbids_sampling_params(model):
+        from agent.plugin_registries import registries
+        _anthropic = registries.get_provider_namespace("anthropic")
+        _forbids_sampling_params = _anthropic.get("_forbids_sampling_params")
+        if _forbids_sampling_params is not None and _forbids_sampling_params(model):
             temperature = None
 
     if temperature is not None:
@@ -4930,8 +4554,8 @@ def call_llm(
 
     # Convert image blocks for Anthropic-compatible endpoints (e.g. MiniMax)
     _client_base = str(getattr(client, "base_url", "") or "")
-    if _is_anthropic_compat_endpoint(resolved_provider, _client_base):
-        kwargs["messages"] = _convert_openai_images_to_anthropic(kwargs["messages"])
+    if _anthropic_plugin_service("is_anthropic_compat_endpoint")(resolved_provider, _client_base):
+        kwargs["messages"] = _anthropic_plugin_service("convert_openai_images_to_anthropic")(kwargs["messages"])
 
     # Handle unsupported temperature, max_tokens vs max_completion_tokens retry,
     # then payment fallback.
@@ -5373,8 +4997,8 @@ async def async_call_llm(
         base_url=_client_base or resolved_base_url)
 
     # Convert image blocks for Anthropic-compatible endpoints (e.g. MiniMax)
-    if _is_anthropic_compat_endpoint(resolved_provider, _client_base):
-        kwargs["messages"] = _convert_openai_images_to_anthropic(kwargs["messages"])
+    if _anthropic_plugin_service("is_anthropic_compat_endpoint")(resolved_provider, _client_base):
+        kwargs["messages"] = _anthropic_plugin_service("convert_openai_images_to_anthropic")(kwargs["messages"])
 
     try:
         return _validate_llm_response(

agent/browser_registry.py

@@ -186,6 +186,37 @@ def _resolve(configured: Optional[str]) -> Optional[BrowserProvider]:
     return None
 
 
+def get_active_browser_provider() -> Optional[BrowserProvider]:
+    """Resolve the currently-active cloud browser provider.
+
+    Reads ``browser.cloud_provider`` from config.yaml; falls back per the
+    module docstring. Returns None for local mode or when no provider is
+    available.
+    """
+    try:
+        from hermes_cli.config import read_raw_config
+
+        cfg = read_raw_config()
+        browser_cfg = cfg.get("browser", {})
+    except Exception as exc:
+        logger.debug("Could not read browser config: %s", exc)
+        browser_cfg = {}
+
+    configured: Optional[str] = None
+    if isinstance(browser_cfg, dict) and "cloud_provider" in browser_cfg:
+        try:
+            from tools.tool_backend_helpers import normalize_browser_cloud_provider
+
+            configured = normalize_browser_cloud_provider(
+                browser_cfg.get("cloud_provider")
+            )
+        except Exception as exc:
+            logger.debug("normalize_browser_cloud_provider failed: %s", exc)
+            configured = None
+
+    return _resolve(configured)
+
+
 def _reset_for_tests() -> None:
     """Clear the registry. **Test-only.**"""
     with _lock:

agent/chat_completion_helpers.py

@@ -15,23 +15,49 @@ sites unchanged.  Symbols that tests patch on ``run_agent`` (e.g.
 
 from __future__ import annotations
 
+import concurrent.futures
+import contextvars
+import copy
 import json
 import logging
 import os
+import random
 import re
+import sys
 import threading
 import time
 import uuid
+from datetime import datetime
+from pathlib import Path
 from types import SimpleNamespace
-from typing import Any, Dict, Optional
+from typing import Any, Dict, List, Optional, Tuple
+from urllib.parse import urlparse, parse_qs, urlunparse
 
 from hermes_cli.timeouts import get_provider_request_timeout, get_provider_stale_timeout
 from hermes_constants import PARTIAL_STREAM_STUB_ID, FINISH_REASON_LENGTH
-from agent.error_classifier import FailoverReason
+from agent.error_classifier import classify_api_error, FailoverReason
 from agent.model_metadata import is_local_endpoint
 from agent.message_sanitization import (
     _sanitize_surrogates,
+    _sanitize_messages_surrogates,
+    _sanitize_structure_surrogates,
+    _sanitize_messages_non_ascii,
+    _sanitize_tools_non_ascii,
+    _sanitize_structure_non_ascii,
+    _strip_images_from_messages,
+    _strip_non_ascii,
     _repair_tool_call_arguments,
+    _escape_invalid_chars_in_json_strings,
+)
+from agent.tool_dispatch_helpers import (
+    _is_multimodal_tool_result,
+    _multimodal_text_summary,
+)
+from agent.retry_utils import jittered_backoff
+from agent.tool_guardrails import (
+    ToolGuardrailDecision,
+    append_toolguard_guidance,
+    toolguard_synthetic_result,
 )
 from tools.terminal_tool import is_persistent_env
 from utils import base_url_host_matches, base_url_hostname
@@ -149,6 +175,13 @@ def interruptible_api_call(agent, api_kwargs: dict):
             request_client_holder["owner_tid"] = threading.get_ident()
         return client
 
+    def _take_request_client():
+        with request_client_lock:
+            client = request_client_holder.get("client")
+            request_client_holder["client"] = None
+            request_client_holder["owner_tid"] = None
+            return client
+
     def _close_request_client_once(reason: str) -> None:
         # #29507: dispatch on the calling thread.
         #
@@ -202,12 +235,14 @@ def interruptible_api_call(agent, api_kwargs: dict):
                 # normalize_converse_response produces an OpenAI-compatible
                 # SimpleNamespace so the rest of the agent loop can treat
                 # bedrock responses like chat_completions responses.
-                from agent.bedrock_adapter import (
-                    _get_bedrock_runtime_client,
-                    invalidate_runtime_client,
-                    is_stale_connection_error,
-                    normalize_converse_response,
-                )
+                from agent.plugin_registries import registries
+                _bedrock = registries.get_provider_namespace("bedrock")
+                _get_bedrock_runtime_client = _bedrock.get("_get_bedrock_runtime_client")
+                invalidate_runtime_client = _bedrock.get("invalidate_runtime_client")
+                is_stale_connection_error = _bedrock.get("is_stale_connection_error")
+                normalize_converse_response = _bedrock.get("normalize_converse_response")
+                if _get_bedrock_runtime_client is None or normalize_converse_response is None:
+                    raise ImportError("bedrock provider not registered")
                 region = api_kwargs.pop("__bedrock_region__", "us-east-1")
                 api_kwargs.pop("__bedrock_converse__", None)
                 client = _get_bedrock_runtime_client(region)
@@ -277,15 +312,8 @@ def interruptible_api_call(agent, api_kwargs: dict):
     else:
         _codex_idle_timeout_default = 12.0
 
-    # No-byte TTFB cutoff. The OpenAI SDK's own streaming read timeout is far
-    # longer (openai 2.x DEFAULT_TIMEOUT.read = 600s), so a tight 12s default
-    # killed subscription-backed Codex requests mid-prefill before the backend
-    # had a chance to emit its first SSE event. Default to 120s — long enough to
-    # clear normal backend admission / prompt prefill, short enough to still
-    # reconnect promptly when the socket is genuinely wedged. Set
-    # HERMES_CODEX_TTFB_TIMEOUT_SECONDS=0 to disable this watchdog entirely.
     _ttfb_enabled = _codex_watchdog_enabled
-    _ttfb_timeout = _env_float("HERMES_CODEX_TTFB_TIMEOUT_SECONDS", 120.0)
+    _ttfb_timeout = _env_float("HERMES_CODEX_TTFB_TIMEOUT_SECONDS", 12.0)
     if _ttfb_timeout <= 0:
         _ttfb_enabled = False
     elif _openai_codex_backend:
@@ -307,7 +335,7 @@ def interruptible_api_call(agent, api_kwargs: dict):
                 _ttfb_disable_above,
             )
         else:
-            _ttfb_cap = _env_float("HERMES_CODEX_TTFB_MAX_SECONDS", 120.0)
+            _ttfb_cap = _env_float("HERMES_CODEX_TTFB_MAX_SECONDS", 20.0)
             if _ttfb_cap > 0 and _ttfb_timeout > _ttfb_cap:
                 logger.info(
                     "Capping openai-codex no-byte TTFB timeout from %.0fs to %.0fs "
@@ -588,23 +616,12 @@ def build_api_kwargs(agent, api_messages: list) -> dict:
         # It also rejects ``enum`` values containing ``/`` (HuggingFace IDs
         # like ``Qwen/Qwen3.5-0.8B`` shipped by MCP servers) — same 400 with
         # the same opaque message; strip those enums too.
-        #
-        # Deep-copy ``tools_for_api`` before sanitizing: the sanitizers
-        # mutate in place (documented contract on ``strip_slash_enum`` /
-        # ``strip_pattern_and_format``), and ``tools_for_api`` is a direct
-        # reference to ``agent.tools``.  Without the copy, the first xAI
-        # request permanently strips constraints from the shared per-agent
-        # tool registry — every subsequent non-xAI call from the same
-        # agent (auxiliary task routed to Anthropic, OpenRouter fallback,
-        # main-model swap) sees the already-stripped schema.  See #27907.
         if is_xai_responses:
             try:
-                import copy as _copy
                 from tools.schema_sanitizer import (
                     strip_pattern_and_format,
                     strip_slash_enum,
                 )
-                tools_for_api = _copy.deepcopy(tools_for_api)
                 tools_for_api, _ = strip_pattern_and_format(tools_for_api)
                 tools_for_api, _ = strip_slash_enum(tools_for_api)
             except Exception as exc:
@@ -681,8 +698,11 @@ def build_api_kwargs(agent, api_messages: list) -> dict:
     _ant_max = None
     if (_is_or or _is_nous) and "claude" in (agent.model or "").lower():
         try:
-            from agent.anthropic_adapter import _get_anthropic_max_output
-            _ant_max = _get_anthropic_max_output(agent.model)
+            from agent.plugin_registries import registries
+            _anthropic = registries.get_provider_namespace("anthropic")
+            _get_anthropic_max_output = _anthropic.get("_get_anthropic_max_output")
+            if _get_anthropic_max_output is not None:
+                _ant_max = _get_anthropic_max_output(agent.model)
         except Exception:
             pass
 
@@ -1167,15 +1187,20 @@ def try_activate_fallback(agent, reason: "FailoverReason | None" = None) -> bool
 
         if fb_api_mode == "anthropic_messages":
             # Build native Anthropic client instead of using OpenAI client
-            from agent.anthropic_adapter import build_anthropic_client, resolve_anthropic_token, _is_oauth_token
-            effective_key = (fb_client.api_key or resolve_anthropic_token() or "") if fb_provider == "anthropic" else (fb_client.api_key or "")
+            from agent.plugin_registries import registries
+            _anthropic = registries.get_provider_namespace("anthropic")
+            build_anthropic_client = _anthropic.get("build_anthropic_client")
+            resolve_anthropic_token = _anthropic.get("resolve_anthropic_token")
+            _is_oauth_token = _anthropic.get("_is_oauth_token")
+            effective_key = (fb_client.api_key or (resolve_anthropic_token() if resolve_anthropic_token else "") or "") if fb_provider == "anthropic" else (fb_client.api_key or "")
             agent.api_key = effective_key
             agent._anthropic_api_key = effective_key
             agent._anthropic_base_url = fb_base_url
-            agent._anthropic_client = build_anthropic_client(
-                effective_key, agent._anthropic_base_url, timeout=_fb_timeout,
-            )
-            agent._is_anthropic_oauth = _is_oauth_token(effective_key) if fb_provider == "anthropic" else False
+            if build_anthropic_client is not None:
+                agent._anthropic_client = build_anthropic_client(
+                    effective_key, agent._anthropic_base_url, timeout=_fb_timeout,
+                )
+            agent._is_anthropic_oauth = _is_oauth_token(effective_key) if fb_provider == "anthropic" and _is_oauth_token else False
             agent.client = None
             agent._client_kwargs = {}
         else:
@@ -1559,12 +1584,14 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
 
         def _bedrock_call():
             try:
-                from agent.bedrock_adapter import (
-                    _get_bedrock_runtime_client,
-                    invalidate_runtime_client,
-                    is_stale_connection_error,
-                    stream_converse_with_callbacks,
-                )
+                from agent.plugin_registries import registries
+                _bedrock = registries.get_provider_namespace("bedrock")
+                _get_bedrock_runtime_client = _bedrock.get("_get_bedrock_runtime_client")
+                invalidate_runtime_client = _bedrock.get("invalidate_runtime_client")
+                is_stale_connection_error = _bedrock.get("is_stale_connection_error")
+                stream_converse_with_callbacks = _bedrock.get("stream_converse_with_callbacks")
+                if _get_bedrock_runtime_client is None or stream_converse_with_callbacks is None:
+                    raise ImportError("bedrock provider not registered")
                 region = api_kwargs.pop("__bedrock_region__", "us-east-1")
                 api_kwargs.pop("__bedrock_converse__", None)
                 client = _get_bedrock_runtime_client(region)
@@ -1621,6 +1648,13 @@ def interruptible_streaming_api_call(agent, api_kwargs: dict, *, on_first_delta=
             request_client_holder["owner_tid"] = threading.get_ident()
         return client
 
+    def _take_request_client():
+        with request_client_lock:
+            client = request_client_holder.get("client")
+            request_client_holder["client"] = None
+            request_client_holder["owner_tid"] = None
+            return client
+
     def _close_request_client_once(reason: str) -> None:
         # See #29507 explanation in the non-streaming variant above. A
         # stranger thread (the interrupt-check / stale-stream detector loop)

agent/codex_responses_adapter.py

@@ -980,48 +980,6 @@ def _extract_responses_reasoning_text(item: Any) -> str:
     return ""
 
 
-def _format_responses_error(error_obj: Any, response_status: str) -> str:
-    """Build a human-readable error string from a Responses ``response.error`` payload.
-
-    The OpenAI Responses API carries failure details under ``response.error``
-    on terminal ``response.failed`` events, in the shape
-    ``{"code": "rate_limit_exceeded", "message": "Slow down", "param": ...}``.
-    Earlier code only surfaced ``message``, which left users staring at bare
-    strings like ``"Slow down"`` while the failure mode (rate limit vs
-    context-length vs internal_error vs model-overloaded) was hidden in
-    ``code``. We now prefix ``code`` when both are present so consumers can
-    distinguish failure modes without parsing the bare message.
-
-    Falls back to ``code`` alone when ``message`` is empty, and to a stable
-    default referencing the response status when no error payload is
-    available at all. Adapted from anomalyco/opencode#28757.
-    """
-    # Pull code and message from either dict or attribute-style payloads.
-    code: Any = None
-    message: Any = None
-    if isinstance(error_obj, dict):
-        code = error_obj.get("code")
-        message = error_obj.get("message")
-    elif error_obj is not None:
-        code = getattr(error_obj, "code", None)
-        message = getattr(error_obj, "message", None)
-
-    code_str = str(code).strip() if isinstance(code, str) else (str(code).strip() if code else "")
-    message_str = str(message).strip() if isinstance(message, str) else (str(message).strip() if message else "")
-
-    if code_str and message_str:
-        return f"{code_str}: {message_str}"
-    if message_str:
-        return message_str
-    if code_str:
-        return code_str
-    if error_obj:
-        # Last-resort: stringify whatever the provider sent so it's at least
-        # visible in logs/UI rather than silently swallowed.
-        return str(error_obj)
-    return f"Responses API returned status '{response_status}'"
-
-
 # ---------------------------------------------------------------------------
 # Full response normalization
 # ---------------------------------------------------------------------------
@@ -1065,7 +1023,10 @@ def _normalize_codex_response(
 
     if response_status in {"failed", "cancelled"}:
         error_obj = getattr(response, "error", None)
-        error_msg = _format_responses_error(error_obj, response_status)
+        if isinstance(error_obj, dict):
+            error_msg = error_obj.get("message") or str(error_obj)
+        else:
+            error_msg = str(error_obj) if error_obj else f"Responses API returned status '{response_status}'"
         raise RuntimeError(error_msg)
 
     content_parts: List[str] = []

agent/codex_runtime.py

@@ -16,6 +16,7 @@ compatibility.
 
 from __future__ import annotations
 
+import json
 import logging
 import os
 import time

agent/context_compressor.py

@@ -75,44 +75,6 @@ _IMAGE_TOKEN_ESTIMATE = 1600
 _IMAGE_CHAR_EQUIVALENT = _IMAGE_TOKEN_ESTIMATE * _CHARS_PER_TOKEN
 _SUMMARY_FAILURE_COOLDOWN_SECONDS = 600
 
-# Hard ceiling for the deterministic summary-failure handoff.  The fallback is
-# only meant to preserve continuity anchors from the dropped window, not to
-# become another unbounded transcript copy after the LLM summarizer failed.
-_FALLBACK_SUMMARY_MAX_CHARS = 8_000
-_FALLBACK_TURN_MAX_CHARS = 700
-
-
-_PATH_MENTION_RE = re.compile(r"(?:/|~/?|[A-Za-z]:\\)[^\s`'\")\]}<>]+")
-
-
-def _dedupe_append(items: list[str], value: str, *, limit: int) -> None:
-    value = value.strip()
-    if value and value not in items and len(items) < limit:
-        items.append(value)
-
-
-def _extract_tool_call_name_and_args(tool_call: Any) -> tuple[str, str]:
-    """Return a best-effort ``(name, arguments)`` pair for dict/object tool calls."""
-    if isinstance(tool_call, dict):
-        fn = tool_call.get("function") or {}
-        return str(fn.get("name") or "unknown"), str(fn.get("arguments") or "")
-
-    fn = getattr(tool_call, "function", None)
-    if fn is None:
-        return "unknown", ""
-    return str(getattr(fn, "name", None) or "unknown"), str(getattr(fn, "arguments", None) or "")
-
-
-def _extract_tool_call_id(tool_call: Any) -> str:
-    if isinstance(tool_call, dict):
-        return str(tool_call.get("id") or "")
-    return str(getattr(tool_call, "id", "") or "")
-
-
-def _collect_path_mentions(text: str, relevant_files: list[str], *, limit: int = 12) -> None:
-    for match in _PATH_MENTION_RE.findall(text):
-        _dedupe_append(relevant_files, match.rstrip(".,:;"), limit=limit)
-
 
 def _content_length_for_budget(raw_content: Any) -> int:
     """Return the effective char-length of a message's content for token budgeting.
@@ -575,8 +537,8 @@ class ContextCompressor(ContextEngine):
         self.quiet_mode = quiet_mode
         # When True, summary-generation failure aborts compression entirely
         # (returns messages unchanged, sets _last_compress_aborted=True).
-        # When False (default = historical behavior), insert a
-        # deterministic "summary unavailable" handoff and drop the middle window.
+        # When False (default = historical behavior), insert a static
+        # "summary unavailable" placeholder and drop the middle window.
         self.abort_on_summary_failure = abort_on_summary_failure
 
         self.context_length = get_model_context_length(
@@ -922,195 +884,6 @@ class ContextCompressor(ContextEngine):
 
         return "\n\n".join(parts)
 
-    def _build_static_fallback_summary(
-        self,
-        turns_to_summarize: List[Dict[str, Any]],
-        reason: str | None = None,
-    ) -> str:
-        """Build a deterministic handoff when the LLM summarizer is unavailable.
-
-        This is intentionally much less rich than an LLM-written summary, but it
-        is still better than a bare "N messages were removed" marker.  It keeps
-        the most useful continuity anchors that can be extracted locally:
-        recent user asks, assistant/tool actions, files/commands mentioned in
-        tool calls, and any error text.  The result uses the normal summary
-        structure so downstream prompts can recover gracefully after a provider
-        outage or summary-model failure.
-        """
-        user_asks: list[str] = []
-        assistant_actions: list[str] = []
-        tool_actions: list[str] = []
-        relevant_files: list[str] = []
-        blockers: list[str] = []
-        last_dropped_turns: list[str] = []
-
-        def _compact_fallback_turn(value: Any) -> str:
-            text = redact_sensitive_text(_content_text_for_contains(value))
-            text = re.sub(r"\bgh[pousr]_[A-Za-z0-9_]{8,}\b", "[REDACTED]", text)
-            text = re.sub(r"\s+", " ", text).strip()
-            if len(text) > _FALLBACK_TURN_MAX_CHARS:
-                text = text[: _FALLBACK_TURN_MAX_CHARS - 15].rstrip() + " ...[truncated]"
-            return re.sub(r"\bgh[pousr]_[A-Za-z0-9_.-]+", "[REDACTED]", text)
-
-        def _remember_dropped_turn(label: str, text: str, *, limit: int = 8) -> None:
-            text = text.strip()
-            if not text:
-                return
-            last_dropped_turns.append(f"{label}: {text}")
-            if len(last_dropped_turns) > limit:
-                del last_dropped_turns[0]
-
-        def _collect_paths_from_jsonish(obj: Any) -> None:
-            if isinstance(obj, dict):
-                for key, val in obj.items():
-                    if key in {"path", "workdir", "file_path", "output_path"} and isinstance(val, str):
-                        _dedupe_append(relevant_files, val, limit=12)
-                    _collect_paths_from_jsonish(val)
-            elif isinstance(obj, list):
-                for val in obj:
-                    _collect_paths_from_jsonish(val)
-            elif isinstance(obj, str):
-                _collect_path_mentions(obj, relevant_files)
-
-        call_id_to_tool: dict[str, tuple[str, str]] = {}
-        for msg in turns_to_summarize:
-            if msg.get("role") == "assistant" and msg.get("tool_calls"):
-                for tc in msg.get("tool_calls") or []:
-                    name, raw_args = _extract_tool_call_name_and_args(tc)
-                    args = redact_sensitive_text(raw_args)
-                    call_id = _extract_tool_call_id(tc)
-                    if call_id:
-                        call_id_to_tool[call_id] = (name, args)
-                    if args:
-                        try:
-                            parsed = json.loads(args)
-                        except Exception:
-                            parsed = args
-                        _collect_paths_from_jsonish(parsed)
-
-        for msg in turns_to_summarize:
-            role = msg.get("role", "unknown")
-            text = _compact_fallback_turn(msg.get("content"))
-            _collect_path_mentions(text, relevant_files)
-
-            turn_text = text
-            turn_tool_names: list[str] = []
-            if role == "assistant" and msg.get("tool_calls"):
-                for tc in msg.get("tool_calls") or []:
-                    name, _args = _extract_tool_call_name_and_args(tc)
-                    turn_tool_names.append(name)
-                if turn_tool_names:
-                    prefix = "tool calls: " + ", ".join(turn_tool_names[:6])
-                    turn_text = f"{prefix}; {turn_text}" if turn_text else prefix
-            _remember_dropped_turn(str(role).upper(), turn_text)
-
-            if len(text) > 600:
-                text = text[:420].rstrip() + " ... " + text[-160:].lstrip()
-
-            if role == "user" and text:
-                user_asks.append(text)
-            elif role == "assistant":
-                tool_names: list[str] = []
-                for tc in msg.get("tool_calls") or []:
-                    name, _args = _extract_tool_call_name_and_args(tc)
-                    tool_names.append(name)
-                if tool_names:
-                    assistant_actions.append(
-                        "Called tool(s): " + ", ".join(tool_names[:6])
-                    )
-                elif text:
-                    assistant_actions.append(text)
-            elif role == "tool":
-                call_id = str(msg.get("tool_call_id") or "")
-                tool_name, tool_args = call_id_to_tool.get(call_id, ("unknown", ""))
-                tool_actions.append(
-                    _summarize_tool_result(tool_name, tool_args, text or "")
-                )
-                if re.search(
-                    r"\b(error|failed|exception|traceback|timeout|timed out|fatal)\b",
-                    text,
-                    re.I,
-                ):
-                    blockers.append(text[:500])
-
-        def _bullets(items: list[str], limit: int = 8) -> str:
-            unique: list[str] = []
-            seen: set[str] = set()
-            for item in items:
-                item = item.strip()
-                if not item or item in seen:
-                    continue
-                seen.add(item)
-                unique.append(item)
-                if len(unique) >= limit:
-                    break
-            return "\n".join(f"- {item}" for item in unique) if unique else "None."
-
-        completed: list[str] = []
-        for idx, item in enumerate((assistant_actions + tool_actions)[:12], start=1):
-            completed.append(f"{idx}. {item}")
-
-        active_task = (
-            f"User asked: {user_asks[-1]!r}"
-            if user_asks
-            else "Unknown from deterministic fallback."
-        )
-        previous_summary_note = ""
-        if self._previous_summary:
-            previous_summary_note = (
-                "\n\nPrevious compaction summary was present and should still be treated as "
-                "background continuity context, but the latest LLM summary update failed."
-            )
-
-        reason_text = f" Summary failure reason: {reason}." if reason else ""
-        body = f"""## Active Task
-{active_task}
-
-## Goal
-Recovered from a deterministic fallback because the LLM context summarizer was unavailable. Continue from the protected recent messages after this summary and use current file/system state for exact details.{previous_summary_note}
-
-## Constraints & Preferences
-- This fallback was generated locally without an LLM summary call.
-- Secrets and credentials were redacted before preservation.
-- The summary may be incomplete; prefer verifying current files, git state, processes, and test results instead of assuming omitted details.
-
-## Completed Actions
-{chr(10).join(completed) if completed else "None recoverable from compacted turns."}
-
-## Active State
-Unknown from deterministic fallback. Inspect current repository/session state if needed.
-
-## In Progress
-{active_task}
-
-## Blocked
-{_bullets(blockers, limit=5)}
-
-## Key Decisions
-None recoverable from deterministic fallback.
-
-## Resolved Questions
-None recoverable from deterministic fallback.
-
-## Pending User Asks
-{active_task}
-
-## Relevant Files
-{_bullets(relevant_files, limit=12)}
-
-## Remaining Work
-Continue from the most recent unfulfilled user ask and protected tail messages. Verify state with tools before making claims.
-
-## Last Dropped Turns
-{_bullets(last_dropped_turns, limit=8)}
-
-## Critical Context
-Summary generation was unavailable, so this is a best-effort deterministic fallback for {len(turns_to_summarize)} compacted message(s).{reason_text}"""
-        summary = self._with_summary_prefix(redact_sensitive_text(body.strip()))
-        if len(summary) > _FALLBACK_SUMMARY_MAX_CHARS:
-            summary = summary[: _FALLBACK_SUMMARY_MAX_CHARS - 42].rstrip() + "\n...[fallback summary truncated]"
-        return summary
-
     def _fallback_to_main_for_compression(self, e: Exception, reason: str) -> None:
         """Switch from a separate ``summary_model`` back to the main model.
 
@@ -1138,11 +911,7 @@ Summary generation was unavailable, so this is a best-effort deterministic fallb
         self.summary_model = ""  # empty = use main model
         self._summary_failure_cooldown_until = 0.0  # no cooldown — retry immediately
 
-    def _generate_summary(
-        self,
-        turns_to_summarize: List[Dict[str, Any]],
-        focus_topic: Optional[str] = None,
-    ) -> Optional[str]:
+    def _generate_summary(self, turns_to_summarize: List[Dict[str, Any]], focus_topic: str = None) -> Optional[str]:
         """Generate a structured summary of conversation turns.
 
         Uses a structured template (Goal, Progress, Decisions, Resolved/Pending
@@ -1839,9 +1608,9 @@ The user has requested that this compaction PRIORITISE preserving all informatio
         #   True  → ABORT compression entirely. Return messages unchanged
         #           and set _last_compress_aborted=True so callers can warn
         #           the user and stop the auto-compress retry loop.
-        #   False → Fall through to the default fallback path below: insert
-        #           a deterministic "summary unavailable" handoff and drop
-        #           the middle window.  Records _last_summary_fallback_used /
+        #   False → Fall through to the legacy fallback path below: insert
+        #           a static "summary unavailable" placeholder and drop the
+        #           middle window.  Records _last_summary_fallback_used /
         #           _last_summary_dropped_count for gateway hygiene to
         #           surface a warning.
         # Default is False (historical behavior).
@@ -1874,18 +1643,21 @@ The user has requested that this compaction PRIORITISE preserving all informatio
                     )
             compressed.append(msg)
 
-        # If LLM summary failed, insert a deterministic fallback so the model
-        # gets at least locally recoverable continuity anchors instead of a
-        # content-free "N messages were removed" marker.
+        # Legacy fallback path: LLM summary failed and abort_on_summary_failure
+        # is False (the default).  Insert a static placeholder so the model
+        # knows context was lost rather than silently dropping everything.
         if not summary:
             if not self.quiet_mode:
-                logger.warning("Summary generation failed — inserting deterministic fallback context summary")
+                logger.warning("Summary generation failed — inserting static fallback context marker")
             n_dropped = compress_end - compress_start
             self._last_summary_dropped_count = n_dropped
             self._last_summary_fallback_used = True
-            summary = self._build_static_fallback_summary(
-                turns_to_summarize,
-                reason=self._last_summary_error,
+            summary = (
+                f"{SUMMARY_PREFIX}\n"
+                f"Summary generation was unavailable. {n_dropped} message(s) were "
+                f"removed to free context space but could not be summarized. The removed "
+                f"messages contained earlier work in this session. Continue based on the "
+                f"recent messages below and the current state of any files or resources."
             )
 
         _merge_summary_into_tail = False

agent/conversation_compression.py

@@ -34,33 +34,13 @@ import tempfile
 import uuid
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Optional, Tuple
+from typing import Any, List, Optional, Tuple
 
 from agent.model_metadata import estimate_request_tokens_rough
 
 logger = logging.getLogger(__name__)
 
 
-def _compression_lock_holder(agent: Any) -> str:
-    """Build a unique holder id for the lock: pid:tid:agent-instance:uuid.
-
-    The pid+tid prefix lets ops tell crashed/abandoned holders apart from
-    live ones (expiry-based recovery uses the timestamp, but ``holder``
-    is what shows up in diagnostics + log lines). The agent instance id
-    and a per-acquire uuid disambiguate two co-resident agents on the
-    same thread (background_review forks run on a worker thread, but
-    on machines where compression itself dispatches to a thread pool
-    we want each acquire to be unique).
-    """
-    import threading
-    return (
-        f"pid={os.getpid()}"
-        f":tid={threading.get_ident()}"
-        f":agent={id(agent):x}"
-        f":nonce={uuid.uuid4().hex[:8]}"
-    )
-
-
 def check_compression_model_feasibility(agent: Any) -> None:
     """Warn at session start if the auxiliary compression model's context
     window is smaller than the main model's compression threshold.
@@ -325,103 +305,6 @@ def compress_context(
         "🗜️ Compacting context — summarizing earlier conversation so I can continue..."
     )
 
-    # ── Compression lock ────────────────────────────────────────────────
-    # Atomic, state.db-backed lock per session_id.  Without this, two
-    # AIAgent instances that share the same session_id (most commonly the
-    # parent-turn agent and its background-review fork — see
-    # ``agent/background_review.py``: ``review_agent.session_id =
-    # agent.session_id``) can each call compress() on overlapping
-    # snapshots of the same conversation.  Both succeed, both rotate
-    # ``agent.session_id`` to a fresh id, both create child sessions in
-    # state.db parented to the same old id.  The gateway's SessionEntry
-    # only catches one rotation, so the other child becomes an orphan
-    # that silently accumulates writes — Damien's repro shape.
-    #
-    # Acquire keyed on the OLD session_id (the rotation target's parent),
-    # because that's the id that competing paths see and read from
-    # SessionEntry at the start of their own compression attempt.
-    #
-    # If we can't acquire the lock, another path is mid-compression on
-    # this session.  Aborting is correct: the messages are unchanged, the
-    # other path's rotation will produce the canonical new session_id,
-    # and our caller's auto-compress loop sees ``len(returned) == len(input)``
-    # and stops retrying for this cycle. The session is NOT corrupted —
-    # we just sit out this round and let the winner finish.
-    _lock_db = getattr(agent, "_session_db", None)
-    _lock_sid = agent.session_id or ""
-    _lock_holder: Optional[str] = None
-    # Probe whether the lock subsystem is actually available on this
-    # SessionDB instance.  A process running mismatched module versions
-    # (e.g. ``conversation_compression.py`` reloaded after a pull but the
-    # long-lived ``hermes_state.SessionDB`` class still bound to the
-    # pre-#34351 version in memory) has the call site but not the method.
-    # In that case ``try_acquire_compression_lock`` raises AttributeError —
-    # NOT a ``sqlite3.Error`` — so the method's own fail-open guard never
-    # runs and the exception propagates to the outer agent loop, which
-    # prints the error and retries.  Because compression never succeeds,
-    # the token count never drops and the loop re-triggers compaction
-    # forever (the "API call #47/#48/#49 ... has no attribute
-    # try_acquire_compression_lock" spin).  Fail OPEN here: if the lock
-    # subsystem is missing or broken in any unexpected way, skip locking
-    # and proceed with compression.  Skipping the lock risks a rare
-    # concurrent-compression session fork; an infinite no-progress loop
-    # that never compresses at all is strictly worse.
-    if _lock_db is not None and _lock_sid:
-        _lock_holder = _compression_lock_holder(agent)
-        try:
-            _lock_acquired = _lock_db.try_acquire_compression_lock(
-                _lock_sid, _lock_holder
-            )
-        except Exception as _lock_err:
-            # Broken/absent lock subsystem (version skew, etc.).  Log once
-            # per session and proceed WITHOUT the lock rather than letting
-            # the exception spin the outer loop.
-            _lock_holder = None  # we don't own anything to release
-            if getattr(agent, "_last_compression_lock_error_sid", None) != _lock_sid:
-                agent._last_compression_lock_error_sid = _lock_sid
-                logger.warning(
-                    "compression lock subsystem unavailable for session=%s "
-                    "(%s: %s) — proceeding without lock. This usually means a "
-                    "stale in-memory module after an update; restart the "
-                    "process (or `hermes update`) to resync.",
-                    _lock_sid, type(_lock_err).__name__, _lock_err,
-                )
-            _lock_acquired = True  # treat as acquired-but-unlocked; proceed
-        if not _lock_acquired:
-            try:
-                existing = _lock_db.get_compression_lock_holder(_lock_sid)
-            except Exception:
-                existing = None
-            logger.warning(
-                "compression skipped: another path is compressing session=%s "
-                "(holder=%s) — returning messages unchanged to avoid session fork",
-                _lock_sid, existing,
-            )
-            _lock_holder = None  # don't release a lock we don't own
-            # Surface to the user once — quiet for downstream auto-compress loops
-            if getattr(agent, "_last_compression_lock_warning_sid", None) != _lock_sid:
-                agent._last_compression_lock_warning_sid = _lock_sid
-                try:
-                    agent._emit_warning(
-                        "⚠ Skipping concurrent compression — another path "
-                        "is already compressing this session. Will retry "
-                        "after it finishes."
-                    )
-                except Exception:
-                    pass
-            _existing_sp = getattr(agent, "_cached_system_prompt", None)
-            if not _existing_sp:
-                _existing_sp = agent._build_system_prompt(system_message)
-            return messages, _existing_sp
-
-    def _release_lock() -> None:
-        """Release the lock keyed on the OLD session_id (before rotation)."""
-        if _lock_db is not None and _lock_sid and _lock_holder:
-            try:
-                _lock_db.release_compression_lock(_lock_sid, _lock_holder)
-            except Exception as _rel_err:
-                logger.debug("compression lock release failed: %s", _rel_err)
-
     # Notify external memory provider before compression discards context
     if agent._memory_manager:
         try:
@@ -435,11 +318,6 @@ def compress_context(
         # Plugin context engine with strict signature that doesn't accept
         # focus_topic / force — fall back to calling without them.
         compressed = agent.context_compressor.compress(messages, current_tokens=approx_tokens)
-    except BaseException:
-        # ANY exception during compress() must release the lock so the
-        # session isn't permanently blocked from future compression.
-        _release_lock()
-        raise
 
     # If compression aborted (aux LLM failed to produce a usable summary)
     # the compressor returns the input messages unchanged.  Surface the
@@ -458,7 +336,6 @@ def compress_context(
         _existing_sp = getattr(agent, "_cached_system_prompt", None)
         if not _existing_sp:
             _existing_sp = agent._build_system_prompt(system_message)
-        _release_lock()  # compression aborted — no rotation will happen
         return messages, _existing_sp
 
     summary_error = getattr(agent.context_compressor, "_last_summary_error", None)
@@ -603,12 +480,6 @@ def compress_context(
         agent.session_id or "none", _pre_msg_count, len(compressed),
         f"{_compressed_est:,}",
     )
-    # Release the lock on the OLD session_id only AFTER rotation completed
-    # and all post-rotation bookkeeping (memory manager, context engine,
-    # file dedup) ran. A concurrent path that wakes up the moment we
-    # release will see the NEW session_id in state.db / SessionEntry and
-    # acquire on that — no race against our just-finished work.
-    _release_lock()
     return compressed, new_system_prompt
 
 

agent/conversation_loop.py

@@ -27,6 +27,8 @@ import time
 import uuid
 from typing import Any, Dict, List, Optional
 
+from agent.plugin_registries import registries as _registries
+from agent.auxiliary_client import set_runtime_main
 from agent.codex_responses_adapter import _summarize_user_message_for_log
 from agent.display import KawaiiSpinner
 from agent.error_classifier import FailoverReason, classify_api_error
@@ -51,13 +53,20 @@ from agent.model_metadata import (
     parse_available_output_tokens_from_error,
     save_context_length,
 )
+from agent.nous_rate_guard import (
+    clear_nous_rate_limit,
+    is_genuine_nous_rate_limit,
+    nous_rate_limit_remaining,
+    record_nous_rate_limit,
+)
 from agent.process_bootstrap import _install_safe_stdio
 from agent.prompt_caching import apply_anthropic_cache_control
 from agent.retry_utils import jittered_backoff
 from agent.trajectory import has_incomplete_scratchpad
 from agent.usage_pricing import estimate_usage_cost, normalize_usage
-from hermes_constants import PARTIAL_STREAM_STUB_ID
+from hermes_constants import display_hermes_home as _dhh_fn, PARTIAL_STREAM_STUB_ID
 from hermes_logging import set_session_context
+from tools.schema_sanitizer import strip_pattern_and_format
 from tools.skill_provenance import set_current_write_origin
 from utils import base_url_host_matches, env_var_enabled
 
@@ -203,13 +212,15 @@ def _print_billing_or_entitlement_guidance(
 def _try_refresh_nous_paid_entitlement_credentials(agent) -> bool:
     """Refresh Nous runtime credentials after a fresh paid-entitlement check."""
     try:
+        from hermes_cli.auth import NOUS_INFERENCE_AUTH_MODE_LEGACY
         from hermes_cli.nous_account import get_nous_portal_account_info
 
         account_info = get_nous_portal_account_info(force_fresh=True)
         if account_info.paid_service_access is not True:
             return False
         return agent._try_refresh_nous_client_credentials(
-            force=True,
+            force=False,
+            inference_auth_mode=NOUS_INFERENCE_AUTH_MODE_LEGACY,
         )
     except Exception:
         return False
@@ -398,6 +409,7 @@ def run_conversation(
 
     # Tag all log records on this thread with the session ID so
     # ``hermes logs --session <id>`` can filter a single conversation.
+    from hermes_logging import set_session_context
     set_session_context(agent.session_id)
 
     # Bind the skill write-origin ContextVar for this thread so tool
@@ -406,6 +418,7 @@ def run_conversation(
     # a foreground user-directed turn. Set at the top of each call;
     # the review fork runs on its own thread with a fresh context,
     # so the foreground value here does not leak into it.
+    from tools.skill_provenance import set_current_write_origin
     set_current_write_origin(getattr(agent, "_memory_write_origin", "assistant_tool"))
 
     # If the previous turn activated fallback, restore the primary
@@ -2370,8 +2383,8 @@ def run_conversation(
                     and not anthropic_auth_retry_attempted
                 ):
                     anthropic_auth_retry_attempted = True
-                    from agent.anthropic_adapter import _is_oauth_token
-                    from agent.azure_identity_adapter import is_token_provider
+                    _is_oauth_token = _registries.get_provider_service("anthropic", "_is_oauth_token")
+                    is_token_provider = _registries.get_provider_service("azure", "is_token_provider")
                     if agent._try_refresh_anthropic_client_credentials():
                         print(f"{agent.log_prefix}🔐 Anthropic credentials refreshed after 401. Retrying request...")
                         continue
@@ -2388,7 +2401,7 @@ def run_conversation(
                         print(f"{agent.log_prefix}   Run `hermes doctor` for credential-chain diagnostics, or")
                         print(f"{agent.log_prefix}   `az login` if your developer session expired.")
                     else:
-                        auth_method = "Bearer (OAuth/setup-token)" if _is_oauth_token(key) else "x-api-key (API key)"
+                        auth_method = "Bearer (OAuth/setup-token)" if (_is_oauth_token is not None and _is_oauth_token(key)) else "x-api-key (API key)"
                         print(f"{agent.log_prefix}   Auth method: {auth_method}")
                         print(f"{agent.log_prefix}   Token prefix: {key[:12]}..." if isinstance(key, str) and len(key) > 12 else f"{agent.log_prefix}   Token: (empty or short)")
                     print(f"{agent.log_prefix}   Troubleshooting:")
@@ -4301,54 +4314,36 @@ def run_conversation(
             )
         final_response = agent._handle_max_iterations(messages, api_call_count)
 
-        # If running as a kanban worker, signal the dispatcher that the
-        # worker could not complete (rather than treating it as a
+        # If running as a kanban worker, block the task so the dispatcher
+        # knows the worker could not complete (rather than treating it as a
         # protocol violation).  The agent loop strips tools before calling
         # _handle_max_iterations, so the model cannot call kanban_block
         # itself — we must do it on its behalf.
-        #
-        # We route through ``_record_task_failure(outcome="timed_out")``
-        # rather than ``kanban_block`` so this counts toward the
-        # ``consecutive_failures`` counter and the dispatcher's
-        # ``failure_limit`` circuit breaker (#29747 gap 2).  Without this,
-        # a task whose worker keeps exhausting its budget would block
-        # silently each run, get auto-promoted by the operator (or never
-        # surface), and re-block in an endless loop with no signal.
         _kanban_task = os.environ.get("HERMES_KANBAN_TASK")
         if _kanban_task:
             try:
-                from hermes_cli import kanban_db as _kb
-                _conn = _kb.connect()
-                try:
-                    _kb._record_task_failure(
-                        _conn,
-                        _kanban_task,
-                        error=(
+                _ra().handle_function_call(
+                    "kanban_block",
+                    {
+                        "task_id": _kanban_task,
+                        "reason": (
                             f"Iteration budget exhausted "
                             f"({api_call_count}/{agent.max_iterations}) — "
                             "task could not complete within the allowed "
                             "iterations"
                         ),
-                        outcome="timed_out",
-                        release_claim=True,
-                        end_run=True,
-                        event_payload_extra={
-                            "budget_used": api_call_count,
-                            "budget_max": agent.max_iterations,
-                        },
-                    )
-                    logger.info(
-                        "recorded budget-exhausted failure for task %s (%d/%d)",
-                        _kanban_task, api_call_count, agent.max_iterations,
-                    )
-                finally:
-                    try:
-                        _conn.close()
-                    except Exception:
-                        pass
+                    },
+                    task_id=effective_task_id,
+                )
+                logger.info(
+                    "kanban_block called for task %s after iteration "
+                    "exhaustion (%d/%d)",
+                    _kanban_task, api_call_count, agent.max_iterations,
+                )
             except Exception:
                 logger.warning(
-                    "Failed to record budget-exhausted failure for task %s",
+                    "Failed to call kanban_block after iteration "
+                    "exhaustion for task %s",
                     _kanban_task,
                     exc_info=True,
                 )

agent/credential_pool.py

@@ -14,7 +14,7 @@ from datetime import datetime, timezone
 from typing import Any, Dict, List, Optional, Set, Tuple
 
 from hermes_constants import OPENROUTER_BASE_URL
-from hermes_cli.config import load_env
+from hermes_cli.config import get_env_value, load_env
 from agent.credential_persistence import (
     is_borrowed_credential_source,
     sanitize_borrowed_credential_payload,
@@ -22,6 +22,7 @@ from agent.credential_persistence import (
 import hermes_cli.auth as auth_mod
 from hermes_cli.auth import (
     CODEX_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
+    DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
     PROVIDER_REGISTRY,
     _auth_store_lock,
     _codex_access_token_is_expiring,
@@ -54,38 +55,6 @@ def _load_config_safe() -> Optional[dict]:
 
 STATUS_OK = "ok"
 STATUS_EXHAUSTED = "exhausted"
-# Terminal failure — the credential will never recover on its own.  Used for
-# upstream-permanent OAuth states like ``token_invalidated`` / ``token_revoked``
-# where retrying after a TTL cooldown is guaranteed to fail.  ``DEAD`` entries
-# are excluded from rotation unconditionally and only clear when an explicit
-# write-side sync (e.g. ``_save_codex_tokens`` after a fresh device-code
-# login) rewrites the tokens.
-STATUS_DEAD = "dead"
-
-# OAuth error reasons that indicate the credential is permanently invalid
-# server-side and cannot be recovered by retry/refresh.  Sourced from
-# OpenAI Codex Responses API, Anthropic, xAI, and Google OAuth spec.
-_TERMINAL_AUTH_REASONS = frozenset({
-    "token_invalidated",   # OpenAI Codex: "Your authentication token has been invalidated."
-    "token_revoked",        # OAuth 2.0 RFC 7009: token explicitly revoked
-    "invalid_token",        # RFC 6750: bearer token is malformed/expired/revoked
-    "invalid_grant",        # RFC 6749: refresh_token rejected during refresh
-    "unauthorized_client",  # RFC 6749: client no longer authorized
-    "refresh_token_reused", # Single-use refresh token consumed by another process
-})
-
-# How long a DEAD manual credential is preserved before being pruned.
-# Manual entries (``manual:*``) are independent credentials with no singleton
-# to re-seed from, so pruning them after a quiet window cleans up dead state
-# without losing recoverability — the user always has the option to re-add
-# via ``hermes auth add``.
-#
-# Singleton-seeded entries (``device_code``, ``loopback_pkce``, ``claude_code``)
-# are NOT pruned because ``_seed_from_singletons`` would just re-create them
-# on the next ``load_pool()`` with the same stale singleton tokens, defeating
-# the cleanup.  They remain in the pool marked DEAD until an explicit re-auth
-# write-side sync (``_save_codex_tokens`` etc.) clears the status.
-DEAD_MANUAL_PRUNE_TTL_SECONDS = 24 * 60 * 60  # 24 hours
 
 AUTH_TYPE_OAUTH = "oauth"
 AUTH_TYPE_API_KEY = "api_key"
@@ -202,22 +171,8 @@ class PooledCredential:
     def runtime_api_key(self) -> str:
         if self.provider == "nous":
             # Nous stores the runtime inference credential in agent_key for
-            # compatibility. It must be a NAS invoke JWT.
-            for token, expires_at in (
-                (self.agent_key, self.agent_key_expires_at),
-                (self.access_token, self.expires_at),
-            ):
-                if (
-                    isinstance(token, str)
-                    and token.strip()
-                    and auth_mod._nous_invoke_jwt_is_usable(
-                        token,
-                        scope=getattr(self, "scope", None),
-                        expires_at=expires_at,
-                    )
-                ):
-                    return token.strip()
-            return ""
+            # compatibility. It may be a NAS invoke JWT or legacy opaque key.
+            return str(self.agent_key or self.access_token or "")
         return str(self.access_token or "")
 
     @property
@@ -483,29 +438,6 @@ class CredentialPool:
             [entry.to_dict() for entry in self._entries],
         )
 
-    def _is_terminal_auth_failure(
-        self,
-        status_code: Optional[int],
-        normalized_error: Dict[str, Any],
-    ) -> bool:
-        """Detect upstream-permanent OAuth failures that won't recover on TTL.
-
-        Only fires for 401 responses whose error code/reason matches a known
-        terminal OAuth state (token_invalidated, token_revoked, invalid_grant,
-        etc.).  Distinguishes permanent failures from transient ones like
-        token_expired (refreshable) or generic 401 without a specific reason
-        (could be a server-side glitch worth retrying).
-
-        Returns False for non-401 status codes — 429 rate limits and 402
-        billing failures are transient by nature and should keep TTL semantics.
-        """
-        if status_code != 401:
-            return False
-        reason = normalized_error.get("reason")
-        if not isinstance(reason, str):
-            return False
-        return reason.strip().lower() in _TERMINAL_AUTH_REASONS
-
     def _mark_exhausted(
         self,
         entry: PooledCredential,
@@ -513,20 +445,9 @@ class CredentialPool:
         error_context: Optional[Dict[str, Any]] = None,
     ) -> PooledCredential:
         normalized_error = _normalize_error_context(error_context)
-        # Permanent OAuth failures (token_invalidated, token_revoked, etc.)
-        # transition to STATUS_DEAD instead of STATUS_EXHAUSTED.  Without this,
-        # a revoked credential gets a 1-hour TTL cooldown and then re-enters
-        # rotation, failing immediately every hour until the user manually
-        # removes it (issue #32849).  DEAD entries are excluded from rotation
-        # unconditionally and only clear via an explicit re-auth write-side
-        # sync (``_save_codex_tokens`` after a fresh device-code login).
-        if self._is_terminal_auth_failure(status_code, normalized_error):
-            terminal_status = STATUS_DEAD
-        else:
-            terminal_status = STATUS_EXHAUSTED
         updated = replace(
             entry,
-            last_status=terminal_status,
+            last_status=STATUS_EXHAUSTED,
             last_status_at=time.time(),
             last_error_code=status_code,
             last_error_reason=normalized_error.get("reason"),
@@ -537,43 +458,6 @@ class CredentialPool:
         self._persist()
         return updated
 
-    def _sync_anthropic_entry_from_credentials_file(self, entry: PooledCredential) -> PooledCredential:
-        """Sync a claude_code pool entry from ~/.claude/.credentials.json if tokens differ.
-
-        OAuth refresh tokens are single-use. When something external (e.g.
-        Claude Code CLI, or another profile's pool) refreshes the token, it
-        writes the new pair to ~/.claude/.credentials.json. The pool entry's
-        refresh token becomes stale. This method detects that and syncs.
-        """
-        if self.provider != "anthropic" or entry.source != "claude_code":
-            return entry
-        try:
-            from agent.anthropic_adapter import read_claude_code_credentials
-            creds = read_claude_code_credentials()
-            if not creds:
-                return entry
-            file_refresh = creds.get("refreshToken", "")
-            file_access = creds.get("accessToken", "")
-            file_expires = creds.get("expiresAt", 0)
-            # If the credentials file has a different token pair, sync it
-            if file_refresh and file_refresh != entry.refresh_token:
-                logger.debug("Pool entry %s: syncing tokens from credentials file (refresh token changed)", entry.id)
-                updated = replace(
-                    entry,
-                    access_token=file_access,
-                    refresh_token=file_refresh,
-                    expires_at_ms=file_expires,
-                    last_status=None,
-                    last_status_at=None,
-                    last_error_code=None,
-                )
-                self._replace_entry(entry, updated)
-                self._persist()
-                return updated
-        except Exception as exc:
-            logger.debug("Failed to sync from credentials file: %s", exc)
-        return entry
-
     def _sync_codex_entry_from_auth_store(self, entry: PooledCredential) -> PooledCredential:
         """Sync a Codex device_code pool entry from auth.json if tokens differ.
 
@@ -863,32 +747,11 @@ class CredentialPool:
             return None
 
         try:
-            if self.provider == "anthropic":
-                from agent.anthropic_adapter import refresh_anthropic_oauth_pure
-
-                refreshed = refresh_anthropic_oauth_pure(
-                    entry.refresh_token,
-                    use_json=entry.source.endswith("hermes_pkce"),
-                )
-                updated = replace(
-                    entry,
-                    access_token=refreshed["access_token"],
-                    refresh_token=refreshed["refresh_token"],
-                    expires_at_ms=refreshed["expires_at_ms"],
-                )
-                # Keep ~/.claude/.credentials.json in sync so that the
-                # fallback path (resolve_anthropic_token) and other profiles
-                # see the latest tokens.
-                if entry.source == "claude_code":
-                    try:
-                        from agent.anthropic_adapter import _write_claude_code_credentials
-                        _write_claude_code_credentials(
-                            refreshed["access_token"],
-                            refreshed["refresh_token"],
-                            refreshed["expires_at_ms"],
-                        )
-                    except Exception as wexc:
-                        logger.debug("Failed to write refreshed token to credentials file: %s", wexc)
+            # ── Plugin-registered credential pool hooks ──
+            from agent.plugin_registries import registries as _cph_reg2
+            _hook = _cph_reg2.get_credential_pool_hook(self.provider)
+            if _hook is not None and _hook.refresh_oauth is not None:
+                updated = _hook.refresh_oauth(entry, pool=self)
             elif self.provider == "openai-codex":
                 # Adopt fresher tokens from auth.json before spending the
                 # refresh_token — single-use tokens consumed by another Hermes
@@ -931,53 +794,30 @@ class CredentialPool:
                 if synced is not entry:
                     entry = synced
                 auth_mod.resolve_nous_runtime_credentials(
-                    force_refresh=force,
+                    min_key_ttl_seconds=DEFAULT_AGENT_KEY_MIN_TTL_SECONDS,
+                    inference_auth_mode=(
+                        auth_mod.NOUS_INFERENCE_AUTH_MODE_LEGACY
+                        if force
+                        else auth_mod.NOUS_INFERENCE_AUTH_MODE_AUTO
+                    ),
                 )
                 updated = self._sync_nous_entry_from_auth_store(entry)
             else:
                 return entry
         except Exception as exc:
             logger.debug("Credential refresh failed for %s/%s: %s", self.provider, entry.id, exc)
-            # For anthropic claude_code entries: the refresh token may have been
-            # consumed by another process. Check if ~/.claude/.credentials.json
-            # has a newer token pair and retry once.
-            if self.provider == "anthropic" and entry.source == "claude_code":
-                synced = self._sync_anthropic_entry_from_credentials_file(entry)
-                if synced.refresh_token != entry.refresh_token:
-                    logger.debug("Retrying refresh with synced token from credentials file")
-                    try:
-                        from agent.anthropic_adapter import refresh_anthropic_oauth_pure
-                        refreshed = refresh_anthropic_oauth_pure(
-                            synced.refresh_token,
-                            use_json=synced.source.endswith("hermes_pkce"),
-                        )
-                        updated = replace(
-                            synced,
-                            access_token=refreshed["access_token"],
-                            refresh_token=refreshed["refresh_token"],
-                            expires_at_ms=refreshed["expires_at_ms"],
-                            last_status=STATUS_OK,
-                            last_status_at=None,
-                            last_error_code=None,
-                        )
-                        self._replace_entry(synced, updated)
-                        self._persist()
-                        try:
-                            from agent.anthropic_adapter import _write_claude_code_credentials
-                            _write_claude_code_credentials(
-                                refreshed["access_token"],
-                                refreshed["refresh_token"],
-                                refreshed["expires_at_ms"],
-                            )
-                        except Exception as wexc:
-                            logger.debug("Failed to write refreshed token to credentials file (retry path): %s", wexc)
-                        return updated
-                    except Exception as retry_exc:
-                        logger.debug("Retry refresh also failed: %s", retry_exc)
-                elif not self._entry_needs_refresh(synced):
-                    # Credentials file had a valid (non-expired) token — use it directly
-                    logger.debug("Credentials file has valid token, using without refresh")
-                    return synced
+            # ── Plugin-registered credential pool hooks ──
+            # The hook's refresh_oauth already handles retry-with-sync internally,
+            # so if we got here it means a non-hook provider failed.
+            from agent.plugin_registries import registries as _cph_reg3
+            _hook = _cph_reg3.get_credential_pool_hook(self.provider)
+            if _hook is not None and _hook.sync_from_credentials_file is not None:
+                # Give the hook a chance to sync from external file
+                synced = _hook.sync_from_credentials_file(entry)
+                if synced is not entry:
+                    entry = synced
+                    self._replace_entry(entry, synced)
+                    self._persist()
             # For xai-oauth: same race as nous — another process may have
             # consumed the refresh token between our proactive sync and the
             # HTTP call.  Re-check auth.json and adopt the fresh tokens if
@@ -1198,10 +1038,11 @@ class CredentialPool:
     def _entry_needs_refresh(self, entry: PooledCredential) -> bool:
         if entry.auth_type != AUTH_TYPE_OAUTH:
             return False
-        if self.provider == "anthropic":
-            if entry.expires_at_ms is None:
-                return False
-            return int(entry.expires_at_ms) <= int(time.time() * 1000) + 120_000
+        # ── Plugin-registered credential pool hooks ──
+        from agent.plugin_registries import registries as _cph_reg
+        _hook = _cph_reg.get_credential_pool_hook(self.provider)
+        if _hook is not None and _hook.needs_refresh is not None:
+            return _hook.needs_refresh(entry)
         if self.provider == "openai-codex":
             return _codex_access_token_is_expiring(
                 entry.access_token,
@@ -1213,7 +1054,7 @@ class CredentialPool:
                 auth_mod.XAI_ACCESS_TOKEN_REFRESH_SKEW_SECONDS,
             )
         if self.provider == "nous":
-            # Nous refresh can require network access and should happen when
+            # Nous refresh/mint can require network access and should happen when
             # runtime credentials are actually resolved, not merely when the pool
             # is enumerated for listing, migration, or selection.
             return False
@@ -1232,15 +1073,18 @@ class CredentialPool:
         """
         now = time.time()
         cleared_any = False
-        entries_to_prune: List[str] = []
         available: List[PooledCredential] = []
         for entry in self._entries:
-            # For anthropic claude_code entries, sync from the credentials file
-            # before any status/refresh checks. This picks up tokens refreshed
-            # by other processes (Claude Code CLI, other Hermes profiles).
-            if (self.provider == "anthropic" and entry.source == "claude_code"
-                    and entry.last_status in {STATUS_EXHAUSTED, STATUS_DEAD}):
-                synced = self._sync_anthropic_entry_from_credentials_file(entry)
+            # ── Plugin-registered credential pool hooks ──
+            # Sync exhausted entries from external credentials files before
+            # status/refresh checks. This picks up tokens refreshed by other
+            # processes (e.g. Claude Code CLI, other Hermes profiles).
+            from agent.plugin_registries import registries as _cph_reg4
+            _avail_hook = _cph_reg4.get_credential_pool_hook(self.provider)
+            if (_avail_hook is not None
+                    and _avail_hook.sync_from_credentials_file is not None
+                    and entry.last_status == STATUS_EXHAUSTED):
+                synced = _avail_hook.sync_from_credentials_file(entry)
                 if synced is not entry:
                     entry = synced
                     cleared_any = True
@@ -1250,7 +1094,7 @@ class CredentialPool:
             # exhausted status stale.
             if (self.provider == "nous"
                     and entry.source == "device_code"
-                    and entry.last_status in {STATUS_EXHAUSTED, STATUS_DEAD}):
+                    and entry.last_status == STATUS_EXHAUSTED):
                 synced = self._sync_nous_entry_from_auth_store(entry)
                 if synced is not entry:
                     entry = synced
@@ -1262,7 +1106,7 @@ class CredentialPool:
             # future for ChatGPT weekly windows).
             if (self.provider == "openai-codex"
                     and entry.source == "device_code"
-                    and entry.last_status in {STATUS_EXHAUSTED, STATUS_DEAD}):
+                    and entry.last_status == STATUS_EXHAUSTED):
                 synced = self._sync_codex_entry_from_auth_store(entry)
                 if synced is not entry:
                     entry = synced
@@ -1273,41 +1117,11 @@ class CredentialPool:
             # xAI Grok OAuth login) has since rotated in auth.json.
             if (self.provider == "xai-oauth"
                     and entry.source == "loopback_pkce"
-                    and entry.last_status in {STATUS_EXHAUSTED, STATUS_DEAD}):
+                    and entry.last_status == STATUS_EXHAUSTED):
                 synced = self._sync_xai_oauth_entry_from_auth_store(entry)
                 if synced is not entry:
                     entry = synced
                     cleared_any = True
-            if entry.last_status == STATUS_DEAD:
-                # Manual DEAD credentials get pruned after a 24h quiet window
-                # so the pool doesn't accumulate dead entries forever.  The
-                # user can always re-add via ``hermes auth add``.  Singleton-
-                # seeded DEAD entries are kept so the audit trail (label,
-                # last_error_reason, timestamps) stays visible — pruning them
-                # would just be undone by ``_seed_from_singletons`` on the
-                # next load anyway.
-                if _is_manual_source(entry.source):
-                    dead_at = entry.last_status_at or 0
-                    if dead_at and now - dead_at > DEAD_MANUAL_PRUNE_TTL_SECONDS:
-                        _label = entry.label or entry.id[:8]
-                        logger.warning(
-                            "credential pool: pruning DEAD manual entry %s "
-                            "(reason=%s, age=%.1fh) — re-add via `hermes auth add %s`",
-                            _label,
-                            entry.last_error_reason or "unknown",
-                            (now - dead_at) / 3600.0,
-                            self.provider,
-                        )
-                        # Mark for removal after the loop completes; we can't
-                        # mutate self._entries while iterating.
-                        entries_to_prune.append(entry.id)
-                        cleared_any = True
-                # Permanently failed credentials never re-enter rotation via
-                # TTL.  They only clear when a write-side re-auth sync rewrites
-                # the tokens (e.g. ``_save_codex_tokens`` after a fresh
-                # device-code login).  The auth.json-sync paths below handle
-                # the re-auth case for OAuth singletons.
-                continue
             if entry.last_status == STATUS_EXHAUSTED:
                 exhausted_until = _exhausted_until(entry)
                 if exhausted_until is not None and now < exhausted_until:
@@ -1331,9 +1145,6 @@ class CredentialPool:
                     continue
                 entry = refreshed
             available.append(entry)
-        if entries_to_prune:
-            pruned_ids = set(entries_to_prune)
-            self._entries = [e for e in self._entries if e.id not in pruned_ids]
         if cleared_any:
             self._persist()
         return available
@@ -1401,22 +1212,11 @@ class CredentialPool:
             if entry is None:
                 return None
             _label = entry.label or entry.id[:8]
-            self._mark_exhausted(entry, status_code, error_context)
-            # Re-read the updated entry to log the correct terminal state.
-            updated_entry = next(
-                (e for e in self._entries if e.id == entry.id), entry,
+            logger.info(
+                "credential pool: marking %s exhausted (status=%s), rotating",
+                _label, status_code,
             )
-            if updated_entry.last_status == STATUS_DEAD:
-                logger.warning(
-                    "credential pool: marking %s DEAD (status=%s, reason=%s) — "
-                    "permanently failed, will NOT re-enter rotation until re-auth",
-                    _label, status_code, updated_entry.last_error_reason or "unknown",
-                )
-            else:
-                logger.info(
-                    "credential pool: marking %s exhausted (status=%s), rotating",
-                    _label, status_code,
-                )
+            self._mark_exhausted(entry, status_code, error_context)
             self._current_id = None
             next_entry = self._select_unlocked()
             if next_entry:
@@ -1634,84 +1434,15 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
         def _is_suppressed(_p, _s):  # type: ignore[misc]
             return False
 
-    if provider == "anthropic":
-        # Only auto-discover external credentials (Claude Code, Hermes PKCE)
-        # when the user has explicitly configured anthropic as their provider.
-        # Without this gate, auxiliary client fallback chains silently read
-        # ~/.claude/.credentials.json without user consent.  See PR #4210.
-        try:
-            from hermes_cli.auth import is_provider_explicitly_configured
-            if not is_provider_explicitly_configured("anthropic"):
-                return changed, active_sources
-        except ImportError:
-            pass
-
-        # API-key vs OAuth is a user-visible choice at `hermes setup` ("Claude
-        # Pro/Max subscription" vs "Anthropic API key").  The signal that the
-        # user picked the API-key path is: ANTHROPIC_API_KEY set in the env,
-        # AND no OAuth env vars set — `save_anthropic_api_key()` writes the
-        # API key and zeros ANTHROPIC_TOKEN; `save_anthropic_oauth_token()`
-        # does the inverse.  When that signal is present we MUST NOT seed
-        # autodiscovered OAuth tokens (~/.claude/.credentials.json from the
-        # Claude Code CLI, hermes_pkce creds from a previous OAuth login)
-        # into the anthropic pool — otherwise rotation on a 401/429 silently
-        # flips the session onto an OAuth credential, which forces the Claude
-        # Code identity injection, `mcp_` tool-name rewrite, and claude-cli
-        # User-Agent header (`agent/anthropic_adapter.py:2128`).  Users who
-        # explicitly opted into the API-key path are explicitly opting OUT of
-        # that masquerade.  Prefer ~/.hermes/.env over os.environ for the
-        # same reason `_seed_from_env` does — that's the authoritative file
-        # that `hermes setup` writes.
-        _env_file = load_env()
-
-        def _env_val(key: str) -> str:
-            return (_env_file.get(key) or os.environ.get(key) or "").strip()
-
-        anthropic_api_key = _env_val("ANTHROPIC_API_KEY")
-        anthropic_oauth_env = (
-            _env_val("ANTHROPIC_TOKEN") or _env_val("CLAUDE_CODE_OAUTH_TOKEN")
+    # ── Plugin-registered credential pool hooks ──
+    from agent.plugin_registries import registries as _cp_reg
+    _cp_hook = _cp_reg.get_credential_pool_hook(provider)
+    if _cp_hook is not None and _cp_hook.discover_credentials is not None:
+        hook_changed, hook_sources = _cp_hook.discover_credentials(
+            entries, provider, _is_suppressed,
         )
-        api_key_path_explicit = bool(anthropic_api_key and not anthropic_oauth_env)
-
-        if api_key_path_explicit:
-            # Prune any stale autodiscovered OAuth entries that may have been
-            # seeded into the on-disk pool during a previous OAuth session.
-            # Without this, switching OAuth -> API key at setup leaves the
-            # OAuth entries dormant in auth.json forever and rotation on a
-            # transient 401 could revive them.
-            retained = [
-                entry for entry in entries
-                if entry.source not in {"hermes_pkce", "claude_code"}
-            ]
-            if len(retained) != len(entries):
-                entries[:] = retained
-                changed = True
-            return changed, active_sources
-
-        from agent.anthropic_adapter import read_claude_code_credentials, read_hermes_oauth_credentials
-
-        for source_name, creds in (
-            ("hermes_pkce", read_hermes_oauth_credentials()),
-            ("claude_code", read_claude_code_credentials()),
-        ):
-            if creds and creds.get("accessToken"):
-                if _is_suppressed(provider, source_name):
-                    continue
-                active_sources.add(source_name)
-                changed |= _upsert_entry(
-                    entries,
-                    provider,
-                    source_name,
-                    {
-                        "source": source_name,
-                        "auth_type": AUTH_TYPE_OAUTH,
-                        "access_token": creds.get("accessToken", ""),
-                        "refresh_token": creds.get("refreshToken"),
-                        "expires_at_ms": creds.get("expiresAt"),
-                        "label": label_from_token(creds.get("accessToken", ""), source_name),
-                    },
-                )
-
+        changed |= hook_changed
+        active_sources |= hook_sources
     elif provider == "nous":
         state = _load_provider_state(auth_store, "nous")
         has_runtime_material = bool(
@@ -1756,9 +1487,9 @@ def _seed_from_singletons(provider: str, entries: List[PooledCredential]) -> Tup
                     "inference_base_url": state.get("inference_base_url"),
                     "agent_key": state.get("agent_key"),
                     "agent_key_expires_at": state.get("agent_key_expires_at"),
-                    # Carry the refresh timestamps into the pool so
+                    # Carry the mint/refresh timestamps into the pool so
                     # freshness-sensitive consumers (self-heal hooks, pool
-                    # pruning by age) can distinguish just-refreshed credentials
+                    # pruning by age) can distinguish just-minted credentials
                     # from stale ones.  Without these, fresh device_code
                     # entries get obtained_at=None and look older than they
                     # are (#15099).
@@ -2022,12 +1753,11 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
         env_url = _get_env_prefer_dotenv(pconfig.base_url_env_var).rstrip("/")
 
     env_vars = list(pconfig.api_key_env_vars)
-    if provider == "anthropic":
-        env_vars = [
-            "ANTHROPIC_TOKEN",
-            "CLAUDE_CODE_OAUTH_TOKEN",
-            "ANTHROPIC_API_KEY",
-        ]
+    # ── Plugin-registered credential pool hooks: env var order override ──
+    from agent.plugin_registries import registries as _env_reg
+    _env_hook = _env_reg.get_credential_pool_hook(provider)
+    if _env_hook is not None and _env_hook.env_var_order is not None:
+        env_vars = _env_hook.env_var_order
 
     for env_var in env_vars:
         # Prefer ~/.hermes/.env over os.environ
@@ -2038,7 +1768,11 @@ def _seed_from_env(provider: str, entries: List[PooledCredential]) -> Tuple[bool
         if _is_source_suppressed(provider, source):
             continue
         active_sources.add(source)
-        auth_type = AUTH_TYPE_OAUTH if provider == "anthropic" and not token.startswith("sk-ant-api") else AUTH_TYPE_API_KEY
+        # ── Plugin-registered credential pool hooks: auth type detection ──
+        if _env_hook is not None and _env_hook.detect_auth_type is not None:
+            auth_type = _env_hook.detect_auth_type(token)
+        else:
+            auth_type = AUTH_TYPE_API_KEY
         base_url = env_url or pconfig.inference_base_url
         if provider == "kimi-coding":
             base_url = _resolve_kimi_base_url(token, pconfig.inference_base_url, env_url)

agent/curator_backup.py

@@ -39,9 +39,12 @@ from __future__ import annotations
 
 import json
 import logging
+import os
 import re
 import shutil
 import tarfile
+import tempfile
+import time
 from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple

agent/file_safety.py

@@ -249,10 +249,6 @@ def get_read_block_error(path: str) -> Optional[str]:
         ".env",
         "webhook_subscriptions.json",
         os.path.join("auth", "google_oauth.json"),
-        # Bitwarden Secrets Manager disk cache: stores plaintext secret values
-        # to avoid re-fetching across back-to-back CLI invocations. The file
-        # was introduced by #31968 but not added to this guard.
-        os.path.join("cache", "bws_cache.json"),
     )
     for hd in hermes_dirs:
         for name in credential_file_names:

agent/google_code_assist.py

@@ -31,6 +31,7 @@ import json
 import logging
 import time
 import urllib.error
+import urllib.parse
 import urllib.request
 import uuid
 from dataclasses import dataclass, field

agent/google_oauth.py

@@ -899,15 +899,7 @@ def start_oauth_flow(
         try:
             import webbrowser
 
-            try:
-                from hermes_cli.auth import (
-                    _can_open_graphical_browser as _can_open_gui,
-                )
-            except Exception:
-                _can_open_gui = lambda: True  # noqa: E731
-
-            if _can_open_gui():
-                webbrowser.open(auth_url, new=1, autoraise=True)
+            webbrowser.open(auth_url, new=1, autoraise=True)
         except Exception as exc:
             logger.debug("webbrowser.open failed: %s", exc)
 

agent/image_routing.py

@@ -37,8 +37,6 @@ from __future__ import annotations
 import base64
 import logging
 import mimetypes
-import os
-import re
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple
 
@@ -48,102 +46,6 @@ logger = logging.getLogger(__name__)
 _VALID_MODES = frozenset({"auto", "native", "text"})
 
 
-# Image extensions used by extract_image_refs(). Kept tight on purpose — we
-# only auto-attach things the model can actually see. Documents/archives are
-# excluded because the gateway's broader extract_local_files() also routes
-# them differently (send_document), and we don't want to attach a PDF as a
-# vision part.
-_IMAGE_EXTS = (
-    ".png", ".jpg", ".jpeg", ".gif", ".webp", ".bmp", ".tiff", ".tif", ".heic",
-)
-_IMAGE_EXT_PATTERN = "|".join(e.lstrip(".") for e in _IMAGE_EXTS)
-
-# Absolute / home-relative local image path. Matches the same shape gateway's
-# extract_local_files() uses: anchors to ``~/`` or ``/``, ignores matches inside
-# URLs (the ``(?<![/:\w.])`` lookbehind), and case-insensitive on the extension.
-_LOCAL_IMAGE_PATH_RE = re.compile(
-    r"(?<![/:\w.])(?:~/|/)(?:[\w.\-]+/)*[\w.\-]+\.(?:" + _IMAGE_EXT_PATTERN + r")\b",
-    re.IGNORECASE,
-)
-
-# http(s) URL ending in an image extension (optionally followed by a
-# query string). Case-insensitive on the extension. Strict ``http(s)://``
-# scheme so we don't accidentally grab ``file://`` URLs or other shapes.
-_IMAGE_URL_RE = re.compile(
-    r"https?://[^\s<>\"']+?\.(?:" + _IMAGE_EXT_PATTERN + r")(?:\?[^\s<>\"']*)?",
-    re.IGNORECASE,
-)
-
-
-def extract_image_refs(text: str) -> Tuple[List[str], List[str]]:
-    """Scan free-form text for image references the model should see.
-
-    Returns ``(local_paths, urls)``:
-
-      * ``local_paths`` — absolute (``/``) or home-relative (``~/``) paths
-        whose suffix is an image extension AND whose expanded form exists
-        on disk as a file. Order-preserving, deduplicated.
-      * ``urls`` — ``http(s)://…`` URLs whose path ends in an image
-        extension (a ``?query`` is allowed after the extension).
-        Order-preserving, deduplicated.
-
-    Matches inside fenced code blocks (``` ``` ```) and inline backticks
-    (`` `…` ``) are skipped so that snippets pasted into a task body for
-    reference aren't mistaken for live attachments. This mirrors the
-    behaviour of ``gateway.platforms.base.BaseAdapter.extract_local_files``.
-
-    Local paths are validated against the filesystem; URLs are not
-    (the provider fetches them at request time).
-    """
-    if not isinstance(text, str) or not text:
-        return [], []
-
-    # Build spans covered by fenced code blocks and inline code so we can
-    # ignore references the author embedded purely as example text.
-    code_spans: list[tuple[int, int]] = []
-    for m in re.finditer(r"```[^\n]*\n.*?```", text, re.DOTALL):
-        code_spans.append((m.start(), m.end()))
-    for m in re.finditer(r"`[^`\n]+`", text):
-        code_spans.append((m.start(), m.end()))
-
-    def _in_code(pos: int) -> bool:
-        return any(s <= pos < e for s, e in code_spans)
-
-    local_paths: list[str] = []
-    seen_paths: set[str] = set()
-    for match in _LOCAL_IMAGE_PATH_RE.finditer(text):
-        if _in_code(match.start()):
-            continue
-        raw = match.group(0)
-        expanded = os.path.expanduser(raw)
-        try:
-            if not os.path.isfile(expanded):
-                continue
-        except OSError:
-            # ENAMETOOLONG / EINVAL on pathological inputs — skip rather than crash.
-            continue
-        if expanded in seen_paths:
-            continue
-        seen_paths.add(expanded)
-        local_paths.append(expanded)
-
-    urls: list[str] = []
-    seen_urls: set[str] = set()
-    for match in _IMAGE_URL_RE.finditer(text):
-        if _in_code(match.start()):
-            continue
-        url = match.group(0)
-        # Strip trailing punctuation that's almost certainly prose, not part
-        # of the URL (e.g. "see https://x.com/a.png." or "/a.png)").
-        url = url.rstrip(".,;:!?)]>")
-        if url in seen_urls:
-            continue
-        seen_urls.add(url)
-        urls.append(url)
-
-    return local_paths, urls
-
-
 # Strict YAML/JSON boolean coercion for capability overrides.
 #
 # ``bool("false")`` is True in Python because non-empty strings are truthy, so
@@ -418,29 +320,20 @@ def _file_to_data_url(path: Path) -> Optional[str]:
 def build_native_content_parts(
     user_text: str,
     image_paths: List[str],
-    image_urls: Optional[List[str]] = None,
 ) -> Tuple[List[Dict[str, Any]], List[str]]:
     """Build an OpenAI-style ``content`` list for a user turn.
 
     Shape:
       [{"type": "text", "text": "...\\n\\n[Image attached at: /local/path]"},
        {"type": "image_url", "image_url": {"url": "data:image/png;base64,..."}},
-       {"type": "image_url", "image_url": {"url": "https://example.com/a.png"}},
        ...]
 
-    Local paths are read from disk and embedded as base64 ``data:`` URLs.
-    Remote URLs (``http(s)://``) are passed through verbatim — the provider
-    fetches them server-side. The model still sees the pixels either way.
-
-    For each successfully attached image, a hint is appended to the text
-    part:
-
-      * local path → ``[Image attached at: <path>]``
-      * URL        → ``[Image attached: <url>]``
-
-    The hint gives the model a string handle so MCP/skill tools that take
-    an image path or URL argument can be invoked on the same image without
-    an extra round-trip. This parallels the text-mode hint produced by
+    The local path of each successfully attached image is appended to the
+    text part as ``[Image attached at: <path>]``. The model still sees the
+    pixels via the ``image_url`` part (full native vision); the path note
+    just gives it a string handle so MCP/skill tools that take an image
+    path or URL argument can be invoked on the same image without an
+    extra round-trip. This parallels the text-mode hint produced by
     ``Runner._enrich_message_with_vision`` (``vision_analyze using image_url:
     <path>``) so behaviour is consistent across both image input modes.
 
@@ -449,14 +342,12 @@ def build_native_content_parts(
     ceiling), the agent's retry loop transparently shrinks and retries
     once — see ``run_agent._try_shrink_image_parts_in_messages``.
 
-    Returns (content_parts, skipped). Skipped entries are local paths
-    that couldn't be read from disk; URLs are never skipped (they're
-    not validated here).
+    Returns (content_parts, skipped_paths). Skipped paths are files that
+    couldn't be read from disk and are NOT advertised in the path hints.
     """
     skipped: List[str] = []
     image_parts: List[Dict[str, Any]] = []
     attached_paths: List[str] = []
-    attached_urls: List[str] = []
 
     for raw_path in image_paths:
         p = Path(raw_path)
@@ -473,26 +364,16 @@ def build_native_content_parts(
         })
         attached_paths.append(str(raw_path))
 
-    for url in image_urls or []:
-        url = (url or "").strip()
-        if not url:
-            continue
-        image_parts.append({
-            "type": "image_url",
-            "image_url": {"url": url},
-        })
-        attached_urls.append(url)
-
     text = (user_text or "").strip()
 
     # If at least one image attached, build a single text part that combines
-    # the user's caption (or a neutral default) with one hint per image.
-    if attached_paths or attached_urls:
+    # the user's caption (or a neutral default) with one path hint per image.
+    if attached_paths:
         base_text = text or "What do you see in this image?"
-        hint_lines: List[str] = []
-        hint_lines.extend(f"[Image attached at: {p}]" for p in attached_paths)
-        hint_lines.extend(f"[Image attached: {u}]" for u in attached_urls)
-        combined_text = f"{base_text}\n\n" + "\n".join(hint_lines)
+        path_hints = "\n".join(
+            f"[Image attached at: {p}]" for p in attached_paths
+        )
+        combined_text = f"{base_text}\n\n{path_hints}"
         parts: List[Dict[str, Any]] = [{"type": "text", "text": combined_text}]
         parts.extend(image_parts)
         return parts, skipped
@@ -507,5 +388,4 @@ def build_native_content_parts(
 __all__ = [
     "decide_image_input_mode",
     "build_native_content_parts",
-    "extract_image_refs",
 ]

agent/lsp/cli.py

@@ -16,6 +16,7 @@ from __future__ import annotations
 
 import argparse
 import sys
+from typing import Optional
 
 
 def register_subparser(subparsers: argparse._SubParsersAction) -> None:
@@ -248,6 +249,7 @@ def _cmd_restart() -> int:
 
 def _cmd_which(server_id: str) -> int:
     from agent.lsp.install import INSTALL_RECIPES, hermes_lsp_bin_dir
+    import os
     import shutil as _shutil
 
     recipe = INSTALL_RECIPES.get(server_id)

agent/lsp/manager.py

@@ -39,20 +39,25 @@ import logging
 import os
 import threading
 import time
+from concurrent.futures import Future as ConcurrentFuture
 from typing import Any, Callable, Dict, List, Optional, Tuple
 
 from agent.lsp import eventlog
 from agent.lsp.client import (
     DIAGNOSTICS_DOCUMENT_WAIT,
     LSPClient,
+    file_uri,
 )
 from agent.lsp.servers import (
     ServerContext,
+    ServerDef,
+    SpawnSpec,
     find_server_for_file,
     language_id_for,
 )
 from agent.lsp.workspace import (
     clear_cache,
+    is_inside_workspace,
     resolve_workspace_for_file,
 )
 

agent/lsp/servers.py

@@ -25,7 +25,7 @@ import shutil
 from dataclasses import dataclass, field
 from typing import Any, Callable, Dict, List, Optional, Sequence, Tuple
 
-from agent.lsp.workspace import nearest_root
+from agent.lsp.workspace import nearest_root, normalize_path
 
 logger = logging.getLogger("agent.lsp.servers")
 

agent/model_metadata.py

@@ -1567,8 +1567,11 @@ def get_model_context_length(
         and base_url_host_matches(base_url, "amazonaws.com")
     ):
         try:
-            from agent.bedrock_adapter import get_bedrock_context_length
-            return get_bedrock_context_length(model)
+            from agent.plugin_registries import registries
+            _bedrock = registries.get_provider_namespace("bedrock")
+            get_bedrock_context_length = _bedrock.get("get_bedrock_context_length")
+            if get_bedrock_context_length is not None:
+                return get_bedrock_context_length(model)
         except ImportError:
             pass  # boto3 not installed — fall through to generic resolution
 

agent/plugin_registries.py

@@ -0,0 +1,586 @@
+"""Plugin capability registries.
+
+Each plugin's ``register(ctx)`` function populates these registries via
+``ctx.register_<capability>()``.  The core codebase then queries the
+registries instead of importing from plugin packages directly.
+
+This is the **only** coupling point between the core and plugins: the core
+imports from ``agent.plugin_registries``, never from ``hermes_agent_*``.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import (
+    Any,
+    Callable,
+    Dict,
+    List,
+    Optional,
+    Protocol,
+    Sequence,
+    Tuple,
+    Type,
+    runtime_checkable,
+)
+
+
+# ---------------------------------------------------------------------------
+# Auth providers
+# ---------------------------------------------------------------------------
+
+@runtime_checkable
+class AuthProvider(Protocol):
+    """A plugin that can provide or check authentication credentials.
+
+    Registered via ``ctx.register_auth_provider(name, provider)``.
+    Queried by ``hermes_cli/auth_commands.py``, ``doctor.py``, etc.
+    """
+
+    @property
+    def name(self) -> str: ...
+
+    def has_credentials(self) -> bool:
+        """Return True if the required credentials are present in env/config."""
+        ...
+
+    def check_env_vars(self) -> Dict[str, str | None]:
+        """Return a dict of env-var-name → current-value (or None if unset).
+
+        Used by ``hermes doctor`` to display credential status.
+        """
+        ...
+
+    def resolve_token(self, **kwargs: Any) -> Any:
+        """Resolve and return an auth token/credential for the provider.
+
+        The return type is provider-specific (string, tuple, object, etc.).
+        """
+        ...
+
+    def refresh_token(self, **kwargs: Any) -> Any:
+        """Refresh an existing token.  Raises if refresh is not supported."""
+        ...
+
+
+@dataclass
+class AuthProviderEntry:
+    provider: AuthProvider
+    """The auth provider instance."""
+
+    cli_group: str = ""
+    """CLI argument group name (e.g. 'Anthropic', 'AWS / Bedrock')."""
+
+    setup_subcommands: bool = False
+    """Whether this provider adds CLI auth subcommands (login, logout, etc.)."""
+
+
+# ---------------------------------------------------------------------------
+# Transport builders
+# ---------------------------------------------------------------------------
+
+@runtime_checkable
+class TransportBuilder(Protocol):
+    """A plugin that builds clients and converts messages for a model transport.
+
+    Registered via ``ctx.register_transport(name, builder)``.
+    Queried by ``agent/transports/`` and ``agent/auxiliary_client.py``.
+    """
+
+    def build_client(self, **kwargs: Any) -> Any:
+        """Build and return a provider-specific API client."""
+        ...
+
+    def build_kwargs(self, **kwargs: Any) -> Dict[str, Any]:
+        """Build the kwargs dict for a provider-specific API call."""
+        ...
+
+    def convert_messages(self, messages: Sequence[Any], **kwargs: Any) -> Any:
+        """Convert internal message format to provider-specific format."""
+        ...
+
+    def convert_tools(self, tools: Sequence[Any], **kwargs: Any) -> Any:
+        """Convert internal tool format to provider-specific format."""
+        ...
+
+    def normalize_response(self, response: Any, **kwargs: Any) -> Any:
+        """Normalize a provider-specific response into the internal format."""
+        ...
+
+
+# ---------------------------------------------------------------------------
+# Platform adapters
+# ---------------------------------------------------------------------------
+
+@dataclass
+class PlatformAdapterEntry:
+    """A registered platform adapter.
+
+    Registered via ``ctx.register_platform(name, entry)``.
+    Queried by ``gateway/run.py`` and ``tools/send_message_tool.py``.
+    """
+    name: str
+    """Platform identifier (e.g. 'telegram', 'slack')."""
+
+    adapter_class: Type
+    """The adapter class (e.g. TelegramAdapter)."""
+
+    check_requirements: Callable[[], bool]
+    """Check if the platform's dependencies are installed and configured."""
+
+    available_flag: str = ""
+    """Name of the module-level AVAILABLE boolean, if any."""
+
+    constants: Dict[str, Any] = field(default_factory=dict)
+    """Platform-specific constants (e.g. FEISHU_DOMAIN, LARK_DOMAIN)."""
+
+    helper_functions: Dict[str, Callable] = field(default_factory=dict)
+    """Platform-specific helper functions (e.g. probe_bot, qr_register)."""
+
+
+# ---------------------------------------------------------------------------
+# Tool providers
+# ---------------------------------------------------------------------------
+
+@dataclass
+class ToolProviderEntry:
+    """A registered tool provider.
+
+    Registered via ``ctx.register_tool_provider(name, entry)``.
+    Queried by ``tools/`` modules.
+    """
+    name: str
+    """Tool identifier (e.g. 'tts', 'stt', 'fal', 'daytona')."""
+
+    tool_functions: Dict[str, Callable] = field(default_factory=dict)
+    """Tool functions keyed by name (e.g. 'text_to_speech_tool', 'transcribe_audio')."""
+
+    check_fn: Optional[Callable] = None
+    """Check if the tool's dependencies are available."""
+
+    constants: Dict[str, Any] = field(default_factory=dict)
+    """Tool-specific constants (e.g. MAX_FILE_SIZE)."""
+
+    config_functions: Dict[str, Callable] = field(default_factory=dict)
+    """Config/utility functions (e.g. _get_provider, _load_stt_config)."""
+
+    environment_classes: Dict[str, Type] = field(default_factory=dict)
+    """Environment classes for terminal backends (e.g. DaytonaEnvironment)."""
+
+
+# ---------------------------------------------------------------------------
+# Model metadata providers
+# ---------------------------------------------------------------------------
+
+@dataclass
+class ModelMetadataEntry:
+    """A registered model metadata provider.
+
+    Registered via ``ctx.register_model_metadata(name, entry)``.
+    Queried by ``agent/model_metadata.py`` and CLI model commands.
+    """
+    name: str
+    """Provider identifier (e.g. 'anthropic', 'bedrock')."""
+
+    get_context_length: Optional[Callable[[str], int | None]] = None
+    """Return the context length for a model name, or None if unknown."""
+
+    list_models: Optional[Callable[[], List[str]]] = None
+    """Return a list of known model IDs for this provider."""
+
+    constants: Dict[str, Any] = field(default_factory=dict)
+    """Provider-specific constants (e.g. _COMMON_BETAS, betas lists)."""
+
+
+# ---------------------------------------------------------------------------
+# Credential pool entries
+# ---------------------------------------------------------------------------
+
+@dataclass
+class CredentialPoolEntry:
+    """A registered credential pool provider.
+
+    Registered via ``ctx.register_credential_pool(name, entry)``.
+    Queried by ``agent/credential_pool.py``.
+    """
+    name: str
+    """Provider identifier (e.g. 'anthropic')."""
+
+    read_credentials: Optional[Callable] = None
+    """Read stored credentials."""
+
+    write_credentials: Optional[Callable] = None
+    """Write/store credentials."""
+
+    refresh_credentials: Optional[Callable] = None
+    """Refresh stored credentials."""
+
+    read_oauth: Optional[Callable] = None
+    """Read OAuth credentials."""
+
+
+# ---------------------------------------------------------------------------
+# Provider resolvers
+# ---------------------------------------------------------------------------
+
+@runtime_checkable
+class ProviderResolver(Protocol):
+    """A plugin that resolves an auxiliary client for a specific provider.
+
+    Registered via ``ctx.register_provider_resolver(provider_name, resolver)``.
+    Queried by ``agent/auxiliary_client.py`` in ``resolve_provider_client()``.
+    """
+
+    def __call__(
+        self,
+        *,
+        model: str | None = None,
+        explicit_api_key: str | None = None,
+        explicit_base_url: str | None = None,
+        async_mode: bool = False,
+        is_vision: bool = False,
+        main_runtime: dict | None = None,
+        api_mode: str | None = None,
+    ) -> tuple[Any, str] | tuple[None, None]:
+        """Return ``(client, default_model)`` or ``(None, None)`` if unavailable."""
+        ...
+
+
+# ---------------------------------------------------------------------------
+# Credential pool hooks
+# ---------------------------------------------------------------------------
+
+@dataclass
+class CredentialPoolHook:
+    """Provider-specific credential pool operations.
+
+    Registered via ``ctx.register_credential_pool_hook(provider_name, hook)``.
+    Queried by ``agent/credential_pool.py``.
+    """
+
+    sync_from_credentials_file: Optional[Callable] = None
+    """Sync a pool entry from an external credentials file (e.g. ~/.claude/.credentials.json)."""
+
+    refresh_oauth: Optional[Callable] = None
+    """Refresh an OAuth token for a pool entry."""
+
+    should_include_in_pool: Optional[Callable] = None
+    """Return True if this provider's credentials should be included in the pool."""
+
+    needs_refresh: Optional[Callable] = None
+    """Return True if an OAuth entry needs a token refresh."""
+
+    source_priority: Optional[Callable] = None
+    """Return integer priority for a credential source (lower = preferred)."""
+
+    discover_credentials: Optional[Callable] = None
+    """Discover external credentials and upsert into the pool entries.
+
+    Signature: (entries: list, provider: str, is_suppressed: Callable) -> (changed: bool, active_sources: set)
+    """
+
+    env_var_order: Optional[list] = None
+    """Override env var scan order for this provider (e.g. ['ANTHROPIC_TOKEN', 'CLAUDE_CODE_OAUTH_TOKEN', 'ANTHROPIC_API_KEY'])."""
+
+    detect_auth_type: Optional[Callable] = None
+    """Given a token string, return the auth type for this provider.
+
+    Signature: (token: str) -> str  (e.g. AUTH_TYPE_OAUTH or AUTH_TYPE_API_KEY)
+    """
+
+
+# ---------------------------------------------------------------------------
+# Pricing providers
+# ---------------------------------------------------------------------------
+
+# Re-export PricingEntry from usage_pricing — that's the canonical definition
+# with Decimal fields. The registry stores these directly keyed by (provider, model).
+# Lazy import to avoid circular dependency (usage_pricing imports registries at runtime).
+def _get_pricing_entry_class():
+    from agent.usage_pricing import PricingEntry
+    return PricingEntry
+
+
+# ---------------------------------------------------------------------------
+# Provider overlays
+# ---------------------------------------------------------------------------
+
+@dataclass
+class ProviderOverlayEntry:
+    """A provider overlay registered by a plugin.
+
+    Registered via ``ctx.register_provider_overlay(provider_name, entry)``.
+    Queried by ``hermes_cli/providers.py``.
+
+    This mirrors the fields of ``HermesOverlay`` so that providers.py
+    can merge plugin-registered overlays seamlessly.
+    """
+
+    provider_name: str
+    """Primary provider name (e.g. 'anthropic', 'bedrock')."""
+
+    transport: str = "openai_chat"
+    """Transport type: openai_chat | anthropic_messages | codex_responses | bedrock_converse"""
+
+    is_aggregator: bool = False
+    """Whether this provider aggregates multiple model providers."""
+
+    auth_type: str = "api_key"
+    """Auth type: api_key | oauth_device_code | oauth_external | aws_sdk | external_process"""
+
+    extra_env_vars: Tuple[str, ...] = ()
+    """Environment variable names that indicate this provider is configured."""
+
+    base_url_override: str = ""
+    """Override if models.dev URL is wrong/missing."""
+
+    base_url_env_var: str = ""
+    """Env var for user-custom base URL."""
+
+    display_name: str = ""
+    """Human-readable name for the provider (e.g. 'Anthropic', 'AWS Bedrock')."""
+
+    aliases: List[str] = field(default_factory=list)
+    """Alternative names that resolve to this provider."""
+
+
+# ---------------------------------------------------------------------------
+# The global registries (singleton)
+# ---------------------------------------------------------------------------
+
+class PluginRegistries:
+    """Central store for all plugin-registered capabilities.
+
+    A single instance is created at import time and shared across the
+    process.  Plugins populate it during ``register()``; the core
+    queries it at runtime.
+    """
+
+    def __init__(self) -> None:
+        self.auth_providers: Dict[str, AuthProviderEntry] = {}
+        self.transport_builders: Dict[str, TransportBuilder] = {}
+        self._transports: Dict[str, type] = {}
+        self.platform_adapters: Dict[str, PlatformAdapterEntry] = {}
+        self.tool_providers: Dict[str, ToolProviderEntry] = {}
+        self.model_metadata: Dict[str, ModelMetadataEntry] = {}
+        self.credential_pools: Dict[str, CredentialPoolEntry] = {}
+        self._provider_services: Dict[str, Dict[str, Any]] = {}
+        self._provider_resolvers: Dict[str, Callable] = {}
+        self._credential_pool_hooks: Dict[str, CredentialPoolHook] = {}
+        self._pricing_providers: Dict[tuple, Any] = {}
+        self._provider_overlays: Dict[str, ProviderOverlayEntry] = {}
+
+    # -- registration methods (called from PluginContext) --------------------
+
+    def register_auth_provider(
+        self,
+        name: str,
+        provider: AuthProvider,
+        *,
+        cli_group: str = "",
+        setup_subcommands: bool = False,
+    ) -> None:
+        self.auth_providers[name] = AuthProviderEntry(
+            provider=provider,
+            cli_group=cli_group,
+            setup_subcommands=setup_subcommands,
+        )
+
+    def register_transport(self, name: str, builder: TransportBuilder) -> None:
+        self.transport_builders[name] = builder
+
+    def register_platform(self, entry: PlatformAdapterEntry) -> None:
+        self.platform_adapters[entry.name] = entry
+
+    def register_tool_provider(self, entry: ToolProviderEntry) -> None:
+        self.tool_providers[entry.name] = entry
+
+    def register_model_metadata(self, entry: ModelMetadataEntry) -> None:
+        self.model_metadata[entry.name] = entry
+
+    def register_credential_pool(self, entry: CredentialPoolEntry) -> None:
+        self.credential_pools[entry.name] = entry
+
+    def register_provider_resolver(self, name: str, resolver: Callable) -> None:
+        """Register a provider resolver callable.
+
+        The resolver is called by ``resolve_provider_client()`` to create an
+        auxiliary client for a specific provider.  Signature::
+
+            def resolver(
+                *,
+                model: str | None,
+                explicit_api_key: str | None,
+                explicit_base_url: str | None,
+                async_mode: bool,
+                is_vision: bool,
+                main_runtime: dict | None,
+                api_mode: str | None,
+            ) -> tuple[Any, str] | tuple[None, None]:
+                ...
+
+        Returns ``(client, default_model)`` or ``(None, None)``.
+        """
+        self._provider_resolvers[name] = resolver
+
+    def register_credential_pool_hook(self, name: str, hook: CredentialPoolHook) -> None:
+        """Register a credential pool hook for provider-specific pool operations."""
+        self._credential_pool_hooks[name] = hook
+
+    def register_pricing_provider(self, name: str, entries: List[tuple]) -> None:
+        """Register pricing entries for a provider.
+
+        Each entry is a (provider, model, PricingEntry) tuple so the
+        lookup key matches the (provider, model) pattern used by
+        _OFFICIAL_DOCS_PRICING.
+        """
+        for prov, model, entry in entries:
+            self._pricing_providers[(prov, model)] = entry
+
+    def register_provider_overlay(self, entry: ProviderOverlayEntry) -> None:
+        """Register a provider overlay entry from a plugin."""
+        self._provider_overlays[entry.provider_name] = entry
+
+    # -- query helpers -------------------------------------------------------
+
+    def get_auth_provider(self, name: str) -> AuthProviderEntry | None:
+        return self.auth_providers.get(name)
+
+    def get_transport(self, name: str) -> TransportBuilder | None:
+        return self.transport_builders.get(name)
+
+    def get_platform(self, name: str) -> PlatformAdapterEntry | None:
+        return self.platform_adapters.get(name)
+
+    def get_tool_provider(self, name: str) -> ToolProviderEntry | None:
+        return self.tool_providers.get(name)
+
+    def get_model_metadata(self, name: str) -> ModelMetadataEntry | None:
+        return self.model_metadata.get(name)
+
+    def get_credential_pool(self, name: str) -> CredentialPoolEntry | None:
+        return self.credential_pools.get(name)
+
+    def get_provider_resolver(self, name: str) -> Callable | None:
+        """Return the registered resolver for a provider, or None."""
+        return self._provider_resolvers.get(name)
+
+    def get_credential_pool_hook(self, name: str) -> CredentialPoolHook | None:
+        """Return the registered credential pool hook for a provider, or None."""
+        return self._credential_pool_hooks.get(name)
+
+    def get_pricing_entry(self, provider: str, model: str) -> Any:
+        """Return a registered pricing entry for (provider, model), or None."""
+        return self._pricing_providers.get((provider, model))
+
+    def all_pricing_entries(self) -> Dict[tuple, Any]:
+        """Return all registered pricing entries (keyed by (provider, model))."""
+        return dict(self._pricing_providers)
+
+    def get_provider_overlay(self, name: str) -> ProviderOverlayEntry | None:
+        """Return a registered provider overlay, or None."""
+        return self._provider_overlays.get(name)
+
+    def all_provider_overlays(self) -> Dict[str, ProviderOverlayEntry]:
+        """Return all registered provider overlays."""
+        return dict(self._provider_overlays)
+
+    def all_auth_providers(self) -> List[AuthProviderEntry]:
+        return list(self.auth_providers.values())
+
+    def all_platforms(self) -> List[PlatformAdapterEntry]:
+        return list(self.platform_adapters.values())
+
+    def all_tool_providers(self) -> List[ToolProviderEntry]:
+        return list(self.tool_providers.values())
+
+    # -- provider services (model-provider namespace) -----------------------
+
+    def register_provider_services(self, name: str, services: Dict[str, Any]) -> None:
+        """Register a namespace dict of provider-specific services.
+
+        This is the escape hatch for model-provider plugins that expose many
+        symbols (anthropic has 50+).  Each plugin registers its public surface
+        as a flat dict of ``{symbol_name: callable_or_value}``.  Core code
+        looks up specific symbols instead of importing from the plugin
+        package directly.
+
+        Each callable value is stored as a *lazy module-attribute reference*
+        so that ``unittest.mock.patch("pkg.mod.fn")`` works correctly in
+        tests — the registry re-reads ``mod.fn`` on every lookup instead of
+        capturing the function object at register time.
+
+        Example::
+
+            registries.register_provider_services("anthropic", {
+                "build_anthropic_client": build_anthropic_client,
+                "resolve_anthropic_token": resolve_anthropic_token,
+                "_is_oauth_token": _is_oauth_token,
+                ...
+            })
+        """
+        import sys
+
+        def _make_lazy(fn: Any) -> Any:
+            """Return a lazy wrapper that re-reads fn from its module each call.
+
+            This makes mock.patch() on the module attribute work transparently —
+            the registry never caches the function object, just the reference path.
+            """
+            if not callable(fn):
+                return fn
+            module = getattr(fn, "__module__", None)
+            qualname = getattr(fn, "__qualname__", None)
+            if not module or not qualname or "." in qualname:
+                # non-simple attribute (lambda, nested fn, class method) — store directly
+                return fn
+
+            class _LazyRef:
+                __slots__ = ("_mod", "_attr", "_fallback")
+
+                def __init__(self, mod: str, attr: str, fallback: Any) -> None:
+                    self._mod = mod
+                    self._attr = attr
+                    self._fallback = fallback
+
+                def _resolve(self) -> Any:
+                    mod = sys.modules.get(self._mod)
+                    return getattr(mod, self._attr, self._fallback) if mod else self._fallback
+
+                def __call__(self, *args: Any, **kwargs: Any) -> Any:
+                    return self._resolve()(*args, **kwargs)
+
+                def __getattr__(self, name: str) -> Any:
+                    if name.startswith("_"):
+                        raise AttributeError(name)
+                    return getattr(self._resolve(), name)
+
+                def __repr__(self) -> str:  # pragma: no cover
+                    return f"<LazyRef {self._mod}.{self._attr}>"
+
+                # Allow isinstance checks and hasattr to pass through
+                def __bool__(self) -> bool:
+                    return True
+
+            return _LazyRef(module, qualname, fn)
+
+        self._provider_services[name] = {k: _make_lazy(v) for k, v in services.items()}
+
+    def get_provider_service(self, provider: str, name: str) -> Any:
+        """Look up a single symbol from a provider's service namespace.
+
+        Returns ``None`` if the provider is not registered or the symbol
+        doesn't exist.
+        """
+        ns = self._provider_services.get(provider)
+        if ns is None:
+            return None
+        return ns.get(name)
+
+    def get_provider_namespace(self, provider: str) -> Dict[str, Any]:
+        """Return the full service namespace dict for a provider (empty dict if unregistered)."""
+        return self._provider_services.get(provider, {})
+
+
+# Module-level singleton — the one and only instance.
+registries = PluginRegistries()

agent/prompt_builder.py

@@ -7,6 +7,7 @@ assemble pieces, then combines them with memory and ephemeral prompts.
 import json
 import logging
 import os
+import re
 import threading
 from collections import OrderedDict
 from pathlib import Path
@@ -235,11 +236,6 @@ KANBAN_GUIDANCE = (
     "- Do not shell out to `hermes kanban <verb>` for board operations. Use "
     "the `kanban_*` tools — they work across all terminal backends.\n"
     "- Do not complete a task you didn't actually finish. Block it.\n"
-    "- Do not call `clarify` to ask questions. You are running headless — "
-    "there is no live user to answer. The call will time out and the task "
-    "will sit silently in `running` with no signal to the operator. Instead: "
-    "`kanban_comment` the context, then `kanban_block(reason=...)` so the "
-    "task surfaces on the board as needing input.\n"
     "- Do not assign follow-up work to yourself. Assign it to the right "
     "specialist profile.\n"
     "- Do not call `delegate_task` as a board substitute. `delegate_task` is "
@@ -266,37 +262,6 @@ TOOL_USE_ENFORCEMENT_GUIDANCE = (
 # Add new patterns here when a model family needs explicit steering.
 TOOL_USE_ENFORCEMENT_MODELS = ("gpt", "codex", "gemini", "gemma", "grok", "glm", "qwen", "deepseek")
 
-# Universal "finish the job" guidance — applied to ALL models, not gated
-# by model family.  Addresses two cross-model failure modes:
-#   1. Stopping after a stub: writing a tiny file or running one command
-#      and then ending the turn with a description of the plan instead
-#      of the finished artifact.  (Observed on Opus during a real
-#      Sarasota real-estate build task: 3 API calls, 85-byte file,
-#      one terminal command, finish_reason=stop.)
-#   2. Fabricating output when a real path is blocked.  When `pip` or a
-#      tool fails, some models will synthesize plausible-looking results
-#      (fake addresses, fake JSON, fake numbers) instead of reporting
-#      the blocker.  (Observed on DeepSeek v4-flash on the same task:
-#      pushed through PEP-668 wall, then returned fabricated listings.)
-#
-# Short on purpose.  This block is shipped to every user, every session,
-# in the cached system prompt — token cost is paid once at install and
-# then amortised across all sessions via prefix caching.  Keep it tight.
-TASK_COMPLETION_GUIDANCE = (
-    "# Finishing the job\n"
-    "When the user asks you to build, run, or verify something, the deliverable is "
-    "a working artifact backed by real tool output — not a description of one. "
-    "Do not stop after writing a stub, a plan, or a single command. Keep working "
-    "until you have actually exercised the code or produced the requested result, "
-    "then report what real execution returned.\n"
-    "If a tool, install, or network call fails and blocks the real path, say so "
-    "directly and try an alternative (different package manager, different "
-    "approach, ask the user). NEVER substitute plausible-looking fabricated "
-    "output (made-up data, invented file contents, synthesised API responses) "
-    "for results you couldn't actually produce. Reporting a blocker honestly "
-    "is always better than inventing a result."
-)
-
 # OpenAI GPT/Codex-specific execution guidance.  Addresses known failure modes
 # where GPT models abandon work on partial results, skip prerequisite lookups,
 # hallucinate instead of using tools, and declare "done" without verification.
@@ -848,27 +813,6 @@ def build_environment_hints() -> str:
 
     if is_wsl():
         hints.append(WSL_ENVIRONMENT_HINT)
-
-    # Embedder-supplied environment description. Lets a host that wraps Hermes
-    # (e.g. a sandbox runner / managed platform) explain the environment the
-    # agent is running in — proxy, credential handling, mount layout — without
-    # forking the identity slot (SOUL.md). Read once at prompt-build time, so
-    # it's part of the stable, cache-safe system prompt. The env var is the
-    # build-time/embedder mechanism (set in a container ENV); config.yaml
-    # ``agent.environment_hint`` is the user-facing surface. Env var wins.
-    extra = (os.getenv("HERMES_ENVIRONMENT_HINT") or "").strip()
-    if not extra:
-        try:
-            from hermes_cli.config import load_config
-
-            extra = str(
-                (load_config().get("agent", {}) or {}).get("environment_hint", "")
-            ).strip()
-        except Exception as e:
-            logger.debug("Could not read agent.environment_hint from config: %s", e)
-    if extra:
-        hints.append(extra)
-
     return "\n\n".join(hints)
 
 

agent/secret_sources/bitwarden.py

@@ -37,6 +37,7 @@ import platform
 import shutil
 import stat
 import subprocess
+import sys
 import tempfile
 import time
 import urllib.error

agent/system_prompt.py

@@ -37,7 +37,6 @@ from agent.prompt_builder import (
     PLATFORM_HINTS,
     SESSION_SEARCH_GUIDANCE,
     SKILLS_GUIDANCE,
-    TASK_COMPLETION_GUIDANCE,
     TOOL_USE_ENFORCEMENT_GUIDANCE,
     TOOL_USE_ENFORCEMENT_MODELS,
 )
@@ -101,15 +100,6 @@ def build_system_prompt_parts(agent: Any, system_message: Optional[str] = None)
     # Pointer to the hermes-agent skill + docs for user questions about Hermes itself.
     stable_parts.append(HERMES_AGENT_HELP_GUIDANCE)
 
-    # Universal task-completion / no-fabrication guidance.  Applied to ALL
-    # models regardless of tool_use_enforcement gating — the failure modes
-    # this targets (stopping after a stub; fabricating output when a real
-    # path is blocked) are not model-family specific.  Gated only by
-    # config.yaml ``agent.task_completion_guidance`` (default True) so
-    # users who want a leaner prompt can turn it off.
-    if getattr(agent, "_task_completion_guidance", True) and agent.valid_tool_names:
-        stable_parts.append(TASK_COMPLETION_GUIDANCE)
-
     # Tool-aware behavioral guidance: only inject when the tools are loaded
     tool_guidance = []
     if "memory" in agent.valid_tool_names:
@@ -215,23 +205,6 @@ def build_system_prompt_parts(agent: Any, system_message: Optional[str] = None)
     if _env_hints:
         stable_parts.append(_env_hints)
 
-    # Local Python toolchain probe — names python/pip/uv/PEP-668 state when
-    # something is non-default so the model can pick the right install
-    # strategy without discovering by failure.  Emits a single line; emits
-    # NOTHING when the environment is clean (no token cost).  Skipped
-    # entirely for remote terminal backends (the host's Python state is
-    # irrelevant when tools run inside docker/modal/ssh).  Gated by
-    # config.yaml ``agent.environment_probe`` (default True).
-    if getattr(agent, "_environment_probe", True):
-        try:
-            from tools.env_probe import get_environment_probe_line
-            _probe_line = get_environment_probe_line()
-            if _probe_line:
-                stable_parts.append(_probe_line)
-        except Exception:
-            # Probe failure must never block prompt build.
-            pass
-
     # Active-profile hint — names the Hermes profile the agent is running
     # under so it doesn't conflate ~/.hermes/skills/ (default profile) with
     # ~/.hermes/profiles/<active>/skills/ (this profile's). Deterministic

agent/tool_executor.py

@@ -13,13 +13,14 @@ extracted functions reach back through the ``run_agent`` module via
 from __future__ import annotations
 
 import concurrent.futures
+import contextvars
 import json
 import logging
 import os
 import random
 import threading
 import time
-from typing import Optional
+from typing import Any, Optional
 
 from agent.display import (
     KawaiiSpinner,
@@ -37,9 +38,12 @@ from agent.tool_dispatch_helpers import (
     make_tool_result_message,
 )
 from tools.terminal_tool import (
+    _get_approval_callback,
+    _get_sudo_password_callback,
+    set_approval_callback as _set_approval_callback,
+    set_sudo_password_callback as _set_sudo_password_callback,
     get_active_env,
 )
-from tools.thread_context import propagate_context_to_thread
 from tools.tool_result_storage import (
     maybe_persist_tool_result,
     enforce_turn_budget,
@@ -58,55 +62,6 @@ def _ra():
     return run_agent
 
 
-def _tool_search_scoped_names(agent) -> frozenset:
-    """Return the deferrable tool names the session may invoke via tool_call.
-
-    The Tool Search unwrap dispatches the underlying tool directly, bypassing
-    the bridge branch (and its scope check) in
-    ``model_tools.handle_function_call``. To keep a restricted-toolset session
-    (subagent, kanban worker, curated gateway session) from reaching tools it
-    was never granted, the unwrap validates the underlying name against this
-    set: the deferrable subset of the session's own enabled/disabled toolset
-    scope.
-
-    Result is cached on the agent and refreshed when the tool registry's
-    generation changes (e.g. an MCP server reconnects), so the common case is
-    a dict lookup, not a full tool-defs rebuild on every tool call.
-    """
-    try:
-        import model_tools
-        from tools import tool_search as _ts
-        from tools.registry import registry as _registry
-    except Exception:
-        return frozenset()
-
-    enabled = getattr(agent, "enabled_toolsets", None)
-    disabled = getattr(agent, "disabled_toolsets", None)
-    cache_key = (
-        getattr(_registry, "_generation", 0),
-        frozenset(enabled) if enabled is not None else None,
-        frozenset(disabled) if disabled is not None else None,
-    )
-    cached = getattr(agent, "_tool_search_scope_cache", None)
-    if cached is not None and cached[0] == cache_key:
-        return cached[1]
-    try:
-        scoped_defs = model_tools.get_tool_definitions(
-            enabled_toolsets=enabled,
-            disabled_toolsets=disabled,
-            quiet_mode=True,
-            skip_tool_search_assembly=True,
-        ) or []
-        names = _ts.scoped_deferrable_names(scoped_defs)
-    except Exception:
-        names = frozenset()
-    try:
-        agent._tool_search_scope_cache = (cache_key, names)
-    except Exception:
-        pass
-    return names
-
-
 def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effective_task_id: str, api_call_count: int = 0) -> None:
     """Execute multiple tool calls concurrently using a thread pool.
 
@@ -145,41 +100,6 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
         if not isinstance(function_args, dict):
             function_args = {}
 
-        # ── Tool Search unwrap ────────────────────────────────────────
-        # When the model invokes the tool_call bridge, peel it open so
-        # every downstream check (checkpointing, guardrails, plugin
-        # pre-tool-call hooks, the display/activity feed, the post-call
-        # callback) sees the underlying tool — not the bridge. This is
-        # the OpenClaw lesson: hooks must observe the real tool name.
-        #
-        # The original tool_call entry on ``tool_call.function`` is left
-        # untouched so the conversation transcript and the matching
-        # tool_call_id are preserved exactly as the model emitted them.
-        #
-        # Scope gate: the unwrap dispatches the underlying tool directly
-        # (bypassing the bridge branch in handle_function_call and its
-        # scope check), so we enforce session toolset scope HERE. A tool
-        # the session was not granted is rejected before any checkpoint,
-        # hook, or dispatch fires.
-        _ts_scope_block = None
-        try:
-            from tools import tool_search as _ts
-            if function_name == _ts.TOOL_CALL_NAME:
-                _underlying, _underlying_args, _err = _ts.resolve_underlying_call(function_args)
-                if not _err and _underlying:
-                    if _underlying in _tool_search_scoped_names(agent):
-                        function_name = _underlying
-                        function_args = _underlying_args
-                    else:
-                        _ts_scope_block = json.dumps({
-                            "error": (
-                                f"'{_underlying}' is not available in this session. "
-                                "Use tool_search to find tools you can call."
-                            ),
-                        }, ensure_ascii=False)
-        except Exception:
-            pass
-
         # Checkpoint for file-mutating tools
         if function_name in {"write_file", "patch"} and agent._checkpoint_mgr.enabled:
             try:
@@ -204,25 +124,21 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
 
         block_result = None
         blocked_by_guardrail = False
-        if _ts_scope_block is not None:
-            # Out-of-scope tool_call: reject before hooks/guardrails/dispatch.
-            block_result = _ts_scope_block
-        else:
-            try:
-                from hermes_cli.plugins import get_pre_tool_call_block_message
-                block_message = get_pre_tool_call_block_message(
-                    function_name, function_args, task_id=effective_task_id or "",
-                )
-            except Exception:
-                block_message = None
+        try:
+            from hermes_cli.plugins import get_pre_tool_call_block_message
+            block_message = get_pre_tool_call_block_message(
+                function_name, function_args, task_id=effective_task_id or "",
+            )
+        except Exception:
+            block_message = None
 
-            if block_message is not None:
-                block_result = json.dumps({"error": block_message}, ensure_ascii=False)
-            else:
-                guardrail_decision = agent._tool_guardrails.before_call(function_name, function_args)
-                if not guardrail_decision.allows_execution:
-                    block_result = agent._guardrail_block_result(guardrail_decision)
-                    blocked_by_guardrail = True
+        if block_message is not None:
+            block_result = json.dumps({"error": block_message}, ensure_ascii=False)
+        else:
+            guardrail_decision = agent._tool_guardrails.before_call(function_name, function_args)
+            if not guardrail_decision.allows_execution:
+                block_result = agent._guardrail_block_result(guardrail_decision)
+                blocked_by_guardrail = True
 
         parsed_calls.append((tool_call, function_name, function_args, block_result, blocked_by_guardrail))
 
@@ -270,6 +186,14 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
     agent._current_tool = tool_names_str
     agent._touch_activity(f"executing {num_tools} tools concurrently: {tool_names_str}")
 
+    # Capture CLI callbacks from the agent thread so worker threads can
+    # register them locally.  Without this, _get_approval_callback() in
+    # terminal_tool returns None in ThreadPoolExecutor workers, causing
+    # the dangerous-command prompt to fall back to input() — which
+    # deadlocks against prompt_toolkit's raw terminal mode (#13617).
+    _parent_approval_cb = _get_approval_callback()
+    _parent_sudo_cb = _get_sudo_password_callback()
+
     def _run_tool(index, tool_call, function_name, function_args):
         """Worker function executed in a thread."""
         # Register this worker tid so the agent can fan out an interrupt
@@ -296,9 +220,18 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
             set_activity_callback(agent._touch_activity)
         except Exception:
             pass
-        # Approval/sudo callbacks (thread-local) and the agent turn's
-        # ContextVars are propagated by propagate_context_to_thread() at the
-        # submit site below (GHSA-qg5c-hvr5-hjgr, #13617).
+        # Propagate approval/sudo callbacks to this worker thread.
+        # Mirrors cli.py run_agent() pattern (GHSA-qg5c-hvr5-hjgr).
+        if _parent_approval_cb is not None:
+            try:
+                _set_approval_callback(_parent_approval_cb)
+            except Exception:
+                pass
+        if _parent_sudo_cb is not None:
+            try:
+                _set_sudo_password_callback(_parent_sudo_cb)
+            except Exception:
+                pass
         start = time.time()
         try:
             result = agent._invoke_tool(
@@ -328,6 +261,13 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
             _ra()._set_interrupt(False, _worker_tid)
         except Exception:
             pass
+        # Clear thread-local callbacks so a recycled worker thread
+        # doesn't hold stale references to a disposed CLI instance.
+        try:
+            _set_approval_callback(None)
+            _set_sudo_password_callback(None)
+        except Exception:
+            pass
 
     # Start spinner for CLI mode (skip when TUI handles tool progress)
     spinner = None
@@ -347,12 +287,9 @@ def execute_tool_calls_concurrent(agent, assistant_message, messages: list, effe
             max_workers = min(len(runnable_calls), _MAX_TOOL_WORKERS)
             with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
                 for i, tc, name, args in runnable_calls:
-                    # Propagate the agent turn's ContextVars (e.g.
-                    # _approval_session_key) AND thread-local approval/sudo
-                    # callbacks into the worker thread; clears callbacks on exit.
-                    f = executor.submit(
-                        propagate_context_to_thread(_run_tool), i, tc, name, args
-                    )
+                    # Propagate ContextVars (e.g. _approval_session_key); mirrors asyncio.to_thread.
+                    ctx = contextvars.copy_context()
+                    f = executor.submit(ctx.run, _run_tool, i, tc, name, args)
                     futures.append(f)
 
                 # Wait for all to complete with periodic heartbeats so the
@@ -560,38 +497,15 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
         if not isinstance(function_args, dict):
             function_args = {}
 
-        # Tool Search unwrap — see execute_tool_calls_concurrent for full
-        # rationale, including the scope gate (the unwrap dispatches the
-        # underlying tool directly, so session toolset scope is enforced here).
-        _ts_scope_block: Optional[str] = None
-        try:
-            from tools import tool_search as _ts
-            if function_name == _ts.TOOL_CALL_NAME:
-                _underlying, _underlying_args, _err = _ts.resolve_underlying_call(function_args)
-                if not _err and _underlying:
-                    if _underlying in _tool_search_scoped_names(agent):
-                        function_name = _underlying
-                        function_args = _underlying_args
-                    else:
-                        _ts_scope_block = (
-                            f"'{_underlying}' is not available in this session. "
-                            "Use tool_search to find tools you can call."
-                        )
-        except Exception:
-            pass
-
         # Check plugin hooks for a block directive before executing.
         _block_msg: Optional[str] = None
-        if _ts_scope_block is not None:
-            _block_msg = _ts_scope_block
-        else:
-            try:
-                from hermes_cli.plugins import get_pre_tool_call_block_message
-                _block_msg = get_pre_tool_call_block_message(
-                    function_name, function_args, task_id=effective_task_id or "",
-                )
-            except Exception:
-                pass
+        try:
+            from hermes_cli.plugins import get_pre_tool_call_block_message
+            _block_msg = get_pre_tool_call_block_message(
+                function_name, function_args, task_id=effective_task_id or "",
+            )
+        except Exception:
+            pass
 
         _guardrail_block_decision: ToolGuardrailDecision | None = None
         if _block_msg is None:
@@ -838,8 +752,6 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
                     session_id=agent.session_id or "",
                     enabled_tools=list(agent.valid_tool_names) if agent.valid_tool_names else None,
                     skip_pre_tool_call_hook=True,
-                    enabled_toolsets=getattr(agent, "enabled_toolsets", None),
-                    disabled_toolsets=getattr(agent, "disabled_toolsets", None),
                 )
                 _spinner_result = function_result
             except Exception as tool_error:
@@ -860,8 +772,6 @@ def execute_tool_calls_sequential(agent, assistant_message, messages: list, effe
                     session_id=agent.session_id or "",
                     enabled_tools=list(agent.valid_tool_names) if agent.valid_tool_names else None,
                     skip_pre_tool_call_hook=True,
-                    enabled_toolsets=getattr(agent, "enabled_toolsets", None),
-                    disabled_toolsets=getattr(agent, "disabled_toolsets", None),
                 )
             except Exception as tool_error:
                 function_result = f"Error executing tool '{function_name}': {tool_error}"

agent/transports/__init__.py

@@ -47,9 +47,16 @@ def get_transport(api_mode: str):
 
 
 def _discover_transports() -> None:
-    """Import all transport modules to trigger auto-registration."""
+    """Import all transport modules to trigger auto-registration.
+
+    Also checks the plugin registry for transports registered by plugins
+    (e.g. anthropic_messages from the anthropic plugin, bedrock_converse
+    from the bedrock plugin).  Plugin-registered transports take priority
+    over core fallbacks when both exist.
+    """
     global _discovered
     _discovered = True
+    # Core transport modules (registered automatically — no plugin needed)
     try:
         import agent.transports.anthropic  # noqa: F401
     except ImportError:
@@ -62,7 +69,10 @@ def _discover_transports() -> None:
         import agent.transports.chat_completions  # noqa: F401
     except ImportError:
         pass
+    # Plugin-registered transports (override core fallbacks)
     try:
-        import agent.transports.bedrock  # noqa: F401
+        from agent.plugin_registries import registries
+        for api_mode, transport_cls in registries._transports.items():
+            _REGISTRY.setdefault(api_mode, transport_cls)
     except ImportError:
         pass

agent/transports/anthropic.py

@@ -1,41 +1,53 @@
-"""Anthropic Messages API transport.
+"""Anthropic Messages API transport — core module.
 
-Delegates to the existing adapter functions in agent/anthropic_adapter.py.
-This transport owns format conversion and normalization — NOT client lifecycle.
+Owns format conversion and response normalization for the ``anthropic_messages``
+wire format.  No SDK dependency; all wire-format logic lives in
+:mod:`agent.anthropic_format`.
 """
 
+import json
 from typing import Any, Dict, List, Optional
 
+from agent.anthropic_format import (
+    build_anthropic_kwargs,
+    convert_messages_to_anthropic,
+    convert_tools_to_anthropic,
+    _to_plain_data,
+)
 from agent.transports.base import ProviderTransport
-from agent.transports.types import NormalizedResponse
+from agent.transports.types import NormalizedResponse, ToolCall
 
 
 class AnthropicTransport(ProviderTransport):
     """Transport for api_mode='anthropic_messages'.
 
-    Wraps the existing functions in anthropic_adapter.py behind the
-    ProviderTransport ABC.  Each method delegates — no logic is duplicated.
+    Uses core functions directly from :mod:`agent.anthropic_format` — no
+    plugin registry lookups needed.  This means core tests, bedrock tests,
+    and any other consumer of the anthropic wire format work without the
+    anthropic plugin being registered.
     """
 
+    _STOP_REASON_MAP = {
+        "end_turn": "stop",
+        "tool_use": "tool_calls",
+        "max_tokens": "length",
+        "stop_sequence": "stop",
+        "refusal": "content_filter",
+        "model_context_window_exceeded": "length",
+    }
+
     @property
     def api_mode(self) -> str:
         return "anthropic_messages"
 
     def convert_messages(self, messages: List[Dict[str, Any]], **kwargs) -> Any:
-        """Convert OpenAI messages to Anthropic (system, messages) tuple.
-
-        kwargs:
-            base_url: Optional[str] — affects thinking signature handling.
-        """
-        from agent.anthropic_adapter import convert_messages_to_anthropic
-
+        """Convert OpenAI messages to Anthropic (system, messages) tuple."""
         base_url = kwargs.get("base_url")
-        return convert_messages_to_anthropic(messages, base_url=base_url)
+        return convert_messages_to_anthropic(messages, base_url=base_url,
+                                             model=kwargs.get("model"))
 
     def convert_tools(self, tools: List[Dict[str, Any]]) -> Any:
         """Convert OpenAI tool schemas to Anthropic input_schema format."""
-        from agent.anthropic_adapter import convert_tools_to_anthropic
-
         return convert_tools_to_anthropic(tools)
 
     def build_kwargs(
@@ -45,23 +57,7 @@ class AnthropicTransport(ProviderTransport):
         tools: Optional[List[Dict[str, Any]]] = None,
         **params,
     ) -> Dict[str, Any]:
-        """Build Anthropic messages.create() kwargs.
-
-        Calls convert_messages and convert_tools internally.
-
-        params (all optional):
-            max_tokens: int
-            reasoning_config: dict | None
-            tool_choice: str | None
-            is_oauth: bool
-            preserve_dots: bool
-            context_length: int | None
-            base_url: str | None
-            fast_mode: bool
-            drop_context_1m_beta: bool
-        """
-        from agent.anthropic_adapter import build_anthropic_kwargs
-
+        """Build Anthropic messages.create() kwargs."""
         return build_anthropic_kwargs(
             model=model,
             messages=messages,
@@ -78,15 +74,7 @@ class AnthropicTransport(ProviderTransport):
         )
 
     def normalize_response(self, response: Any, **kwargs) -> NormalizedResponse:
-        """Normalize Anthropic response to NormalizedResponse.
-
-        Parses content blocks (text, thinking, tool_use), maps stop_reason
-        to OpenAI finish_reason, and collects reasoning_details in provider_data.
-        """
-        import json
-        from agent.anthropic_adapter import _to_plain_data
-        from agent.transports.types import ToolCall
-
+        """Normalize Anthropic response to NormalizedResponse."""
         strip_tool_prefix = kwargs.get("strip_tool_prefix", False)
         _MCP_PREFIX = "mcp_"
 
@@ -107,12 +95,6 @@ class AnthropicTransport(ProviderTransport):
                 name = block.name
                 if strip_tool_prefix and name.startswith(_MCP_PREFIX):
                     stripped = name[len(_MCP_PREFIX):]
-                    # Only strip the mcp_ prefix for OAuth-injected tools
-                    # (where Hermes adds the prefix when sending to Anthropic
-                    # and must remove it on the way back).  Native MCP server
-                    # tools (from mcp_servers: in config.yaml) are registered
-                    # in the tool registry under their FULL mcp_<server>_<tool>
-                    # name and must NOT be stripped.  GH-25255.
                     from tools.registry import registry as _tool_registry
                     if (_tool_registry.get_entry(stripped)
                             and not _tool_registry.get_entry(name)):
@@ -141,13 +123,7 @@ class AnthropicTransport(ProviderTransport):
         )
 
     def validate_response(self, response: Any) -> bool:
-        """Check Anthropic response structure is valid.
-
-        An empty content list is legitimate when ``stop_reason == "end_turn"``
-        — the model's canonical way of signalling "nothing more to add" after
-        a tool turn that already delivered the user-facing text. Treating it
-        as invalid falsely retries a completed response.
-        """
+        """Check Anthropic response structure is valid."""
         if response is None:
             return False
         content_blocks = getattr(response, "content", None)
@@ -168,16 +144,6 @@ class AnthropicTransport(ProviderTransport):
             return {"cached_tokens": cached, "creation_tokens": written}
         return None
 
-    # Promote the adapter's canonical mapping to module level so it's shared
-    _STOP_REASON_MAP = {
-        "end_turn": "stop",
-        "tool_use": "tool_calls",
-        "max_tokens": "length",
-        "stop_sequence": "stop",
-        "refusal": "content_filter",
-        "model_context_window_exceeded": "length",
-    }
-
     def map_finish_reason(self, raw_reason: str) -> str:
         """Map Anthropic stop_reason to OpenAI finish_reason."""
         return self._STOP_REASON_MAP.get(raw_reason, "stop")

agent/transports/chat_completions.py

@@ -10,7 +10,7 @@ reasoning configuration, temperature handling, and extra_body assembly.
 """
 
 import copy
-from typing import Any, Dict
+from typing import Any, Dict, List, Optional
 
 from agent.lmstudio_reasoning import resolve_lmstudio_effort
 from agent.moonshot_schema import is_moonshot_model, sanitize_moonshot_tools
@@ -476,17 +476,13 @@ class ChatCompletionsTransport(ProviderTransport):
         ephemeral = params.get("ephemeral_max_output_tokens")
         user_max = params.get("max_tokens")
         anthropic_max = params.get("anthropic_max_output")
-        # Per-model default cap — profiles override get_max_tokens() when
-        # they front several backends with different completion-token limits
-        # (e.g. opencode-go: mimo-v2.5-pro = 131072).
-        profile_max = profile.get_max_tokens(model)
 
         if ephemeral is not None and max_tokens_fn:
             api_kwargs.update(max_tokens_fn(ephemeral))
         elif user_max is not None and max_tokens_fn:
             api_kwargs.update(max_tokens_fn(user_max))
-        elif profile_max and max_tokens_fn:
-            api_kwargs.update(max_tokens_fn(profile_max))
+        elif profile.default_max_tokens and max_tokens_fn:
+            api_kwargs.update(max_tokens_fn(profile.default_max_tokens))
         elif anthropic_max is not None:
             api_kwargs["max_tokens"] = anthropic_max
 

agent/transports/codex_app_server.py

@@ -23,7 +23,7 @@ import subprocess
 import threading
 import time
 from dataclasses import dataclass, field
-from typing import Any, Optional
+from typing import Any, Callable, Optional
 
 # Default minimum codex version we test against. The PR sets this from the
 # `codex --version` parsed at install time; bumping is a one-line change here.

agent/transports/codex_app_server_session.py

@@ -31,7 +31,6 @@ import time
 from dataclasses import dataclass, field
 from typing import Any, Callable, Optional
 
-from agent.codex_responses_adapter import _format_responses_error
 from agent.redact import redact_sensitive_text
 from agent.transports.codex_app_server import (
     CodexAppServerClient,
@@ -582,7 +581,7 @@ class CodexAppServerSession:
                         (note.get("params") or {}).get("turn") or {}
                     ).get("error")
                     if err_obj:
-                        err_msg = _format_responses_error(err_obj, str(turn_status))
+                        err_msg = err_obj.get("message") or str(err_obj)
                         # If the turn failed for an auth/refresh reason,
                         # rewrite the error into a re-auth hint AND mark
                         # the session for retirement.

agent/usage_pricing.py

@@ -115,6 +115,8 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
     # Opus 4.5/4.6/4.7 share $5/$25 pricing (new tokenizer, up to 35% more
     # tokens for the same text).
     # Source: https://platform.claude.com/docs/en/about-claude/pricing
+    # NOTE: The anthropic plugin also registers these — plugin takes priority
+    # at runtime, but these static entries ensure costs work without the plugin.
     (
         "anthropic",
         "claude-opus-4-7",
@@ -139,7 +141,6 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
         source_url="https://platform.claude.com/docs/en/about-claude/pricing",
         pricing_version="anthropic-pricing-2026-05",
     ),
-    # ── Anthropic Claude 4.6 ─────────────────────────────────────────────
     (
         "anthropic",
         "claude-opus-4-6",
@@ -188,7 +189,6 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
         source_url="https://platform.claude.com/docs/en/about-claude/pricing",
         pricing_version="anthropic-pricing-2026-05",
     ),
-    # ── Anthropic Claude 4.5 ─────────────────────────────────────────────
     (
         "anthropic",
         "claude-opus-4-5",
@@ -225,7 +225,6 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
         source_url="https://platform.claude.com/docs/en/about-claude/pricing",
         pricing_version="anthropic-pricing-2026-05",
     ),
-    # ── Anthropic Claude 4 / 4.1 ─────────────────────────────────────────
     (
         "anthropic",
         "claude-opus-4-20250514",
@@ -250,7 +249,56 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
         source_url="https://platform.claude.com/docs/en/about-claude/pricing",
         pricing_version="anthropic-pricing-2026-05",
     ),
-    # OpenAI
+    # ── Anthropic older models (pre-4.5 generation) ────────────────────────
+    (
+        "anthropic",
+        "claude-3-5-sonnet-20241022",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("3.00"),
+        output_cost_per_million=Decimal("15.00"),
+        cache_read_cost_per_million=Decimal("0.30"),
+        cache_write_cost_per_million=Decimal("3.75"),
+        source="official_docs_snapshot",
+        source_url="https://platform.claude.com/docs/en/about-claude/pricing",
+        pricing_version="anthropic-pricing-2026-05",
+    ),
+    (
+        "anthropic",
+        "claude-3-5-haiku-20241022",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.80"),
+        output_cost_per_million=Decimal("4.00"),
+        cache_read_cost_per_million=Decimal("0.08"),
+        cache_write_cost_per_million=Decimal("1.00"),
+        source="official_docs_snapshot",
+        source_url="https://platform.claude.com/docs/en/about-claude/pricing",
+        pricing_version="anthropic-pricing-2026-05",
+    ),
+    (
+        "anthropic",
+        "claude-3-opus-20240229",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("15.00"),
+        output_cost_per_million=Decimal("75.00"),
+        cache_read_cost_per_million=Decimal("1.50"),
+        cache_write_cost_per_million=Decimal("18.75"),
+        source="official_docs_snapshot",
+        source_url="https://platform.claude.com/docs/en/about-claude/pricing",
+        pricing_version="anthropic-pricing-2026-05",
+    ),
+    (
+        "anthropic",
+        "claude-3-haiku-20240307",
+    ): PricingEntry(
+        input_cost_per_million=Decimal("0.25"),
+        output_cost_per_million=Decimal("1.25"),
+        cache_read_cost_per_million=Decimal("0.03"),
+        cache_write_cost_per_million=Decimal("0.30"),
+        source="official_docs_snapshot",
+        source_url="https://platform.claude.com/docs/en/about-claude/pricing",
+        pricing_version="anthropic-pricing-2026-05",
+    ),
+    # ── OpenAI ────────────────────────────────────────────────────────────
     (
         "openai",
         "gpt-4o",
@@ -328,55 +376,6 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
         source_url="https://openai.com/api/pricing/",
         pricing_version="openai-pricing-2026-03-16",
     ),
-    # ── Anthropic older models (pre-4.5 generation) ────────────────────────
-    (
-        "anthropic",
-        "claude-3-5-sonnet-20241022",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("3.00"),
-        output_cost_per_million=Decimal("15.00"),
-        cache_read_cost_per_million=Decimal("0.30"),
-        cache_write_cost_per_million=Decimal("3.75"),
-        source="official_docs_snapshot",
-        source_url="https://platform.claude.com/docs/en/about-claude/pricing",
-        pricing_version="anthropic-pricing-2026-05",
-    ),
-    (
-        "anthropic",
-        "claude-3-5-haiku-20241022",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.80"),
-        output_cost_per_million=Decimal("4.00"),
-        cache_read_cost_per_million=Decimal("0.08"),
-        cache_write_cost_per_million=Decimal("1.00"),
-        source="official_docs_snapshot",
-        source_url="https://platform.claude.com/docs/en/about-claude/pricing",
-        pricing_version="anthropic-pricing-2026-05",
-    ),
-    (
-        "anthropic",
-        "claude-3-opus-20240229",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("15.00"),
-        output_cost_per_million=Decimal("75.00"),
-        cache_read_cost_per_million=Decimal("1.50"),
-        cache_write_cost_per_million=Decimal("18.75"),
-        source="official_docs_snapshot",
-        source_url="https://platform.claude.com/docs/en/about-claude/pricing",
-        pricing_version="anthropic-pricing-2026-05",
-    ),
-    (
-        "anthropic",
-        "claude-3-haiku-20240307",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.25"),
-        output_cost_per_million=Decimal("1.25"),
-        cache_read_cost_per_million=Decimal("0.03"),
-        cache_write_cost_per_million=Decimal("0.30"),
-        source="official_docs_snapshot",
-        source_url="https://platform.claude.com/docs/en/about-claude/pricing",
-        pricing_version="anthropic-pricing-2026-05",
-    ),
     # DeepSeek
     (
         "deepseek",
@@ -440,80 +439,6 @@ _OFFICIAL_DOCS_PRICING: Dict[tuple[str, str], PricingEntry] = {
         source_url="https://ai.google.dev/pricing",
         pricing_version="google-pricing-2026-03-16",
     ),
-    # AWS Bedrock — pricing per the Bedrock pricing page.
-    # Bedrock charges the same per-token rates as the model provider but
-    # through AWS billing.  These are the on-demand prices (no commitment).
-    # Source: https://aws.amazon.com/bedrock/pricing/
-    (
-        "bedrock",
-        "anthropic.claude-opus-4-6",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("15.00"),
-        output_cost_per_million=Decimal("75.00"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "anthropic.claude-sonnet-4-6",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("3.00"),
-        output_cost_per_million=Decimal("15.00"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "anthropic.claude-sonnet-4-5",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("3.00"),
-        output_cost_per_million=Decimal("15.00"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "anthropic.claude-haiku-4-5",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.80"),
-        output_cost_per_million=Decimal("4.00"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "amazon.nova-pro",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.80"),
-        output_cost_per_million=Decimal("3.20"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "amazon.nova-lite",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.06"),
-        output_cost_per_million=Decimal("0.24"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
-    (
-        "bedrock",
-        "amazon.nova-micro",
-    ): PricingEntry(
-        input_cost_per_million=Decimal("0.035"),
-        output_cost_per_million=Decimal("0.14"),
-        source="official_docs_snapshot",
-        source_url="https://aws.amazon.com/bedrock/pricing/",
-        pricing_version="bedrock-pricing-2026-04",
-    ),
     # MiniMax
     (
         "minimax",
@@ -581,36 +506,27 @@ def resolve_billing_route(
     return BillingRoute(provider=provider_name or "unknown", model=model.split("/")[-1] if model else "", base_url=base_url or "", billing_mode="unknown")
 
 
-def _normalize_anthropic_model_name(model: str) -> str:
-    """Normalize Anthropic model name variants to canonical form.
-
-    Handles:
-      - Dot notation: claude-opus-4.7 → claude-opus-4-7
-      - Short aliases: claude-opus-4.7 → claude-opus-4-7
-      - Strips anthropic/ prefix if present
-    """
-    name = model.lower().strip()
-    if name.startswith("anthropic/"):
-        name = name[len("anthropic/"):]
-    # Normalize dots to dashes in version numbers (e.g. 4.7 → 4-7, 4.6 → 4-6)
-    # But preserve the rest of the name structure
-    name = re.sub(r"(\d+)\.(\d+)", r"\1-\2", name)
-    return name
-
-
 def _lookup_official_docs_pricing(route: BillingRoute) -> Optional[PricingEntry]:
     model = route.model.lower()
-    # Direct lookup first
+
+    # ── Plugin-registered pricing entries take priority ──
+    from agent.plugin_registries import registries as _preg
+    plugin_entry = _preg.get_pricing_entry(route.provider, model)
+    if plugin_entry:
+        return plugin_entry
+    # Try provider-specific name normalization via registry
+    _norm = _preg.get_provider_service(route.provider, "normalize_model_name")
+    if _norm is not None:
+        normalized = _norm(model)
+        if normalized != model:
+            plugin_entry = _preg.get_pricing_entry(route.provider, normalized)
+            if plugin_entry:
+                return plugin_entry
+
+    # Fall back to static dict
     entry = _OFFICIAL_DOCS_PRICING.get((route.provider, model))
     if entry:
         return entry
-    # Try normalized name for Anthropic (handles dot-notation like opus-4.7)
-    if route.provider == "anthropic":
-        normalized = _normalize_anthropic_model_name(model)
-        if normalized != model:
-            entry = _OFFICIAL_DOCS_PRICING.get((route.provider, normalized))
-            if entry:
-                return entry
     return None
 
 

cli.py

@@ -74,15 +74,10 @@ except (ImportError, AttributeError):
     _STEADY_CURSOR = None
 
 try:
-    from hermes_cli.pt_input_extras import (
-        install_ctrl_enter_alias,
-        install_ignored_terminal_sequences,
-        install_shift_enter_alias,
-    )
+    from hermes_cli.pt_input_extras import install_shift_enter_alias, install_ctrl_enter_alias
     install_shift_enter_alias()
     install_ctrl_enter_alias()
-    install_ignored_terminal_sequences()
-    del install_shift_enter_alias, install_ctrl_enter_alias, install_ignored_terminal_sequences
+    del install_shift_enter_alias, install_ctrl_enter_alias
 except Exception:
     pass
 import threading
@@ -387,10 +382,6 @@ def load_cli_config() -> Dict[str, Any]:
             "inactivity_timeout": 120,  # Auto-cleanup inactive browser sessions after 2 min
             "record_sessions": False,  # Auto-record browser sessions as WebM videos
             "engine": "auto",  # Browser engine: auto (Chrome), lightpanda, chrome
-            "camofox": {
-                "rewrite_loopback_urls": False,
-                "loopback_host_alias": "host.docker.internal",
-            },
         },
         "compression": {
             "enabled": True,      # Auto-compress when approaching context limit
@@ -585,8 +576,6 @@ def load_cli_config() -> Dict[str, Any]:
         "docker_env": "TERMINAL_DOCKER_ENV",
         "docker_mount_cwd_to_workspace": "TERMINAL_DOCKER_MOUNT_CWD_TO_WORKSPACE",
         "docker_run_as_host_user": "TERMINAL_DOCKER_RUN_AS_HOST_USER",
-        "docker_persist_across_processes": "TERMINAL_DOCKER_PERSIST_ACROSS_PROCESSES",
-        "docker_orphan_reaper": "TERMINAL_DOCKER_ORPHAN_REAPER",
         "sandbox_dir": "TERMINAL_SANDBOX_DIR",
         # Persistent shell (non-local backends)
         "persistent_shell": "TERMINAL_PERSISTENT_SHELL",
@@ -2486,9 +2475,8 @@ _TERMINAL_INPUT_MODE_RESET_SEQ = (
 def _preserve_ctrl_enter_newline() -> bool:
     """Detect environments where Ctrl+Enter must produce a newline, not submit.
 
-    Windows Terminal, WSL, SSH sessions, Ghostty, and some modern terminals
-    deliver Ctrl+Enter/Ctrl+J as bare LF (c-j). On those terminals c-j must
-    NOT be bound to submit;
+    Native Windows, WSL, SSH sessions, and Windows Terminal all send Ctrl+Enter
+    as bare LF (c-j). On those terminals c-j must NOT be bound to submit;
     binding it to submit makes Ctrl+Enter (intended as 'newline like Alt+Enter')
     submit instead. Local POSIX TTYs that deliver Enter as LF (docker exec,
     some thin PTYs without SSH) still need c-j bound to submit, so we keep
@@ -2502,12 +2490,6 @@ def _preserve_ctrl_enter_newline() -> bool:
         return True
     if os.environ.get("WT_SESSION"):
         return True
-    if os.environ.get("GHOSTTY_RESOURCES_DIR") or os.environ.get("GHOSTTY_BIN_DIR"):
-        return True
-    if os.environ.get("TERM", "").lower() == "xterm-ghostty":
-        return True
-    if os.environ.get("TERM_PROGRAM", "").lower() == "ghostty":
-        return True
     if "microsoft" in os.environ.get("WSL_DISTRO_NAME", "").lower():
         return True
     # WSL detection — env vars can be scrubbed under sudo, also peek /proc.
@@ -2528,7 +2510,7 @@ def _bind_prompt_submit_keys(kb, handler) -> None:
     some thin PTYs (docker exec, certain SSH flavors) deliver Enter as LF
     instead of CR — without this, Enter appears dead on those terminals.
 
-    Exception: on Windows, WSL, SSH sessions, Windows Terminal, and Ghostty,
+    Exception: on Windows, WSL, SSH sessions, and Windows Terminal,
     c-j is the wire encoding of Ctrl+Enter (a distinct keystroke from
     plain Enter / c-m). We leave c-j unbound there so the c-j newline
     handler registered separately can fire — giving the user an
@@ -6252,8 +6234,10 @@ class HermesCLI:
         
         # ``self.api_key`` may be a callable (Azure Foundry Entra ID bearer
         # provider). Never invoke it; just identify the auth surface.
-        from agent.azure_identity_adapter import is_token_provider
-        if is_token_provider(self.api_key):
+        from agent.plugin_registries import registries
+        _azure_ns = registries.get_provider_namespace("azure")
+        is_token_provider = _azure_ns.get("is_token_provider")
+        if is_token_provider and is_token_provider(self.api_key):
             api_key_display = "Microsoft Entra ID"
         elif isinstance(self.api_key, str) and len(self.api_key) > 12:
             api_key_display = f"{self.api_key[:8]}...{self.api_key[-4:]}"
@@ -10984,7 +10968,14 @@ class HermesCLI:
             return
         self._voice_tts_done.clear()
         try:
-            from tools.tts_tool import text_to_speech_tool
+            from agent.plugin_registries import registries
+            _tts_provider = registries.get_tool_provider("tts")
+            if _tts_provider is None:
+                raise ImportError("tts tool provider not registered")
+            text_to_speech_tool = _tts_provider.tool_functions.get("text_to_speech_tool")
+            check_tts_requirements = _tts_provider.check_fn
+            if text_to_speech_tool is None:
+                raise ImportError("text_to_speech_tool not found in tts provider")
             from tools.voice_mode import play_audio_file
 
             # Strip markdown and non-speech content for cleaner TTS
@@ -11167,8 +11158,10 @@ class HermesCLI:
         status = "enabled" if self._voice_tts else "disabled"
 
         if self._voice_tts:
-            from tools.tts_tool import check_tts_requirements
-            if not check_tts_requirements():
+            from agent.plugin_registries import registries
+            _tts_provider = registries.get_tool_provider("tts")
+            check_tts_requirements = _tts_provider.check_fn if _tts_provider else None
+            if check_tts_requirements and not check_tts_requirements():
                 _cprint(f"{_DIM}Warning: No TTS provider available. Install edge-tts or set API keys.{_RST}")
 
         _cprint(f"{_ACCENT}Voice TTS {status}.{_RST}")
@@ -11790,13 +11783,17 @@ class HermesCLI:
 
             if self._voice_tts:
                 try:
-                    from tools.tts_tool import (
-                        _load_tts_config as _load_tts_cfg,
-                        _get_provider as _get_prov,
-                        _import_elevenlabs,
-                        _import_sounddevice,
-                        stream_tts_to_speaker,
-                    )
+                    from agent.plugin_registries import registries
+                    _tts_provider = registries.get_tool_provider("tts")
+                    if _tts_provider is None:
+                        raise ImportError("tts tool provider not registered")
+                    _load_tts_cfg = _tts_provider.config_functions.get("_load_tts_config")
+                    _get_prov = _tts_provider.config_functions.get("_get_provider")
+                    _import_elevenlabs = _tts_provider.config_functions.get("_import_elevenlabs")
+                    _import_sounddevice = _tts_provider.config_functions.get("_import_sounddevice")
+                    stream_tts_to_speaker = _tts_provider.tool_functions.get("stream_tts_to_speaker")
+                    if not all([_load_tts_cfg, _get_prov, stream_tts_to_speaker]):
+                        raise ImportError("streaming TTS functions not found in tts provider")
                     _tts_cfg = _load_tts_cfg()
                     if _get_prov(_tts_cfg) == "elevenlabs":
                         # Verify both ElevenLabs SDK and audio output are available
@@ -12722,21 +12719,7 @@ class HermesCLI:
         
         # Key bindings for the input area
         kb = KeyBindings()
-
-        from prompt_toolkit.keys import Keys as _IgnoreKeys
-
-        @kb.add(_IgnoreKeys.Ignore, eager=True)
-        def handle_ignored_terminal_sequence(event):
-            """Consume parser-level ignored terminal sequences before self-insert.
-
-            install_ignored_terminal_sequences() in hermes_cli.pt_input_extras
-            registers focus reports (CSI I / CSI O) as Keys.Ignore at the
-            VT100 parser level. Without this no-op binding the default
-            self-insert path would still fire and the bytes would land in
-            the buffer.
-            """
-            return None
-
+        
         def handle_enter(event):
             """Handle Enter key - submit input.
             
@@ -15157,50 +15140,13 @@ def main(
     # Handle single query mode
     if query or image:
         query, single_query_images = _collect_query_images(query, image)
-        # Kanban workers spawn with ``hermes chat -q "work kanban task <id>"``;
-        # the actual task description lives in the task body. Mirror the
-        # gateway/CLI behaviour for inbound images by scanning the body for
-        # local image paths and http(s) image URLs and attaching them to the
-        # worker's first turn. Without this, users who paste a screenshot
-        # path or URL into a kanban task body never get it routed to the
-        # model's vision input.
-        single_query_image_urls: list[str] = []
-        _kanban_task_id = os.environ.get("HERMES_KANBAN_TASK", "").strip()
-        if _kanban_task_id:
-            try:
-                from hermes_cli import kanban_db as _kb
-                from agent.image_routing import extract_image_refs as _extract_refs
-
-                _conn = _kb.connect()
-                try:
-                    _task = _kb.get_task(_conn, _kanban_task_id)
-                finally:
-                    try:
-                        _conn.close()
-                    except Exception:
-                        pass
-                _body = getattr(_task, "body", "") if _task is not None else ""
-                if _body:
-                    _kb_paths, _kb_urls = _extract_refs(_body)
-                    if _kb_paths:
-                        # Dedupe against any --image the user already passed.
-                        _seen = {str(p) for p in single_query_images}
-                        for _p in _kb_paths:
-                            if _p not in _seen:
-                                _seen.add(_p)
-                                single_query_images.append(Path(_p))
-                    if _kb_urls:
-                        single_query_image_urls.extend(_kb_urls)
-            except Exception as _exc:
-                # Best-effort enrichment; never block worker startup on it.
-                logger.debug("kanban image-ref extraction failed: %s", _exc)
         if quiet:
             # Quiet mode: suppress banner, spinner, tool previews.
             # Only print the final response and parseable session info.
             cli.tool_progress_mode = "off"
             if cli._ensure_runtime_credentials():
                 effective_query: Any = query
-                if single_query_images or single_query_image_urls:
+                if single_query_images:
                     # Honour the same image-routing decision used by the
                     # interactive path. With a vision-capable model (incl.
                     # custom-provider models declared via
@@ -15229,26 +15175,19 @@ def main(
                             _parts, _skipped = _build_parts(
                                 query if isinstance(query, str) else "",
                                 [str(p) for p in single_query_images],
-                                image_urls=list(single_query_image_urls) or None,
                             )
                             if any(p.get("type") == "image_url" for p in _parts):
                                 effective_query = _parts
                             else:
                                 # All images unreadable — text fallback.
-                                # ``_preprocess_images_with_vision`` only knows
-                                # about local files; URLs would be lost there,
-                                # so keep the original query text intact when
-                                # only URLs were supplied.
-                                if single_query_images:
-                                    effective_query = cli._preprocess_images_with_vision(
-                                        query, single_query_images, announce=False,
-                                    )
-                        except Exception:
-                            if single_query_images:
                                 effective_query = cli._preprocess_images_with_vision(
                                     query, single_query_images, announce=False,
                                 )
-                    elif single_query_images:
+                        except Exception:
+                            effective_query = cli._preprocess_images_with_vision(
+                                query, single_query_images, announce=False,
+                            )
+                    else:
                         effective_query = cli._preprocess_images_with_vision(
                             query,
                             single_query_images,

conftest.py

@@ -21,16 +21,45 @@ test runner at ``scripts/run_tests.sh``.
 
 import asyncio
 import os
+import re
 import sys
 from pathlib import Path
+from unittest.mock import patch
 
 import pytest
 
 # Ensure project root is importable
-PROJECT_ROOT = Path(__file__).parent.parent
+PROJECT_ROOT = Path(__file__).parent
 if str(PROJECT_ROOT) not in sys.path:
     sys.path.insert(0, str(PROJECT_ROOT))
 
+# ── Plugin directory sys.path shadow fix ────────────────────────────────────
+# pytest adds ``plugins/model-providers/`` to sys.path because
+# ``plugins/model-providers/anthropic/__init__.py`` (a provider profile) exists.
+# This makes ``import anthropic`` shadow the real SDK package with the plugin
+# directory.  We fix this via pytest_load_initial_conftests (runs before pytest
+# adds package roots) AND inline here as belt-and-suspenders.
+_bad_path = str(PROJECT_ROOT / "plugins" / "model-providers")
+while _bad_path in sys.path:
+    sys.path.remove(_bad_path)
+if "anthropic" in sys.modules and not hasattr(sys.modules["anthropic"], "Anthropic"):
+    del sys.modules["anthropic"]
+
+
+def pytest_load_initial_conftests(early_config, parser, args):
+    """Remove plugin dirs from sys.path before pytest adds package roots.
+
+    This must run as early as possible — before hermes_agent_anthropic is
+    imported — to prevent ``plugins/model-providers/anthropic/__init__.py``
+    (a provider profile) from shadowing the real ``anthropic`` SDK.
+    """
+    _bad = str(PROJECT_ROOT / "plugins" / "model-providers")
+    while _bad in sys.path:
+        sys.path.remove(_bad)
+    if "anthropic" in sys.modules and not hasattr(sys.modules["anthropic"], "Anthropic"):
+        del sys.modules["anthropic"]
+
+
 
 # ── Per-file process isolation ──────────────────────────────────────────────
 # Tests run via ``scripts/run_tests_parallel.py``, which spawns a fresh
@@ -225,8 +254,6 @@ _HERMES_BEHAVIORAL_VARS = frozenset({
     "TERMINAL_CONTAINER_DISK",
     "TERMINAL_CONTAINER_MEMORY",
     "TERMINAL_CONTAINER_PERSISTENT",
-    "TERMINAL_DOCKER_PERSIST_ACROSS_PROCESSES",
-    "TERMINAL_DOCKER_ORPHAN_REAPER",
     "TERMINAL_DOCKER_RUN_AS_HOST_USER",
     "BROWSER_CDP_URL",
     "CAMOFOX_URL",
@@ -533,6 +560,43 @@ def pytest_configure(config):  # noqa: D401 — pytest hook
     )
 
 
+def pytest_collection_finish(session) -> None:  # noqa: D401 — pytest hook
+    """Warn when pytest is invoked directly instead of via the parallel runner.
+
+    The canonical runner (scripts/run_tests_parallel.py) spawns one
+    pytest subprocess per file, giving each a fresh Python interpreter.
+    This prevents cross-file module-level state leakage (especially the
+    plugin-registry singleton) from causing ordering-dependent failures.
+
+    Running ``pytest tests/`` directly collapses all files into one
+    process and WILL see spurious failures that don't exist in CI.
+    The runner sets HERMES_PARALLEL_RUNNER=1 in each subprocess so we
+    can detect the difference here.
+    """
+    if os.environ.get("HERMES_PARALLEL_RUNNER"):
+        return  # launched by the runner — all good
+
+    n = len(session.items)
+    if n < 50:
+        return  # single-file or tiny run — fine to use bare pytest
+
+    _YELLOW = "\033[33m"
+    _BOLD   = "\033[1m"
+    _RESET  = "\033[0m"
+    print(
+        f"\n{_BOLD}{_YELLOW}⚠  hermes-agent test suite warning{_RESET}\n"
+        f"   You're running {n} tests directly under pytest.\n"
+        f"   Cross-file module-state leakage (esp. the plugin registry\n"
+        f"   singleton) can cause ordering-dependent failures that don't\n"
+        f"   exist in CI.\n\n"
+        f"   Use the canonical runner instead:\n"
+        f"     {_BOLD}python scripts/run_tests_parallel.py{_RESET}\n\n"
+        f"   To suppress this warning (e.g. for a focused multi-file run):\n"
+        f"     {_BOLD}HERMES_PARALLEL_RUNNER=1 pytest ...{_RESET}\n",
+        file=sys.stderr,
+    )
+
+
 @pytest.fixture(autouse=True)
 def _live_system_guard(request, monkeypatch):
     """Block real os.kill / systemctl / gateway-pid scans during tests.
@@ -838,3 +902,235 @@ def _live_system_guard(request, monkeypatch):
         pass
 
     yield
+
+# ── Anthropic registry seed (shared across all test subdirs) ────────────────
+# Defined in root conftest so tests/hermes_cli, tests/run_agent,
+# tests/tools, tests/gateway all get it. tests/agent has its own copy too.
+from contextlib import contextmanager
+from unittest.mock import MagicMock
+
+
+
+__all__ = ["mock_anthropic_provider"]
+
+
+def _mock_endpoint_speaks_anthropic_messages(base_url: str) -> bool:
+    """Functional mock — detects Anthropic-wire endpoints by URL pattern.
+
+    Reproduces the real plugin's logic without importing it.
+    """
+    if not base_url:
+        return False
+    normalized = base_url.lower().rstrip("/")
+    if normalized.endswith("/anthropic"):
+        return True
+    # api.anthropic.com
+    if "api.anthropic.com" in normalized:
+        return True
+    # kimi coding plan
+    if "api.kimi.com" in normalized and "/coding" in normalized:
+        return True
+    return False
+
+def _mock_is_anthropic_compat_endpoint(provider: str, base_url: str) -> bool:
+    """Functional mock — detects Anthropic-compat endpoints.
+
+    Reproduces the real plugin's logic: named compat providers OR /anthropic URL suffix.
+    """
+    _COMPAT_PROVIDERS = frozenset({"minimax", "minimax-oauth", "minimax-cn"})
+    if provider in _COMPAT_PROVIDERS:
+        return True
+    url_lower = (base_url or "").lower()
+    return "/anthropic" in url_lower
+
+def _mock_convert_openai_images_to_anthropic(messages: list) -> list:
+    """Functional mock — converts OpenAI image_url blocks to Anthropic image blocks."""
+    converted = []
+    for msg in messages:
+        content = msg.get("content")
+        if not isinstance(content, list):
+            converted.append(msg)
+            continue
+        new_content = []
+        changed = False
+        for block in content:
+            if block.get("type") == "image_url":
+                image_url_val = (block.get("image_url") or {}).get("url", "")
+                if image_url_val.startswith("data:"):
+                    header, _, b64data = image_url_val.partition(",")
+                    media_type = "image/png"
+                    if ":" in header and ";" in header:
+                        media_type = header.split(":", 1)[1].split(";", 1)[0]
+                    new_content.append({
+                        "type": "image",
+                        "source": {
+                            "type": "base64",
+                            "media_type": media_type,
+                            "data": b64data,
+                        },
+                    })
+                else:
+                    new_content.append({
+                        "type": "image",
+                        "source": {
+                            "type": "url",
+                            "url": image_url_val,
+                        },
+                    })
+                changed = True
+            else:
+                new_content.append(block)
+        converted.append({**msg, "content": new_content} if changed else msg)
+    return converted
+
+def _mock_maybe_wrap_anthropic(client_obj, model, api_key, base_url, api_mode=None):
+    """Functional mock for maybe_wrap_anthropic — wraps when endpoint is Anthropic-wire.
+
+    Reproduces the real plugin's wrapping logic without importing it.
+    Uses the real AnthropicAuxiliaryClient from core (no SDK dependency).
+    """
+    # Already wrapped — don't double-wrap
+    from agent.anthropic_aux import (AnthropicAuxiliaryClient,
+                                      AsyncAnthropicAuxiliaryClient)
+    if isinstance(client_obj, (AnthropicAuxiliaryClient, AsyncAnthropicAuxiliaryClient)):
+        return client_obj
+
+    # Check for other specialized adapters we should never re-dispatch
+    try:
+        from agent.auxiliary_client import CodexAuxiliaryClient
+        if isinstance(client_obj, CodexAuxiliaryClient):
+            return client_obj
+    except ImportError:
+        pass
+
+    # Explicit non-anthropic api_mode wins over URL heuristics
+    if api_mode and api_mode != "anthropic_messages":
+        return client_obj
+
+    should_wrap = (
+        api_mode == "anthropic_messages"
+        or _mock_endpoint_speaks_anthropic_messages(base_url)
+    )
+    if not should_wrap:
+        return client_obj
+
+    # Use the registry's build_anthropic_client to construct a real(ish) client
+    from agent.plugin_registries import registries
+    build_fn = registries.get_provider_service("anthropic", "build_anthropic_client")
+    if build_fn is None:
+        return client_obj
+
+    try:
+        real_client = build_fn(api_key, base_url)
+    except Exception:
+        return client_obj
+
+    return AnthropicAuxiliaryClient(
+        real_client, model, api_key, base_url, is_oauth=False,
+    )
+
+def _make_base_anthropic_namespace() -> dict:
+    """Build a minimal anthropic service namespace with safe mock stubs.
+
+    Wire-format code (build_anthropic_kwargs, convert_messages_to_anthropic,
+    AnthropicAuxiliaryClient, etc.) has moved to core modules and is no
+    longer looked up via the registry.  Only SDK-dependent orchestration
+    (maybe_wrap_anthropic, is_anthropic_compat_endpoint, client building,
+    auth) still needs mock stubs here.
+    """
+    mock_client = MagicMock(name="anthropic_client")
+    mock_client.base_url = "https://api.anthropic.com/v1"
+    mock_client.api_key = "sk-ant-mock"
+
+    def _resolve_token():
+        """Return token from env vars if set — mimics the real resolve_anthropic_token."""
+        import os
+        return (os.environ.get("ANTHROPIC_TOKEN")
+                or os.environ.get("ANTHROPIC_API_KEY"))
+
+    return {
+        # SDK-dependent client building
+        "build_anthropic_client": MagicMock(return_value=mock_client),
+        "build_anthropic_bedrock_client": MagicMock(return_value=mock_client),
+        "resolve_anthropic_token": _resolve_token,
+        "_is_oauth_token": lambda k: bool(k) and not (k or "").startswith("sk-ant-api"),
+        "is_claude_code_token_valid": MagicMock(return_value=False),
+        "read_claude_code_credentials": MagicMock(return_value=None),
+        "write_claude_code_credentials": MagicMock(),
+        "refresh_oauth_token": MagicMock(return_value=None),
+        "run_hermes_oauth_login_pure": MagicMock(return_value=("mock-token", None)),
+        "_HERMES_OAUTH_FILE": MagicMock(),
+        # Resolve / endpoint detection (still plugin-provided, still needs mocking)
+        "maybe_wrap_anthropic": _mock_maybe_wrap_anthropic,
+        "endpoint_speaks_anthropic_messages": _mock_endpoint_speaks_anthropic_messages,
+        "is_anthropic_compat_endpoint": _mock_is_anthropic_compat_endpoint,
+        "convert_openai_images_to_anthropic": _mock_convert_openai_images_to_anthropic,
+        "ANTHROPIC_DEFAULT_BASE_URL": "https://api.anthropic.com",
+        "_ANTHROPIC_COMPAT_PROVIDERS": frozenset(),
+        "resolve_auxiliary_client": MagicMock(return_value=(mock_client, "claude-3-5-sonnet-20241022")),
+    }
+
+@contextmanager
+def mock_anthropic_provider(**overrides):
+    """Patch the anthropic registry namespace. Use in core tests instead of
+    patching hermes_agent_anthropic.* directly.
+
+    Usage:
+        with mock_anthropic_provider(build_anthropic_client=my_mock):
+            result = resolve_provider_client(...)
+    """
+    from agent.plugin_registries import registries
+    base = _make_base_anthropic_namespace()
+    base.update(overrides)
+    with patch.dict(registries._provider_services, {"anthropic": base}):
+        yield base
+
+@pytest.fixture(autouse=True)
+def _seed_anthropic_registry(request):
+    """Install mock anthropic namespace before each test, restore after.
+
+    Skips for plugin tests — they have their own conftest that registers the
+    real plugin, and we must NOT block them with _guarded_register.
+
+    Uses patch.dict so it's guaranteed to restore even when plugin tests
+    in other directories (which use the real plugin) run before us in the
+    same process. Function-scoped (not session) so it re-seeds after each
+    plugin test that overwrites the registry.
+
+    Also clears _provider_resolvers["anthropic"] so a real plugin registration
+    that leaked from another test file doesn't affect core unit tests.
+
+    Also blocks _ensure_plugins_discovered() so that code paths that lazily
+    trigger plugin loading (e.g. get_plugin_auxiliary_tasks via
+    _resolve_task_provider_model) don't overwrite the mock namespace.
+    """
+    # Skip for plugin tests — they manage the registry themselves
+    node_path = str(request.fspath)
+    if "/plugins/" in node_path:
+        yield
+        return
+    from unittest.mock import patch
+    from agent.plugin_registries import registries
+    ns = _make_base_anthropic_namespace()
+    # Guard registries.register_provider_services so that if discover_and_load()
+    # fires during a test (e.g. via get_plugin_auxiliary_tasks in
+    # _resolve_task_provider_model), it can't overwrite our mock anthropic
+    # namespace.  We only block "anthropic" — other providers / hooks proceed
+    # normally so tests like test_context_engine.py still work.
+    _orig_register = registries.register_provider_services
+
+    def _guarded_register(name, services):
+        if name == "anthropic":
+            return  # mock namespace wins — don't let the real plugin clobber it
+        return _orig_register(name, services)
+
+    _orig_resolver = registries._provider_resolvers.pop("anthropic", None)
+    with patch.dict(registries._provider_services, {"anthropic": ns}), \
+         patch.object(registries, "register_provider_services", _guarded_register):
+        yield
+    # Restore resolver (None means "not registered", which is correct for
+    # core unit tests; plugin tests that need the real resolver load it themselves)
+    if _orig_resolver is not None:
+        registries._provider_resolvers["anthropic"] = _orig_resolver
+    else:
+        registries._provider_resolvers.pop("anthropic", None)

docker/s6-rc.d/dashboard/run

@@ -30,21 +30,13 @@ cd /opt/data
 dash_host="${HERMES_DASHBOARD_HOST:-0.0.0.0}"
 dash_port="${HERMES_DASHBOARD_PORT:-9119}"
 
-# `--insecure` is opt-in via HERMES_DASHBOARD_INSECURE. The dashboard's
-# OAuth auth gate engages automatically on non-loopback binds when a
-# DashboardAuthProvider is registered (e.g. the bundled dashboard_auth/nous
-# provider, which auto-registers when HERMES_DASHBOARD_OAUTH_CLIENT_ID is
-# set). If no provider is registered, start_server fails closed with a
-# specific operator-facing error.
-#
-# This used to derive --insecure from the bind host ("anything non-loopback
-# implies insecure"), but that predates the OAuth gate and silently
-# disabled it on every container-deployed dashboard. The gate is now the
-# authority; operators on trusted LANs / behind a reverse proxy without
-# the OAuth contract opt in explicitly.
+# Binding to anything other than localhost requires --insecure — the
+# dashboard refuses otherwise because it exposes API keys. Inside a
+# container this is the expected deployment.
 insecure=""
-case "${HERMES_DASHBOARD_INSECURE:-}" in
-    1|true|TRUE|True|yes|YES|Yes) insecure="--insecure" ;;
+case "$dash_host" in
+    127.0.0.1|localhost) ;;
+    *) insecure="--insecure" ;;
 esac
 
 # shellcheck disable=SC2086  # word-splitting of $insecure is intentional

docker/stage2-hook.sh

@@ -33,15 +33,6 @@ INSTALL_DIR="/opt/hermes"
 mkdir -p "$HERMES_HOME"
 
 # --- UID/GID remap ---
-# Accept PUID/PGID as aliases for HERMES_UID/HERMES_GID.  NAS users (UGOS,
-# Synology, unRAID) expect the LinuxServer.io PUID/PGID convention and
-# bind-mount /opt/data from a host directory owned by their own UID; without
-# this alias those vars are silently ignored and the s6-setuidgid drop to
-# UID 10000 leaves the runtime unable to read the volume.  HERMES_UID/
-# HERMES_GID still win when both are set.  See #15290, salvages #25872.
-HERMES_UID="${HERMES_UID:-${PUID:-}}"
-HERMES_GID="${HERMES_GID:-${PGID:-}}"
-
 if [ -n "${HERMES_UID:-}" ] && [ "$HERMES_UID" != "$(id -u hermes)" ]; then
     echo "[stage2] Changing hermes UID to $HERMES_UID"
     usermod -u "$HERMES_UID" hermes
@@ -53,62 +44,6 @@ if [ -n "${HERMES_GID:-}" ] && [ "$HERMES_GID" != "$(id -g hermes)" ]; then
     groupmod -o -g "$HERMES_GID" hermes 2>/dev/null || true
 fi
 
-# --- Docker socket group membership (docker-in-docker / DooD) ---
-# When the user bind-mounts the host Docker daemon socket
-# (`-v /var/run/docker.sock:/var/run/docker.sock`) to use the `docker`
-# terminal backend from inside the container, the socket is owned by the
-# host's `docker` group (or root). The supervised hermes user (UID 10000)
-# is not a member of any group that matches the socket's GID, so every
-# `docker` invocation EACCES'es and `check_terminal_requirements()` fails.
-# See #16703.
-#
-# Granting the supp group via `docker run --group-add <gid>` alone is
-# NOT sufficient with our s6-setuidgid privilege drop: s6-setuidgid (and
-# gosu, the older shim) calls initgroups() for the target user, which
-# rebuilds the supplementary group list from /etc/group. Without an
-# /etc/group entry whose GID matches the socket, the kernel-granted
-# supp group is silently wiped between PID 1 and the dropped process.
-# Confirmed empirically: `--group-add 998` alone leaves the dropped
-# hermes process with `Groups: 10000` (998 gone); after this hook adds
-# the entry, the dropped process has `Groups: 998 10000` as expected.
-#
-# Fix: detect the socket's GID at boot and ensure /etc/group has a
-# matching entry that includes hermes. Idempotent across container
-# restarts. Skipped silently when no socket is bind-mounted.
-#
-# Handles the awkward corner cases:
-#   - socket owned by GID 0 (root) — some Podman setups; usermod -aG root
-#   - socket GID already used by a known container group (e.g. tty=5):
-#     reuse that group's name rather than creating a duplicate
-#   - hermes is already a member of the right group (idempotent restart)
-#   - chown/groupadd failures under rootless containers — non-fatal
-for sock in /var/run/docker.sock /run/docker.sock; do
-    [ -S "$sock" ] || continue
-    sock_gid=$(stat -c '%g' "$sock" 2>/dev/null) || continue
-    [ -n "$sock_gid" ] || continue
-    # Already a member? Nothing to do.
-    if id -G hermes 2>/dev/null | tr ' ' '\n' | grep -qx "$sock_gid"; then
-        echo "[stage2] hermes already in group $sock_gid for $sock"
-        break
-    fi
-    # Resolve or create a group name for this GID.
-    sock_group=$(getent group "$sock_gid" 2>/dev/null | cut -d: -f1)
-    if [ -z "$sock_group" ]; then
-        sock_group="hostdocker"
-        if ! groupadd -g "$sock_gid" "$sock_group" 2>/dev/null; then
-            echo "[stage2] Warning: groupadd -g $sock_gid $sock_group failed; skipping docker socket group setup"
-            break
-        fi
-        echo "[stage2] Created group $sock_group (GID $sock_gid) for Docker socket"
-    fi
-    if usermod -aG "$sock_group" hermes 2>/dev/null; then
-        echo "[stage2] Added hermes to group $sock_group (GID $sock_gid) for $sock"
-    else
-        echo "[stage2] Warning: usermod -aG $sock_group hermes failed; docker backend may fail with EACCES"
-    fi
-    break
-done
-
 # --- Fix ownership of data volume ---
 # When HERMES_UID is remapped or the top-level $HERMES_HOME isn't owned by
 # the runtime hermes UID, restore ownership to hermes — but ONLY for the

docs/security/network-egress-isolation.md

@@ -1,195 +0,0 @@
-# Network Egress Isolation for Docker Deployments
-
-When running Hermes inside Docker, the default `network_mode: host` gives the
-agent process unrestricted outbound network access. This guide shows how to
-segment traffic so the agent core can only reach the services it needs, while
-blocking arbitrary outbound connections.
-
-This is primarily a defense against prompt injection attacks that attempt to
-exfiltrate data via `curl`, `wget`, or raw HTTP from tool-generated shell
-commands.
-
-## Threat Model
-
-The Hermes [SECURITY.md](../../SECURITY.md) §2 defines the trust model. The
-terminal backend is the primary execution boundary. However, when running with
-`network_mode: host`, any command the agent executes can reach any endpoint on
-the network, including external ones.
-
-Network egress isolation adds a second layer: even if a malicious command
-executes inside the container, it cannot reach endpoints outside the
-explicitly allowlisted set.
-
-## Architecture
-
-```
-┌─────────────────────────────────────────────┐
-│  Docker Network: internal (no internet)     │
-│                                             │
-│   ┌──────────────┐   ┌──────────────────┐   │
-│   │ hermes-agent │   │ hermes-dashboard │   │
-│   └──────┬───────┘   └────────┬─────────┘   │
-│          │                    │              │
-│          ▼                    │              │
-│   ┌──────────────┐            │              │
-│   │ hermes-gtw   │◄───────────┘              │
-│   └──────┬───────┘                           │
-│          │                                   │
-└──────────┼───────────────────────────────────┘
-           │
-┌──────────┼───────────────────────────────────┐
-│  Docker Network: egress (internet-capable)   │
-│          │                                   │
-│          ▼                                   │
-│   ┌─────────────────┐                        │
-│   │ egress-proxy     │──► allowlisted hosts  │
-│   │ (squid / envoy)  │                       │
-│   └─────────────────┘                        │
-└──────────────────────────────────────────────┘
-```
-
-Two Docker networks:
-
-- **`internal`** — no default route, no internet access. The agent, dashboard,
-  and gateway run here.
-- **`egress`** — has internet access. Only services that need to reach external
-  APIs are attached to this network.
-
-The gateway service is dual-homed (attached to both networks) so it can
-receive inbound messages from Telegram/Slack/etc. and forward them to the
-agent on the internal network.
-
-## Compose Configuration
-
-Override the default `docker-compose.yml` with a
-`docker-compose.override.yml`:
-
-```yaml
-# docker-compose.override.yml
-# Network egress isolation for production deployments.
-#
-# Usage:
-#   HERMES_UID=$(id -u) HERMES_GID=$(id -g) docker compose up -d
-#
-# This overrides network_mode: host with isolated Docker networks.
-
-networks:
-  internal:
-    driver: bridge
-    internal: true          # no default route, no internet
-  egress:
-    driver: bridge
-
-services:
-  gateway:
-    network_mode: ""        # clear the host-mode default
-    networks:
-      - internal
-      - egress              # needs outbound for Telegram, LLM APIs
-    ports:
-      - "127.0.0.1:9119:9119"   # dashboard proxy, localhost only
-
-  dashboard:
-    network_mode: ""
-    networks:
-      - internal            # internal only, no egress needed
-```
-
-### With an Egress Proxy (Recommended)
-
-For tighter control, route all outbound traffic through an HTTP proxy with
-an explicit allowlist:
-
-```yaml
-# docker-compose.override.yml (with egress proxy)
-
-networks:
-  internal:
-    driver: bridge
-    internal: true
-  egress:
-    driver: bridge
-
-services:
-  gateway:
-    network_mode: ""
-    networks:
-      - internal
-      - egress
-    environment:
-      - HTTP_PROXY=http://egress-proxy:3128
-      - HTTPS_PROXY=http://egress-proxy:3128
-      - NO_PROXY=hermes,hermes-dashboard,localhost
-
-  dashboard:
-    network_mode: ""
-    networks:
-      - internal
-
-  egress-proxy:
-    image: ubuntu/squid:6.10-24.04_edge
-    networks:
-      - egress
-    volumes:
-      - ./config/squid-allowlist.conf:/etc/squid/conf.d/allowlist.conf:ro
-    restart: unless-stopped
-```
-
-Example `config/squid-allowlist.conf`:
-
-```
-# Only allow HTTPS CONNECT to these hosts
-acl allowed_hosts dstdomain api.openai.com
-acl allowed_hosts dstdomain api.anthropic.com
-acl allowed_hosts dstdomain openrouter.ai
-acl allowed_hosts dstdomain generativelanguage.googleapis.com
-acl allowed_hosts dstdomain api.telegram.org
-acl allowed_hosts dstdomain api.github.com
-acl allowed_hosts dstdomain discord.com
-
-http_access allow CONNECT allowed_hosts
-http_access deny all
-```
-
-Adjust the allowlist to match your LLM provider and messaging platform.
-
-## Validating the Setup
-
-After bringing up the stack, verify isolation:
-
-```bash
-# From the agent container: this should FAIL (no egress)
-docker compose exec gateway \
-  curl -sf --max-time 5 https://example.com && echo "FAIL: egress not blocked" || echo "OK: egress blocked"
-
-# From the agent container: this should SUCCEED (internal network)
-docker compose exec gateway \
-  curl -sf --max-time 5 http://hermes-dashboard:9119/health && echo "OK: internal reachable" || echo "FAIL"
-
-# If using egress proxy: this should SUCCEED (allowlisted)
-docker compose exec gateway \
-  curl -sf --max-time 5 --proxy http://egress-proxy:3128 https://api.openai.com/v1/models && echo "OK" || echo "FAIL"
-```
-
-## Limitations
-
-- **DNS resolution:** The `internal` network can still resolve external DNS
-  names unless you also run a local DNS resolver that blocks external queries.
-  For most threat models this is acceptable since DNS resolution alone does not
-  exfiltrate meaningful data.
-
-- **Not a substitute for sandbox backends:** This guide isolates the agent
-  *container's* network. If you use the default local terminal backend, tool
-  commands execute inside the same container. For stronger isolation, combine
-  network segmentation with a sandboxed terminal backend (Docker, Modal,
-  Daytona).
-
-- **Platform adapters need egress:** The gateway service needs outbound access
-  to reach messaging platform APIs. If you add new platform adapters, add their
-  API endpoints to the proxy allowlist.
-
-## Related
-
-- [SECURITY.md](../../SECURITY.md) — Hermes trust model and vulnerability reporting
-- [Terminal backends](../../README.md) — sandboxed execution targets
-- [docker-compose.yml](../../docker-compose.yml) — default compose configuration

gateway/platforms/base.py

@@ -472,7 +472,6 @@ def is_host_excluded_by_no_proxy(hostname: str, no_proxy_value: str | None = Non
     return False
 
 
-import dataclasses
 from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
@@ -848,13 +847,6 @@ MEDIA_DELIVERY_SAFE_ROOTS = (
     _HERMES_HOME / "video_cache",
     _HERMES_HOME / "document_cache",
     _HERMES_HOME / "browser_screenshots",
-    # Canonical cache layout — listed alongside the legacy *_cache dirs so
-    # generated artifacts deliver on installs that have both (#31733).
-    _HERMES_HOME / "cache" / "images",
-    _HERMES_HOME / "cache" / "audio",
-    _HERMES_HOME / "cache" / "videos",
-    _HERMES_HOME / "cache" / "documents",
-    _HERMES_HOME / "cache" / "screenshots",
 )
 
 # Default recency window for trusting freshly-produced files (seconds).
@@ -1029,11 +1021,7 @@ def validate_media_delivery_path(path: str) -> Optional[str]:
     if not candidate:
         return None
 
-    try:
-        expanded = Path(os.path.expanduser(candidate))
-    except (OSError, RuntimeError, ValueError):
-        # expanduser raises ValueError("embedded null byte") for a ~\x00 path.
-        return None
+    expanded = Path(os.path.expanduser(candidate))
     if not expanded.is_absolute():
         return None
 
@@ -1077,17 +1065,6 @@ def validate_media_delivery_path(path: str) -> Optional[str]:
     return None
 
 
-# Neutralise control chars and the Unicode line separators (NEL, LS, PS) that
-# str.splitlines() / log aggregators treat as breaks, so a model-emitted path
-# can't forge a second log line. Truncated to keep records bounded.
-_LOG_UNSAFE_CHARS = re.compile(r"[\x00-\x1f\x7f\x85\u2028\u2029]")
-
-
-def _log_safe_path(path: str) -> str:
-    """Return a single-line, length-bounded path for log output."""
-    return _LOG_UNSAFE_CHARS.sub("?", str(path))[:200]
-
-
 SUPPORTED_DOCUMENT_TYPES = {
     ".pdf": "application/pdf",
     ".md": "text/markdown",
@@ -1584,10 +1561,6 @@ class BasePlatformAdapter(ABC):
         self.config = config
         self.platform = platform
         self._message_handler: Optional[MessageHandler] = None
-        # Optional hook (e.g. Telegram DM topic recovery) that rewrites
-        # ``event.source.thread_id`` before session keying. Returns the
-        # corrected thread_id or None to leave the source untouched.
-        self._topic_recovery_fn: Optional[Callable[[Any], Optional[str]]] = None
         self._running = False
         self._fatal_error_code: Optional[str] = None
         self._fatal_error_message: Optional[str] = None
@@ -1655,29 +1628,6 @@ class BasePlatformAdapter(ABC):
         """
         return len
 
-    @property
-    def enforces_own_access_policy(self) -> bool:
-        """Whether this adapter gates inbound access before dispatch.
-
-        Some adapters (WeCom, Weixin, Yuanbao, QQBot) implement a documented
-        config-driven access surface — ``dm_policy`` / ``group_policy`` /
-        ``allow_from`` / ``group_allow_from`` in ``PlatformConfig.extra`` — and
-        enforce it at intake: a message is dropped inside the adapter and never
-        reaches the gateway unless it already passed that policy.
-
-        The gateway's env-based allowlist check runs *after* the adapter, so for
-        these platforms a message arriving at ``_is_user_authorized`` has, by
-        definition, already been authorized by the adapter. Without this flag the
-        gateway would then deny it again (no env allowlist → default deny),
-        silently breaking ``dm_policy: open`` and config-only allowlists.
-
-        Adapters that own their access policy override this to return ``True``.
-        The gateway treats that as "already authorized at intake" and skips the
-        env-allowlist default-deny. Adapters that delegate access control to the
-        gateway leave it ``False`` (the default).
-        """
-        return False
-
     def supports_draft_streaming(
         self,
         chat_type: Optional[str] = None,
@@ -1866,40 +1816,6 @@ class BasePlatformAdapter(ABC):
         """
         self._message_handler = handler
 
-    def set_topic_recovery_fn(
-        self,
-        fn: Optional[Callable[[Any], Optional[str]]],
-    ) -> None:
-        """Install a thread_id-recovery hook (Telegram DM topic mode).
-
-        The hook is called with ``event.source`` before session keying;
-        a non-None return value replaces ``source.thread_id``. Pass
-        ``None`` to clear the hook.
-        """
-        # Guard against subclasses that initialize via ``object.__new__`` in
-        # tests and never run ``BasePlatformAdapter.__init__``.
-        self._topic_recovery_fn = fn  # type: ignore[attr-defined]
-
-    def _apply_topic_recovery(self, event: MessageEvent) -> None:
-        """Rewrite ``event.source.thread_id`` in place if the hook returns one."""
-        recover = getattr(self, "_topic_recovery_fn", None)
-        if recover is None:
-            return
-        source = getattr(event, "source", None)
-        if source is None:
-            return
-        try:
-            recovered = recover(source)
-        except Exception:
-            logger.debug("topic recovery hook failed", exc_info=True)
-            return
-        if recovered is None or str(recovered) == str(source.thread_id or ""):
-            return
-        try:
-            event.source = dataclasses.replace(source, thread_id=str(recovered))
-        except Exception:
-            logger.debug("topic recovery rewrite failed", exc_info=True)
-
     def set_busy_session_handler(self, handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]]) -> None:
         """Set an optional handler for messages arriving during active sessions."""
         self._busy_session_handler = handler
@@ -2483,12 +2399,11 @@ class BasePlatformAdapter(ABC):
         """Drop unsafe MEDIA paths and normalize accepted paths."""
         safe_media: List[Tuple[str, bool]] = []
         for media_path, is_voice in media_files or []:
-            raw = str(media_path)
-            safe_path = validate_media_delivery_path(raw)
+            safe_path = validate_media_delivery_path(str(media_path))
             if safe_path:
                 safe_media.append((safe_path, bool(is_voice)))
             else:
-                logger.warning("Skipping unsafe MEDIA directive path: %s", _log_safe_path(raw))
+                logger.warning("Skipping unsafe MEDIA directive path outside allowed roots")
         return safe_media
 
     @staticmethod
@@ -2496,12 +2411,11 @@ class BasePlatformAdapter(ABC):
         """Drop unsafe bare local file paths and normalize accepted paths."""
         safe_paths: List[str] = []
         for file_path in file_paths or []:
-            raw = str(file_path)
-            safe_path = validate_media_delivery_path(raw)
+            safe_path = validate_media_delivery_path(str(file_path))
             if safe_path:
                 safe_paths.append(safe_path)
             else:
-                logger.warning("Skipping unsafe local file path: %s", _log_safe_path(raw))
+                logger.warning("Skipping unsafe local file path outside allowed roots")
         return safe_paths
 
     @staticmethod
@@ -2552,12 +2466,7 @@ class BasePlatformAdapter(ABC):
                 path = path[1:-1].strip()
             path = path.lstrip("`\"'").rstrip("`\"',.;:)}]")
             if path:
-                try:
-                    media.append((os.path.expanduser(path), has_voice_tag))
-                except (OSError, RuntimeError, ValueError):
-                    # Skip a crafted ~\x00 path rather than aborting extraction
-                    # and dropping every other attachment in the response.
-                    continue
+                media.append((os.path.expanduser(path), has_voice_tag))
 
         # Remove MEDIA tags from content (including surrounding quote/backtick wrappers)
         if media:
@@ -3423,12 +3332,7 @@ class BasePlatformAdapter(ABC):
             return
 
         coerce_plaintext_gateway_command(event)
-
-        # Rewrite ``event.source.thread_id`` via the installed recovery hook
-        # (Telegram DM topic mode) so the session key, guard checks, and
-        # downstream delivery all agree on the same lane.
-        self._apply_topic_recovery(event)
-
+        
         session_key = build_session_key(
             event.source,
             group_sessions_per_user=self.config.extra.get("group_sessions_per_user", True),
@@ -3750,8 +3654,11 @@ class BasePlatformAdapter(ABC):
                         and text_content
                         and not media_files):
                     try:
-                        from tools.tts_tool import text_to_speech_tool, check_tts_requirements
-                        if check_tts_requirements():
+                        from agent.plugin_registries import registries
+                        _tts = registries.get_tool_provider("tts")
+                        text_to_speech_tool = _tts.tool_functions.get("text_to_speech_tool") if _tts else None
+                        check_tts_requirements = _tts.check_fn if _tts else None
+                        if check_tts_requirements and text_to_speech_tool and check_tts_requirements():
                             import json as _json
                             speech_text = self.prepare_tts_text(text_content)
                             if not speech_text:

gateway/platforms/qqbot/adapter.py

@@ -126,6 +126,7 @@ from gateway.platforms.qqbot.chunked_upload import (
 )
 from gateway.platforms.qqbot.keyboards import (
     ApprovalRequest,
+    ApprovalSender,
     InlineKeyboard,
     InteractionEvent,
     build_approval_keyboard,
@@ -269,11 +270,6 @@ class QQAdapter(BasePlatformAdapter):
     def name(self) -> str:
         return "QQBot"
 
-    @property
-    def enforces_own_access_policy(self) -> bool:
-        """QQBot gates DM/group access at intake via dm_policy/group_policy."""
-        return True
-
     # ------------------------------------------------------------------
     # Connection lifecycle
     # ------------------------------------------------------------------

gateway/platforms/qqbot/chunked_upload.py

@@ -37,7 +37,7 @@ import asyncio
 import functools
 import hashlib
 import logging
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Any, Awaitable, Callable, Dict, List, Optional
 

gateway/platforms/wecom.py

@@ -847,11 +847,6 @@ class WeComAdapter(BasePlatformAdapter):
     # Policy helpers
     # ------------------------------------------------------------------
 
-    @property
-    def enforces_own_access_policy(self) -> bool:
-        """WeCom gates DM/group access at intake via dm_policy/group_policy."""
-        return True
-
     def _is_dm_allowed(self, sender_id: str) -> bool:
         if self._dm_policy == "disabled":
             return False

gateway/platforms/weixin.py

@@ -658,6 +658,52 @@ def _split_table_row(line: str) -> List[str]:
     return [cell.strip() for cell in row.split("|")]
 
 
+def _rewrite_headers_for_weixin(line: str) -> str:
+    match = _HEADER_RE.match(line)
+    if not match:
+        return line.rstrip()
+    level = len(match.group(1))
+    title = match.group(2).strip()
+    if level == 1:
+        return f"【{title}】"
+    return f"**{title}**"
+
+
+def _rewrite_table_block_for_weixin(lines: List[str]) -> str:
+    if len(lines) < 2:
+        return "\n".join(lines)
+    headers = _split_table_row(lines[0])
+    body_rows = [_split_table_row(line) for line in lines[2:] if line.strip()]
+    if not headers or not body_rows:
+        return "\n".join(lines)
+
+    formatted_rows: List[str] = []
+    for row in body_rows:
+        pairs = []
+        for idx, header in enumerate(headers):
+            if idx >= len(row):
+                break
+            label = header or f"Column {idx + 1}"
+            value = row[idx].strip()
+            if value:
+                pairs.append((label, value))
+        if not pairs:
+            continue
+        if len(pairs) == 1:
+            label, value = pairs[0]
+            formatted_rows.append(f"- {label}: {value}")
+            continue
+        if len(pairs) == 2:
+            label, value = pairs[0]
+            other_label, other_value = pairs[1]
+            formatted_rows.append(f"- {label}: {value}")
+            formatted_rows.append(f"  {other_label}: {other_value}")
+            continue
+        summary = " | ".join(f"{label}: {value}" for label, value in pairs)
+        formatted_rows.append(f"- {summary}")
+    return "\n".join(formatted_rows) if formatted_rows else "\n".join(lines)
+
+
 def _normalize_markdown_blocks(content: str) -> str:
     lines = content.splitlines()
     result: List[str] = []
@@ -1397,11 +1443,6 @@ class WeixinAdapter(BasePlatformAdapter):
         logger.info("[%s] inbound from=%s type=%s media=%d", self.name, _safe_id(sender_id), source.chat_type, len(media_paths))
         await self.handle_message(event)
 
-    @property
-    def enforces_own_access_policy(self) -> bool:
-        """Weixin gates DM/group access at intake via dm_policy/group_policy."""
-        return True
-
     def _is_dm_allowed(self, sender_id: str) -> bool:
         if self._dm_policy == "disabled":
             return False

gateway/platforms/yuanbao.py

@@ -2230,45 +2230,6 @@ class MediaResolveMiddleware(InboundMiddleware):
 
     name = "media-resolve"
 
-    # --- Resource download cache (keyed by resourceId) ---
-    # Avoids redundant downloads of the same resource within the TTL window.
-    # The same resourceId can be referenced multiple times in a session (own
-    # attachment, then quoted again, then observed in a group backfill); each
-    # reference otherwise triggers a fresh token exchange + download.
-    _resource_cache: ClassVar[Dict[str, Tuple[str, str, float]]] = {}  # rid -> (local_path, mime, ts)
-    _RESOURCE_CACHE_TTL_S: ClassVar[int] = 24 * 60 * 60  # 24 hours
-    _RESOURCE_CACHE_MAX_SIZE: ClassVar[int] = 256
-
-    @classmethod
-    def _get_cached_resource(cls, resource_id: str) -> Optional[Tuple[str, str]]:
-        """Return cached ``(local_path, mime)`` if still valid and file exists, else None."""
-        if not resource_id:
-            return None
-        entry = cls._resource_cache.get(resource_id)
-        if entry is None:
-            return None
-        local_path, mime, ts = entry
-        if time.time() - ts > cls._RESOURCE_CACHE_TTL_S:
-            cls._resource_cache.pop(resource_id, None)
-            return None
-        # Verify the cached file still exists on disk (cache dir may be swept).
-        if not os.path.isfile(local_path):
-            cls._resource_cache.pop(resource_id, None)
-            return None
-        return local_path, mime
-
-    @classmethod
-    def _put_cached_resource(cls, resource_id: str, local_path: str, mime: str) -> None:
-        """Store download result in cache. Evicts oldest entries when over capacity."""
-        if not resource_id:
-            return
-        if len(cls._resource_cache) >= cls._RESOURCE_CACHE_MAX_SIZE:
-            # Drop the oldest 25% of entries by timestamp.
-            sorted_keys = sorted(cls._resource_cache, key=lambda k: cls._resource_cache[k][2])
-            for k in sorted_keys[: cls._RESOURCE_CACHE_MAX_SIZE // 4]:
-                cls._resource_cache.pop(k, None)
-        cls._resource_cache[resource_id] = (local_path, mime, time.time())
-
     @staticmethod
     def _guess_image_ext_from_url(url: str) -> str:
         """Guess image extension from URL path."""
@@ -2366,23 +2327,8 @@ class MediaResolveMiddleware(InboundMiddleware):
     async def _download_and_cache(
         cls, adapter, *, fetch_url: str, kind: str,
         file_name: Optional[str] = None, log_tag: str = "",
-        resource_id: str = "",
     ) -> Optional[Tuple[str, str]]:
-        """Download a Yuanbao resource and cache locally. Returns ``(local_path, mime)`` or ``None``.
-
-        When *resource_id* is provided, an in-memory cache keyed by resourceId
-        is consulted first to skip redundant downloads of the same resource
-        within the TTL window.
-        """
-        if resource_id:
-            hit = cls._get_cached_resource(resource_id)
-            if hit is not None:
-                logger.debug(
-                    "[%s] resource cache hit: rid=%s path=%s",
-                    adapter.name, resource_id, hit[0],
-                )
-                return hit
-
+        """Download a Yuanbao resource and cache locally. Returns ``(local_path, mime)`` or ``None``."""
         try:
             file_bytes, content_type = await media_download_url(
                 fetch_url, max_size_mb=adapter.MEDIA_MAX_SIZE_MB,
@@ -2407,7 +2353,6 @@ class MediaResolveMiddleware(InboundMiddleware):
             mime = guess_mime_type(f"image{ext}")
             if not mime.startswith("image/"):
                 mime = content_type if content_type.startswith("image/") else "image/jpeg"
-            cls._put_cached_resource(resource_id, local_path, mime)
             return local_path, mime
 
         # kind == "file"
@@ -2423,7 +2368,6 @@ class MediaResolveMiddleware(InboundMiddleware):
             )
             return None
         mime = guess_mime_type(file_name) or content_type or "application/octet-stream"
-        cls._put_cached_resource(resource_id, local_path, mime)
         return local_path, mime
 
     @classmethod
@@ -2449,9 +2393,6 @@ class MediaResolveMiddleware(InboundMiddleware):
             if kind not in _RESOLVABLE_MEDIA_KINDS or not url:
                 continue
 
-            # Extract resourceId from the placeholder URL for cache dedup.
-            rid = ExtractContentMiddleware._parse_resource_id(url)
-
             try:
                 fetch_url = await cls._resolve_download_url(adapter, url)
             except Exception as exc:
@@ -2467,7 +2408,6 @@ class MediaResolveMiddleware(InboundMiddleware):
                 kind=kind,
                 file_name=str(ref.get("name") or "").strip() or None,
                 log_tag=f"placeholder_url={url[:80]}",
-                resource_id=rid,
             )
             if cached is None:
                 continue
@@ -2540,7 +2480,6 @@ class MediaResolveMiddleware(InboundMiddleware):
                 kind=kind,
                 file_name=filename or None,
                 log_tag=f"rid={rid}",
-                resource_id=rid,
             )
             if cached is None:
                 continue
@@ -2624,7 +2563,6 @@ class DispatchMiddleware(InboundMiddleware):
                         kind=kind,
                         file_name=filename or None,
                         log_tag=f"quote rid={rid}",
-                        resource_id=rid,
                     )
                     if cached is None:
                         continue
@@ -4691,11 +4629,6 @@ class YuanbaoAdapter(BasePlatformAdapter):
     # Abstract method implementations
     # ------------------------------------------------------------------
 
-    @property
-    def enforces_own_access_policy(self) -> bool:
-        """Yuanbao gates DM/group access at intake via dm_policy/group_policy."""
-        return True
-
     async def connect(self) -> bool:
         """Connect to Yuanbao WS gateway and authenticate.
 

gateway/run.py

@@ -751,7 +751,7 @@ _hermes_home = get_hermes_home()
 
 # Load environment variables from ~/.hermes/.env first.
 # User-managed env files should override stale shell exports on restart.
-from dotenv import load_dotenv  # noqa: F401  # backward-compat for tests that monkeypatch this symbol
+from dotenv import load_dotenv  # backward-compat for tests that monkeypatch this symbol
 from hermes_cli.env_loader import load_hermes_dotenv
 _env_path = _hermes_home / '.env'
 load_hermes_dotenv(hermes_home=_hermes_home, project_env=Path(__file__).resolve().parents[1] / '.env')
@@ -831,8 +831,6 @@ if _config_path.exists():
                 "docker_env": "TERMINAL_DOCKER_ENV",
                 "docker_mount_cwd_to_workspace": "TERMINAL_DOCKER_MOUNT_CWD_TO_WORKSPACE",
                 "docker_run_as_host_user": "TERMINAL_DOCKER_RUN_AS_HOST_USER",
-                "docker_persist_across_processes": "TERMINAL_DOCKER_PERSIST_ACROSS_PROCESSES",
-                "docker_orphan_reaper": "TERMINAL_DOCKER_ORPHAN_REAPER",
                 "sandbox_dir": "TERMINAL_SANDBOX_DIR",
                 "persistent_shell": "TERMINAL_PERSISTENT_SHELL",
             }
@@ -1807,34 +1805,7 @@ class GatewayRunner:
             ensure_installed(log_failures=False)
         except Exception:
             pass  # Non-fatal — fail-open at scan time if unavailable
-
-        # Startup heads-up (#30882): a gateway in manual approval mode with no
-        # automated risk assessor (tirith disabled AND no auxiliary.approval
-        # model) can only gate dangerous commands / execute_code scripts via
-        # live in-chat approval. With approval routing fixed, those actions now
-        # fail closed (block) rather than silently auto-running — surface that
-        # so operators knowingly enable tirith or configure auxiliary.approval
-        # for unattended gateways.
-        try:
-            from hermes_cli.config import load_config as _load_full_config
-            _appr_cfg = _load_full_config()
-            _appr_mode = str(
-                cfg_get(_appr_cfg, "approvals", "mode", default="manual") or "manual"
-            ).strip().lower()
-            _tirith_on = bool(cfg_get(_appr_cfg, "security", "tirith_enabled", default=True))
-            _aux_approval = cfg_get(_appr_cfg, "auxiliary", "approval", default=None)
-            if _appr_mode == "manual" and not _tirith_on and not _aux_approval:
-                logger.warning(
-                    "Gateway approvals.mode=manual with no automated risk "
-                    "assessor (security.tirith_enabled is false and "
-                    "auxiliary.approval is unset): dangerous commands and "
-                    "execute_code scripts will BLOCK until a human approves "
-                    "them in chat. Enable security.tirith_enabled or configure "
-                    "auxiliary.approval for unattended operation."
-                )
-        except Exception:
-            logger.debug("approvals.mode startup check skipped", exc_info=True)
-
+        
         # Initialize session database for session_search tool support
         self._session_db = None
         try:
@@ -2330,32 +2301,6 @@ class GatewayRunner:
             session_id=session_entry.session_id,
         )
 
-    def _sync_telegram_topic_binding(
-        self,
-        source: SessionSource,
-        session_entry,
-        *,
-        reason: str,
-    ) -> None:
-        """Update the topic binding to point at ``session_entry.session_id``.
-
-        Telegram topic lanes persist a (chat_id, thread_id) -> session_id row
-        so reopening a topic in a fresh process resumes the right Hermes
-        session. When compression rotates ``session_entry.session_id`` mid-turn,
-        the binding goes stale and the next inbound message in that topic
-        reloads the oversized parent transcript instead of the compressed
-        child, retriggering preflight compression — sometimes in a loop
-        (#20470, #29712, #33414).
-        """
-        if not self._is_telegram_topic_lane(source):
-            return
-        try:
-            self._record_telegram_topic_binding(source, session_entry)
-        except Exception:
-            logger.debug(
-                "telegram topic binding refresh failed (%s)", reason, exc_info=True,
-            )
-
     def _recover_telegram_topic_thread_id(
         self,
         source: SessionSource,
@@ -4212,7 +4157,6 @@ class GatewayRunner:
             adapter.set_fatal_error_handler(self._handle_adapter_fatal_error)
             adapter.set_session_store(self.session_store)
             adapter.set_busy_session_handler(self._handle_active_session_busy_message)
-            adapter.set_topic_recovery_fn(self._recover_telegram_topic_thread_id)
             adapter._busy_text_mode = self._busy_text_mode
             
             # Try to connect
@@ -5474,49 +5418,6 @@ class GatewayRunner:
             )
             stale_timeout_seconds = 0
 
-        # Read kanban.default_assignee — fallback profile for tasks
-        # created without an explicit assignee (e.g. via the dashboard).
-        # When set, the dispatcher applies it to unassigned ready tasks
-        # instead of skipping them indefinitely (#27145). Empty string
-        # (the schema default) means "no fallback, keep skipping" —
-        # backward-compatible with existing installs.
-        default_assignee = (kanban_cfg.get("default_assignee") or "").strip() or None
-        if default_assignee:
-            logger.info(
-                "kanban dispatcher: default_assignee=%r (unassigned ready tasks "
-                "will route to this profile)",
-                default_assignee,
-            )
-
-        # Read kanban.max_in_progress_per_profile — per-profile concurrency
-        # cap (#21582). When set, no single profile gets more than N
-        # workers running at once, even if the global max_in_progress
-        # would allow it. Prevents one profile's local model / API quota
-        # / browser pool from being overwhelmed by a fan-out.
-        raw_per_profile = kanban_cfg.get("max_in_progress_per_profile", None)
-        max_in_progress_per_profile = None
-        if raw_per_profile is not None:
-            try:
-                max_in_progress_per_profile = int(raw_per_profile)
-            except (TypeError, ValueError):
-                logger.warning(
-                    "kanban dispatcher: invalid kanban.max_in_progress_per_profile=%r; ignoring",
-                    raw_per_profile,
-                )
-                max_in_progress_per_profile = None
-            else:
-                if max_in_progress_per_profile < 1:
-                    logger.warning(
-                        "kanban dispatcher: kanban.max_in_progress_per_profile=%r is below 1; ignoring",
-                        raw_per_profile,
-                    )
-                    max_in_progress_per_profile = None
-                else:
-                    logger.info(
-                        "kanban dispatcher: max_in_progress_per_profile=%d",
-                        max_in_progress_per_profile,
-                    )
-
         # Initial delay so the gateway finishes wiring adapters before the
         # dispatcher spawns workers (those workers may hit gateway notify
         # subscriptions etc.). Matches the notifier watcher's delay.
@@ -5608,8 +5509,6 @@ class GatewayRunner:
                     max_in_progress=max_in_progress,
                     failure_limit=failure_limit,
                     stale_timeout_seconds=stale_timeout_seconds,
-                    default_assignee=default_assignee,
-                    max_in_progress_per_profile=max_in_progress_per_profile,
                 )
             except sqlite3.DatabaseError as exc:
                 if _is_corrupt_board_db_error(exc):
@@ -5918,7 +5817,6 @@ class GatewayRunner:
                     adapter.set_fatal_error_handler(self._handle_adapter_fatal_error)
                     adapter.set_session_store(self.session_store)
                     adapter.set_busy_session_handler(self._handle_active_session_busy_message)
-                    adapter.set_topic_recovery_fn(self._recover_telegram_topic_thread_id)
                     adapter._busy_text_mode = self._busy_text_mode
 
                     success = await self._connect_adapter_with_timeout(adapter, platform)
@@ -6365,6 +6263,29 @@ class GatewayRunner:
                     # plugin adapters don't need a custom factory signature.
                     if hasattr(adapter, "gateway_runner"):
                         adapter.gateway_runner = self
+                    # ── Telegram: notification mode from config ──
+                    # Applied here (not in the adapter factory) because it
+                    # reads gateway-local config that only the gateway runner
+                    # has access to.
+                    if platform.value == "telegram":
+                        _notify_mode = os.getenv("HERMES_TELEGRAM_NOTIFICATIONS", "")
+                        if not _notify_mode:
+                            try:
+                                _gw_cfg = _load_gateway_config()
+                                _raw = cfg_get(_gw_cfg, "display", "platforms", "telegram", "notifications")
+                                if _raw not in {None, ""}:
+                                    _notify_mode = str(_raw).strip().lower()
+                            except Exception:
+                                pass
+                        _notify_mode = _notify_mode or "important"
+                        if _notify_mode not in {"all", "important"}:
+                            logger.warning(
+                                "Unknown telegram notifications mode '%s', "
+                                "defaulting to 'important' (valid: all, important)",
+                                _notify_mode,
+                            )
+                            _notify_mode = "important"
+                        adapter._notifications_mode = _notify_mode
                     return adapter
                 # Registered but failed to instantiate — don't silently fall
                 # through to built-ins (there are none for plugin platforms).
@@ -6378,49 +6299,13 @@ class GatewayRunner:
             logger.debug("Platform registry lookup for '%s' failed: %s", platform.value, e)
         # Fall through to built-in adapters below
 
-        if platform == Platform.TELEGRAM:
-            from gateway.platforms.telegram import TelegramAdapter, check_telegram_requirements
-            if not check_telegram_requirements():
-                logger.warning("Telegram: python-telegram-bot not installed")
-                return None
-            adapter = TelegramAdapter(config)
-            # Apply Telegram notification mode from config.  Controls whether
-            # intermediate messages (tool progress, streaming, status) trigger
-            # push notifications.  Supports ENV override for quick testing.
-            _notify_mode = os.getenv("HERMES_TELEGRAM_NOTIFICATIONS", "")
-            if not _notify_mode:
-                try:
-                    _gw_cfg = _load_gateway_config()
-                    _raw = cfg_get(_gw_cfg, "display", "platforms", "telegram", "notifications")
-                    if _raw not in {None, ""}:
-                        _notify_mode = str(_raw).strip().lower()
-                except Exception:
-                    pass
-            _notify_mode = _notify_mode or "important"
-            if _notify_mode not in {"all", "important"}:
-                logger.warning(
-                    "Unknown telegram notifications mode '%s', "
-                    "defaulting to 'important' (valid: all, important)",
-                    _notify_mode,
-                )
-                _notify_mode = "important"
-            adapter._notifications_mode = _notify_mode
-            return adapter
-        
-        elif platform == Platform.WHATSAPP:
+        if platform == Platform.WHATSAPP:
             from gateway.platforms.whatsapp import WhatsAppAdapter, check_whatsapp_requirements
             if not check_whatsapp_requirements():
                 logger.warning("WhatsApp: Node.js not installed or bridge not configured")
                 return None
             return WhatsAppAdapter(config)
         
-        elif platform == Platform.SLACK:
-            from gateway.platforms.slack import SlackAdapter, check_slack_requirements
-            if not check_slack_requirements():
-                logger.warning("Slack: slack-bolt not installed. Run: pip install 'hermes-agent[slack]'")
-                return None
-            return SlackAdapter(config)
-
         elif platform == Platform.SIGNAL:
             from gateway.platforms.signal import SignalAdapter, check_signal_requirements
             if not check_signal_requirements():
@@ -6449,20 +6334,6 @@ class GatewayRunner:
                 return None
             return SmsAdapter(config)
 
-        elif platform == Platform.DINGTALK:
-            from gateway.platforms.dingtalk import DingTalkAdapter, check_dingtalk_requirements
-            if not check_dingtalk_requirements():
-                logger.warning("DingTalk: dingtalk-stream not installed or DINGTALK_CLIENT_ID/SECRET not set")
-                return None
-            return DingTalkAdapter(config)
-
-        elif platform == Platform.FEISHU:
-            from gateway.platforms.feishu import FeishuAdapter, check_feishu_requirements
-            if not check_feishu_requirements():
-                logger.warning("Feishu: lark-oapi not installed or FEISHU_APP_ID/SECRET not set")
-                return None
-            return FeishuAdapter(config)
-
         elif platform == Platform.WECOM_CALLBACK:
             from gateway.platforms.wecom_callback import (
                 WecomCallbackAdapter,
@@ -6487,13 +6358,6 @@ class GatewayRunner:
                 return None
             return WeixinAdapter(config)
 
-        elif platform == Platform.MATRIX:
-            from gateway.platforms.matrix import MatrixAdapter, check_matrix_requirements
-            if not check_matrix_requirements():
-                logger.warning("Matrix: mautrix not installed or credentials not set. Run: pip install 'mautrix[encryption]'")
-                return None
-            return MatrixAdapter(config)
-
         elif platform == Platform.API_SERVER:
             from gateway.platforms.api_server import APIServerAdapter, check_api_server_requirements
             if not check_api_server_requirements():
@@ -6542,31 +6406,6 @@ class GatewayRunner:
             return YuanbaoAdapter(config)
 
         return None
-
-    def _adapter_enforces_own_access_policy(self, platform: Optional[Platform]) -> bool:
-        """Whether the adapter for *platform* gates access at intake itself.
-
-        Mirrors ``BasePlatformAdapter.enforces_own_access_policy``. Adapters
-        such as WeCom, Weixin, Yuanbao, and QQBot evaluate their documented
-        ``dm_policy`` / ``group_policy`` / ``allow_from`` config before a
-        message is dispatched to the gateway, so a message that reaches
-        ``_is_user_authorized`` has already been authorized by the adapter.
-        Defaults to ``False`` when the adapter is unknown or doesn't expose
-        the flag.
-        """
-        if not platform:
-            return False
-        # Some test helpers build a bare GatewayRunner via object.__new__ and
-        # never set ``adapters``; treat a missing/empty map as "no adapter"
-        # rather than raising (see pitfalls.md #17).
-        adapters = getattr(self, "adapters", None)
-        if not adapters:
-            return False
-        adapter = adapters.get(platform)
-        if adapter is None:
-            return False
-        return bool(getattr(adapter, "enforces_own_access_policy", False))
-
     def _is_user_authorized(self, source: SessionSource) -> bool:
         """
         Check if a user is authorized to use the bot.
@@ -6706,15 +6545,6 @@ class GatewayRunner:
         global_allowlist = os.getenv("GATEWAY_ALLOWED_USERS", "").strip()
 
         if not platform_allowlist and not group_user_allowlist and not group_chat_allowlist and not global_allowlist:
-            # No env allowlists configured. Adapters that own their own
-            # config-driven access policy (dm_policy / group_policy /
-            # allow_from / group_allow_from) already gated this message at
-            # intake — it would not have reached the gateway otherwise — so
-            # honor that decision instead of falling through to the
-            # env-only default-deny below, which would silently break
-            # `dm_policy: open` and config-only allowlists. (#34515)
-            if self._adapter_enforces_own_access_policy(source.platform):
-                return True
             # No allowlists configured -- check global allow-all flag
             return os.getenv("GATEWAY_ALLOW_ALL_USERS", "").lower() in {"true", "1", "yes"}
 
@@ -6822,20 +6652,6 @@ class GatewayRunner:
             if config.unauthorized_dm_behavior != "pair":  # non-default → explicit override
                 return config.unauthorized_dm_behavior
 
-        # Config-driven dm_policy (WeCom / Weixin / Yuanbao / QQBot). An
-        # allowlist or disabled DM policy means the operator restricted access,
-        # so unauthorized DMs should be dropped silently rather than answered
-        # with a pairing code. An explicit pairing policy opts back into codes.
-        if platform and config and hasattr(config, "platforms"):
-            platform_cfg = config.platforms.get(platform)
-            extra = getattr(platform_cfg, "extra", None) if platform_cfg else None
-            if isinstance(extra, dict):
-                dm_policy = str(extra.get("dm_policy") or "").strip().lower()
-                if dm_policy == "pairing":
-                    return "pair"
-                if dm_policy in {"allowlist", "disabled"}:
-                    return "ignore"
-
         # No explicit override.  Fall back to allowlist-aware default:
         # if any allowlist is configured for this platform, silently drop
         # unauthorized messages instead of sending pairing codes.
@@ -8380,28 +8196,6 @@ class GatewayRunner:
                 binding = None
             if binding:
                 bound_session_id = str(binding.get("session_id") or "")
-                # Heal bindings that point at a pre-compression parent: walk
-                # the compression-continuation chain forward to its tip so the
-                # next message resumes the compressed child instead of
-                # reloading the oversized parent transcript (#20470/#29712/
-                # #33414). Returns the input unchanged when the session isn't
-                # a compression parent, so this is cheap and safe.
-                if bound_session_id and self._session_db is not None:
-                    try:
-                        canonical_session_id = self._session_db.get_compression_tip(
-                            bound_session_id,
-                        )
-                    except Exception:
-                        logger.debug(
-                            "compression-tip lookup failed for %s",
-                            bound_session_id, exc_info=True,
-                        )
-                        canonical_session_id = bound_session_id
-                    if (
-                        canonical_session_id
-                        and canonical_session_id != bound_session_id
-                    ):
-                        bound_session_id = canonical_session_id
                 if bound_session_id and bound_session_id != session_entry.session_id:
                     # Route the override through SessionStore so the session_key
                     # → session_id mapping is persisted to disk and the previous
@@ -8411,15 +8205,6 @@ class GatewayRunner:
                     switched = self.session_store.switch_session(session_key, bound_session_id)
                     if switched is not None:
                         session_entry = switched
-                # If the stored binding pointed at a parent, rewrite it to the
-                # canonical descendant now that we've followed the chain.
-                if (
-                    bound_session_id
-                    and bound_session_id != str(binding.get("session_id") or "")
-                ):
-                    self._sync_telegram_topic_binding(
-                        source, session_entry, reason="compression-tip-walk",
-                    )
             else:
                 try:
                     self._record_telegram_topic_binding(source, session_entry)
@@ -8796,10 +8581,6 @@ class GatewayRunner:
                                     if _hyg_new_sid != session_entry.session_id:
                                         session_entry.session_id = _hyg_new_sid
                                         self.session_store._save()
-                                        self._sync_telegram_topic_binding(
-                                            source, session_entry,
-                                            reason="hygiene-compression",
-                                        )
 
                                     self.session_store.rewrite_transcript(
                                         session_entry.session_id, _compressed
@@ -9065,9 +8846,6 @@ class GatewayRunner:
             if agent_result.get("session_id") and agent_result["session_id"] != session_entry.session_id:
                 session_entry.session_id = agent_result["session_id"]
                 self.session_store._save()
-                self._sync_telegram_topic_binding(
-                    source, session_entry, reason="agent-result-compression",
-                )
 
             # Prepend reasoning/thinking if display is enabled (per-platform)
             try:
@@ -11650,7 +11428,12 @@ class GatewayRunner:
         audio_path = None
         actual_path = None
         try:
-            from tools.tts_tool import text_to_speech_tool, _strip_markdown_for_tts
+            from agent.plugin_registries import registries
+            _tts_entry = registries.get_tool_provider("tts")
+            if _tts_entry is None:
+                return
+            text_to_speech_tool = _tts_entry.tool_functions["text_to_speech_tool"]
+            _strip_markdown_for_tts = _tts_entry.tool_functions["_strip_markdown_for_tts"]
 
             tts_text = _strip_markdown_for_tts(text[:4000])
             if not tts_text:
@@ -12512,9 +12295,6 @@ class GatewayRunner:
                 if new_session_id != session_entry.session_id:
                     session_entry.session_id = new_session_id
                     self.session_store._save()
-                    self._sync_telegram_topic_binding(
-                        source, session_entry, reason="compress-command",
-                    )
 
                 self.session_store.rewrite_transcript(new_session_id, compressed)
                 # Reset stored token count — transcript changed, old value is stale
@@ -14941,9 +14721,32 @@ class GatewayRunner:
                 return f"{prefix}\n\n{user_text}"
             return prefix
 
-        from tools.transcription_tools import transcribe_audio
-
+        from agent.plugin_registries import registries
+        _stt_entry = registries.get_tool_provider("stt")
         enriched_parts = []
+        if _stt_entry is None or "transcribe_audio" not in _stt_entry.tool_functions:
+            # No STT plugin registered — treat each audio path the same way
+            # as a "No STT provider" transcription failure.
+            for path in audio_paths:
+                abs_path = os.path.abspath(path)
+                duration_str = await _probe_audio_duration(abs_path)
+                if duration_str:
+                    enriched_parts.append(
+                        f"[The user sent a voice message: {abs_path} (duration: {duration_str})]"
+                    )
+                else:
+                    enriched_parts.append(f"[The user sent a voice message: {abs_path}]")
+            if not enriched_parts:
+                return user_text
+            prefix = "\n\n".join(enriched_parts)
+            _placeholder = "(The user sent a message with no text content)"
+            if user_text and user_text.strip() == _placeholder:
+                return prefix
+            if user_text:
+                return f"{prefix}\n\n{user_text}"
+            return prefix
+        transcribe_audio = _stt_entry.tool_functions["transcribe_audio"]
+
         for path in audio_paths:
             try:
                 logger.debug("Transcribing user voice: %s", path)

gateway/runtime_footer.py

@@ -26,6 +26,7 @@ piecemeal, the footer is sent as a separate trailing message via
 from __future__ import annotations
 
 import os
+from pathlib import Path
 from typing import Any, Iterable, Optional
 
 _DEFAULT_FIELDS: tuple[str, ...] = ("model", "context_pct", "cwd")

hermes_cli/__init__.py

@@ -14,8 +14,8 @@ Provides subcommands for:
 import os
 import sys
 
-__version__ = "0.15.1"
-__release_date__ = "2026.5.29"
+__version__ = "0.15.0"
+__release_date__ = "2026.5.28"
 
 
 def _ensure_utf8():

hermes_cli/_subprocess_compat.py

@@ -27,9 +27,11 @@ guarantee.
 
 from __future__ import annotations
 
+import os
 import shutil
+import subprocess
 import sys
-from typing import Sequence
+from typing import Optional, Sequence
 
 __all__ = [
     "IS_WINDOWS",

hermes_cli/auth_commands.py

@@ -221,9 +221,12 @@ def auth_add_command(args) -> None:
         return
 
     if provider == "anthropic":
-        from agent import anthropic_adapter as anthropic_mod
-
-        creds = anthropic_mod.run_hermes_oauth_login_pure()
+        from agent.plugin_registries import registries
+        _anthropic_ns = registries.get_provider_namespace("anthropic")
+        run_hermes_oauth_login_pure = _anthropic_ns.get("run_hermes_oauth_login_pure")
+        if not run_hermes_oauth_login_pure:
+            raise SystemExit("Anthropic plugin not loaded — cannot run OAuth login.")
+        creds = run_hermes_oauth_login_pure()
         if not creds:
             raise SystemExit("Anthropic OAuth login did not return credentials.")
         label = (getattr(args, "label", None) or "").strip() or label_from_token(
@@ -272,6 +275,9 @@ def auth_add_command(args) -> None:
                 print("Rehydrating Nous session from shared credentials...")
                 rehydrated = auth_mod._try_import_shared_nous_state(
                     timeout_seconds=getattr(args, "timeout", None) or 15.0,
+                    min_key_ttl_seconds=max(
+                        60, int(getattr(args, "min_key_ttl_seconds", 5 * 60))
+                    ),
                 )
                 if rehydrated is not None:
                     custom_label = (getattr(args, "label", None) or "").strip() or None
@@ -294,6 +300,7 @@ def auth_add_command(args) -> None:
             timeout_seconds=getattr(args, "timeout", None) or 15.0,
             insecure=bool(getattr(args, "insecure", False)),
             ca_bundle=getattr(args, "ca_bundle", None),
+            min_key_ttl_seconds=max(60, int(getattr(args, "min_key_ttl_seconds", 5 * 60))),
         )
         # Honor `--label <name>` so nous matches other providers' UX.  The
         # helper embeds this into providers.nous so that label_from_token
@@ -545,8 +552,12 @@ def _interactive_auth() -> None:
 
     # Show AWS Bedrock credential status (not in the pool — uses boto3 chain)
     try:
-        from agent.bedrock_adapter import has_aws_credentials, resolve_aws_auth_env_var, resolve_bedrock_region
-        if has_aws_credentials():
+        from agent.plugin_registries import registries
+        _bedrock = registries.get_provider_namespace("bedrock")
+        has_aws_credentials = _bedrock.get("has_aws_credentials")
+        resolve_aws_auth_env_var = _bedrock.get("resolve_aws_auth_env_var")
+        resolve_bedrock_region = _bedrock.get("resolve_bedrock_region")
+        if has_aws_credentials and has_aws_credentials():
             auth_source = resolve_aws_auth_env_var() or "unknown"
             region = resolve_bedrock_region()
             print(f"bedrock (AWS SDK credential chain):")
@@ -573,12 +584,12 @@ def _interactive_auth() -> None:
             _cfg_provider = str(_model_cfg.get("provider") or "").strip().lower()
             _cfg_auth_mode = str(_model_cfg.get("auth_mode") or "").strip().lower()
             if _cfg_provider == "azure-foundry" and _cfg_auth_mode == "entra_id":
-                from agent.azure_identity_adapter import (
-                    EntraIdentityConfig,
-                    SCOPE_AI_AZURE_DEFAULT,
-                    describe_active_credential,
-                    has_azure_identity_installed,
-                )
+                from agent.plugin_registries import registries
+                _azure = registries.get_provider_namespace("azure")
+                EntraIdentityConfig = _azure.get("EntraIdentityConfig")
+                SCOPE_AI_AZURE_DEFAULT = _azure.get("SCOPE_AI_AZURE_DEFAULT")
+                describe_active_credential = _azure.get("describe_active_credential")
+                has_azure_identity_installed = _azure.get("has_azure_identity_installed")
                 _base_url = str(_model_cfg.get("base_url") or "").strip()
                 _entra = _model_cfg.get("entra") or {}
                 if not isinstance(_entra, dict):

hermes_cli/banner.py

@@ -50,6 +50,17 @@ def _skin_color(key: str, fallback: str) -> str:
         return get_active_skin().get_color(key, fallback)
     except Exception:
         return fallback
+
+
+def _skin_branding(key: str, fallback: str) -> str:
+    """Get a branding string from the active skin, or return fallback."""
+    try:
+        from hermes_cli.skin_engine import get_active_skin
+        return get_active_skin().get_branding(key, fallback)
+    except Exception:
+        return fallback
+
+
 # =========================================================================
 # ASCII Art & Branding
 # =========================================================================

hermes_cli/bundles.py

@@ -15,7 +15,7 @@ Subcommands:
 from __future__ import annotations
 
 import sys
-from typing import List
+from typing import List, Optional
 
 from rich.console import Console
 from rich.table import Table

hermes_cli/checkpoints.py

@@ -25,7 +25,7 @@ import argparse
 import time
 from datetime import datetime
 from pathlib import Path
-from typing import Any
+from typing import Any, Dict
 
 
 def _fmt_bytes(n: int) -> str:

hermes_cli/config.py

@@ -669,27 +669,6 @@ DEFAULT_CONFIG = {
         # (force on/off for all models), or a list of model-name substrings
         # to match (e.g. ["gpt", "codex", "gemini", "qwen"]).
         "tool_use_enforcement": "auto",
-        # Universal "finish the job" guidance — short prompt block applied to
-        # all models that targets two cross-family failure modes: (1) stopping
-        # after a stub instead of finishing the artifact, (2) fabricating
-        # plausible-looking output when a real path is blocked.  Costs ~80
-        # tokens in the cached system prompt.  Set False to disable globally.
-        "task_completion_guidance": True,
-        # Local-environment toolchain probe — surfaces Python/pip/uv/PEP-668
-        # state in the system prompt when something non-default is detected
-        # (e.g. python3 has no pip module, pip→python version mismatch, PEP
-        # 668 enforcement without uv).  Costs zero tokens when the env is
-        # clean (probe emits nothing).  Skipped for remote terminal backends
-        # (docker/modal/ssh — they have their own probe).  Set False to
-        # disable entirely.
-        "environment_probe": True,
-        # Embedder-supplied environment description appended to the system
-        # prompt's environment-hints block. Lets a host that wraps Hermes
-        # (sandbox runner, managed platform) explain the runtime environment
-        # — proxy, credential handling, mount layout — without editing the
-        # identity slot (SOUL.md). Empty by default. The HERMES_ENVIRONMENT_HINT
-        # env var overrides this (build-time/container mechanism).
-        "environment_hint": "",
         # Staged inactivity warning: send a warning to the user at this
         # threshold before escalating to a full timeout.  The warning fires
         # once per run and does not interrupt the agent.  0 = disable warning.
@@ -857,11 +836,6 @@ DEFAULT_CONFIG = {
             "session_key": "",
             # Rehydrate tab_id from Camofox before creating a new tab.
             "adopt_existing_tab": False,
-            # Docker Camofox opens page URLs from inside the container. Enable
-            # this to rewrite loopback page URLs (localhost/127.0.0.1/::1) to a
-            # host alias while leaving CAMOFOX_URL itself unchanged.
-            "rewrite_loopback_urls": False,
-            "loopback_host_alias": "host.docker.internal",
         },
     },
 
@@ -1752,15 +1726,6 @@ DEFAULT_CONFIG = {
         # assignee to any installed profile. When unset, falls back to the
         # default profile. A task never ends up with assignee=None.
         "default_assignee": "",
-        # Per-profile concurrency cap (#21582). When set to a positive int,
-        # no single profile can have more than N workers running at once,
-        # even if the global max_in_progress / max_spawn caps would allow
-        # it. Tasks blocked this way defer to the next dispatcher tick.
-        # Unset (None) means "no per-profile cap" — backward-compatible
-        # with existing installs. Useful for fan-out workflows that would
-        # otherwise saturate one profile's local model / API quota /
-        # browser pool while leaving other profiles idle.
-        "max_in_progress_per_profile": None,
         # When true, the kanban dispatcher auto-runs the decomposer on
         # tasks that land in Triage (every dispatcher tick). When false,
         # decomposition is manual via `hermes kanban decompose <id>` or
@@ -1792,38 +1757,6 @@ DEFAULT_CONFIG = {
         "mode": "project",
     },
 
-    # Tool Search (progressive disclosure for large tool surfaces).
-    # When the model is connected to many MCP servers or non-core plugin
-    # tools, their JSON schemas can consume a substantial fraction of the
-    # context window on every turn. When enabled, those tools are replaced
-    # in the model-facing tools array with three bridge tools —
-    # tool_search / tool_describe / tool_call — and surfaced on demand.
-    #
-    # Core Hermes tools (terminal, read_file, write_file, patch,
-    # search_files, todo, memory, browser_*, etc.) are NEVER deferred.
-    # See tools/tool_search.py for full design notes and the
-    # openclaw-tool-search-report PDF in this PR for the rationale.
-    "tools": {
-        "tool_search": {
-            # "auto" (default) — activate only when deferrable tool schemas
-            #   exceed ``threshold_pct`` of the active model's context length,
-            #   so small toolsets pay no overhead.
-            # "on"  — always activate when there is at least one deferrable
-            #   tool. Use when you have many MCP servers and want maximum
-            #   token reduction unconditionally.
-            # "off" — disable entirely. Tools-array assembly is a pass-through.
-            "enabled": "auto",
-            # Percentage of context length at which "auto" mode kicks in.
-            # 10 matches the Claude Code default. Range 0..100.
-            "threshold_pct": 10,
-            # When the model calls tool_search without a ``limit`` argument,
-            # how many hits to return. Range 1..max_search_limit.
-            "search_default_limit": 5,
-            # Hard upper bound the model can request via ``limit``. Range 1..50.
-            "max_search_limit": 20,
-        },
-    },
-
     # Logging — controls file logging to ~/.hermes/logs/.
     # agent.log captures INFO+ (all agent activity); errors.log captures WARNING+.
     "logging": {
@@ -5618,8 +5551,6 @@ def set_config_value(key: str, value: str):
         "terminal.daytona_image": "TERMINAL_DAYTONA_IMAGE",
         "terminal.docker_mount_cwd_to_workspace": "TERMINAL_DOCKER_MOUNT_CWD_TO_WORKSPACE",
         "terminal.docker_run_as_host_user": "TERMINAL_DOCKER_RUN_AS_HOST_USER",
-        "terminal.docker_persist_across_processes": "TERMINAL_DOCKER_PERSIST_ACROSS_PROCESSES",
-        "terminal.docker_orphan_reaper": "TERMINAL_DOCKER_ORPHAN_REAPER",
         "terminal.docker_env": "TERMINAL_DOCKER_ENV",
         # terminal.cwd intentionally excluded — CLI resolves at runtime,
         # gateway bridges it in gateway/run.py. Persisting to .env causes

hermes_cli/dashboard_auth/middleware.py

@@ -26,15 +26,10 @@ from hermes_cli.dashboard_auth import list_providers
 from hermes_cli.dashboard_auth.audit import AuditEvent, audit_log
 from hermes_cli.dashboard_auth.base import ProviderError
 from hermes_cli.dashboard_auth.cookies import read_session_cookies
-from hermes_cli.dashboard_auth.public_paths import PUBLIC_API_PATHS
 
 _log = logging.getLogger(__name__)
 
-# Prefixes that bypass the auth gate. Match via ``path == prefix`` or
-# ``path.startswith(prefix)`` — so ``/assets/`` (with trailing slash)
-# matches ``/assets/foo.css`` but not ``/assetsleak``. Auth-bootstrap
-# (login page, OAuth round trip, provider listing) and static asset
-# mounts go here.
+# Paths that bypass the auth gate. Order matters: prefix match.
 _GATE_PUBLIC_PREFIXES: tuple[str, ...] = (
     "/auth/login",
     "/auth/callback",
@@ -50,20 +45,6 @@ _GATE_PUBLIC_PREFIXES: tuple[str, ...] = (
 
 
 def _path_is_public(path: str) -> bool:
-    """True if ``path`` bypasses the OAuth auth gate.
-
-    Two sources of public-ness:
-
-    * :data:`PUBLIC_API_PATHS` — the shared ``/api/*`` allowlist that
-      the legacy ``_SESSION_TOKEN`` middleware also honours. Matched
-      exactly (no prefix expansion) so adding ``/api/status`` doesn't
-      accidentally expose ``/api/status/secret-extension``.
-    * :data:`_GATE_PUBLIC_PREFIXES` — auth-bootstrap routes and static
-      mounts. Prefix-matched so ``/assets/foo.css`` lights up via
-      ``/assets/``.
-    """
-    if path in PUBLIC_API_PATHS:
-        return True
     return any(
         path == prefix or path.startswith(prefix)
         for prefix in _GATE_PUBLIC_PREFIXES

hermes_cli/dashboard_auth/public_paths.py

@@ -1,49 +0,0 @@
-"""Shared allowlist of ``/api/*`` paths that bypass dashboard auth.
-
-Two middlewares enforce dashboard auth and previously kept independent
-copies of this list:
-
-* ``hermes_cli.web_server.auth_middleware`` — loopback / ``--insecure``
-  mode, gates on the ephemeral ``_SESSION_TOKEN``.
-* ``hermes_cli.dashboard_auth.middleware.gated_auth_middleware`` —
-  non-loopback mode, gates on the OAuth session cookie.
-
-When the lists drifted, ``/api/status`` ended up public under the legacy
-gate but 401'd under the OAuth gate. That broke the portal's wildcard
-liveness probe (``nous-account-service`` ``fly-provider.ts``
-``getInstanceRuntimeStatus``), which fetches ``/api/status`` without a
-cookie as its sole signal of "agent dashboard is alive": every healthy
-wildcard-subdomain agent surfaced as STARTING/down in the portal UI even
-though the dashboard was serving correctly.
-
-Centralising the allowlist here so both middlewares import the same
-frozenset prevents the next drift. Keep this list minimal — only truly
-non-sensitive, read-only endpoints belong here. As a sanity check, every
-entry should be safe to expose to:
-
-  * external uptime probes (Pingdom, Better Stack, NAS),
-  * the dashboard SPA before the user has logged in,
-  * anyone who happens to ``curl`` the hostname.
-
-If a new endpoint doesn't pass all three tests, it should be gated and
-the SPA should bootstrap it after login instead.
-"""
-from __future__ import annotations
-
-PUBLIC_API_PATHS: frozenset[str] = frozenset({
-    # Liveness probe target. Returns version, gateway state, active
-    # session count, and the dashboard auth-gate shape. No bodies, no
-    # session content, no secrets. Documented as the portal's wildcard
-    # liveness probe in
-    # ``docs/agent-dashboard-public-url-contract.md`` (NAS side).
-    "/api/status",
-    # Read-only config-defaults / schema feeds for the SPA's Config page.
-    "/api/config/defaults",
-    "/api/config/schema",
-    # Read-only model metadata (context windows, etc.) — same shape as
-    # provider catalogs already exposed on the public internet.
-    "/api/model/info",
-    # Read-only theme + plugin manifests for the dashboard skin engine.
-    "/api/dashboard/themes",
-    "/api/dashboard/plugins",
-})

hermes_cli/debug.py

@@ -17,6 +17,8 @@ import logging
 import re
 import sys
 import time
+import urllib.error
+import urllib.parse
 import urllib.request
 from dataclasses import dataclass
 from pathlib import Path
@@ -258,6 +260,15 @@ def _schedule_auto_delete(urls: list[str], delay_seconds: int = _AUTO_DELETE_SEC
     _record_pending(urls, delay_seconds=delay_seconds)
 
 
+def _delete_hint(url: str) -> str:
+    """Return a one-liner delete command for the given paste URL."""
+    paste_id = _extract_paste_id(url)
+    if paste_id:
+        return f"hermes debug delete {url}"
+    # dpaste.com — no API delete, expires on its own.
+    return "(auto-expires per dpaste.com policy)"
+
+
 def _upload_paste_rs(content: str) -> str:
     """Upload to paste.rs.  Returns the paste URL.
 

hermes_cli/doctor.py

@@ -8,6 +8,7 @@ import os
 import sys
 import subprocess
 import shutil
+import importlib.util
 from pathlib import Path
 
 from hermes_cli.config import get_project_root, get_hermes_home, get_env_path
@@ -27,7 +28,6 @@ from hermes_cli.models import _HERMES_USER_AGENT
 from hermes_constants import OPENROUTER_MODELS_URL
 from utils import base_url_host_matches
 
-
 _PROVIDER_ENV_HINTS = (
     "OPENROUTER_API_KEY",
     "OPENAI_API_KEY",
@@ -53,14 +53,11 @@ _PROVIDER_ENV_HINTS = (
     "TOKENHUB_API_KEY",
 )
 
-
 from hermes_constants import is_termux as _is_termux
 
-
 def _python_install_cmd() -> str:
     return "python -m pip install" if _is_termux() else "uv pip install"
 
-
 def _system_package_install_cmd(pkg: str) -> str:
     if _is_termux():
         return f"pkg install {pkg}"
@@ -68,7 +65,6 @@ def _system_package_install_cmd(pkg: str) -> str:
         return f"brew install {pkg}"
     return f"sudo apt install {pkg}"
 
-
 def _safe_which(cmd: str) -> str | None:
     """shutil.which wrapper resilient to platform monkeypatching in tests."""
     try:
@@ -76,7 +72,6 @@ def _safe_which(cmd: str) -> str | None:
     except Exception:
         return None
 
-
 def _termux_browser_setup_steps(node_installed: bool) -> list[str]:
     steps: list[str] = []
     step = 1
@@ -87,7 +82,6 @@ def _termux_browser_setup_steps(node_installed: bool) -> list[str]:
     steps.append(f"{step + 1}) agent-browser install")
     return steps
 
-
 def _termux_install_all_fallback_notes() -> list[str]:
     return [
         "Termux install profile: use .[termux-all] for broad compatibility (installer default on Termux).",
@@ -96,12 +90,10 @@ def _termux_install_all_fallback_notes() -> list[str]:
         "STT fallback: use Groq Whisper (set GROQ_API_KEY) or OpenAI Whisper (set VOICE_TOOLS_OPENAI_KEY).",
     ]
 
-
 def _has_provider_env_config(content: str) -> bool:
     """Return True when ~/.hermes/.env contains provider auth/base URL settings."""
     return any(key in content for key in _PROVIDER_ENV_HINTS)
 
-
 def _honcho_is_configured_for_doctor() -> bool:
     """Return True when Honcho is configured, even if this process has no active session."""
     try:
@@ -112,7 +104,6 @@ def _honcho_is_configured_for_doctor() -> bool:
     except Exception:
         return False
 
-
 def _is_kanban_worker_env_gate(item: dict) -> bool:
     """Return True when Kanban is unavailable only because this is not a worker process."""
     if item.get("name") != "kanban":
@@ -123,14 +114,12 @@ def _is_kanban_worker_env_gate(item: dict) -> bool:
     tools = item.get("tools") or []
     return bool(tools) and all(str(tool).startswith("kanban_") for tool in tools)
 
-
 def _doctor_tool_availability_detail(toolset: str) -> str:
     """Optional explanatory suffix for toolsets whose doctor status needs context."""
     if toolset == "kanban" and not os.environ.get("HERMES_KANBAN_TASK"):
         return "(runtime-gated; loaded only for dispatcher-spawned workers)"
     return ""
 
-
 def _apply_doctor_tool_availability_overrides(available: list[str], unavailable: list[dict]) -> tuple[list[str], list[dict]]:
     """Adjust runtime-gated tool availability for doctor diagnostics."""
     updated_available = list(available)
@@ -148,7 +137,6 @@ def _apply_doctor_tool_availability_overrides(available: list[str], unavailable:
         updated_unavailable.append(item)
     return updated_available, updated_unavailable
 
-
 def _has_healthy_oauth_fallback_for_apikey_provider(provider_label: str) -> bool:
     """Return True when a direct API-key probe failure is non-blocking.
 
@@ -178,7 +166,6 @@ def _has_healthy_oauth_fallback_for_apikey_provider(provider_label: str) -> bool
             return False
     return False
 
-
 def check_ok(text: str, detail: str = ""):
     print(f"  {color('✓', Colors.GREEN)} {text}" + (f" {color(detail, Colors.DIM)}" if detail else ""))
 
@@ -191,19 +178,16 @@ def check_fail(text: str, detail: str = ""):
 def check_info(text: str):
     print(f"    {color('→', Colors.CYAN)} {text}")
 
-
 def _section(title: str) -> None:
     """Print a doctor section banner: blank line + bold cyan ◆ title."""
     print()
     print(color(f"◆ {title}", Colors.CYAN, Colors.BOLD))
 
-
 def _fail_and_issue(text: str, detail: str, fix: str, issues: list[str]) -> None:
     """Emit a check_fail and append the corresponding fix instruction."""
     check_fail(text, detail)
     issues.append(fix)
 
-
 def _check_s6_supervision(issues: list[str]) -> None:
     """Inside a container under our s6 /init, surface what s6 sees.
 
@@ -251,7 +235,6 @@ def _check_s6_supervision(issues: list[str]) -> None:
         + (f" ({', '.join(sorted(profiles))})" if len(profiles) <= 8 else "")
     )
 
-
 def _check_gateway_service_linger(issues: list[str]) -> None:
     """Warn when a systemd user gateway service will stop after logout.
 
@@ -295,10 +278,8 @@ def _check_gateway_service_linger(issues: list[str]) -> None:
     else:
         check_warn("Could not verify systemd linger", f"({linger_detail})")
 
-
 _APIKEY_PROVIDERS_CACHE: list | None = None
 
-
 def _build_apikey_providers_list() -> list:
     """Build the API-key provider health-check list once and cache it.
 
@@ -390,7 +371,6 @@ def _build_apikey_providers_list() -> list:
         pass
     return _static
 
-
 def run_doctor(args):
     """Run diagnostic checks."""
     should_fix = getattr(args, 'fix', False)
@@ -1474,12 +1454,15 @@ def run_doctor(args):
             return _ConnectivityResult("Anthropic API", [], [])
         try:
             import httpx
-            from agent.anthropic_adapter import (
-                _is_oauth_token,
-                _COMMON_BETAS,
-                _OAUTH_ONLY_BETAS,
-                _CONTEXT_1M_BETA,
-            )
+            from agent.plugin_registries import registries
+            _anthropic_ns = registries.get_provider_namespace("anthropic")
+            _is_oauth_token = _anthropic_ns.get("_is_oauth_token")
+            # _COMMON_BETAS and _CONTEXT_1M_BETA are now in core
+            from agent.anthropic_format import _COMMON_BETAS, _CONTEXT_1M_BETA
+            _OAUTH_ONLY_BETAS = _anthropic_ns.get("_OAUTH_ONLY_BETAS")
+
+            if not all([_is_oauth_token, _OAUTH_ONLY_BETAS]):
+                raise ImportError("anthropic provider services not fully registered")
             headers = {"anthropic-version": "2023-06-01"}
             is_oauth = _is_oauth_token(key)
             if is_oauth:
@@ -1623,11 +1606,13 @@ def run_doctor(args):
 
     def _probe_bedrock() -> _ConnectivityResult:
         try:
-            from agent.bedrock_adapter import (
-                has_aws_credentials,
-                resolve_aws_auth_env_var,
-                resolve_bedrock_region,
-            )
+            from agent.plugin_registries import registries
+            _bedrock_ns = registries.get_provider_namespace("bedrock")
+            has_aws_credentials = _bedrock_ns.get("has_aws_credentials")
+            resolve_aws_auth_env_var = _bedrock_ns.get("resolve_aws_auth_env_var")
+            resolve_bedrock_region = _bedrock_ns.get("resolve_bedrock_region")
+            if not all([has_aws_credentials, resolve_aws_auth_env_var, resolve_bedrock_region]):
+                raise ImportError("bedrock provider services not fully registered")
         except ImportError:
             return _ConnectivityResult("AWS Bedrock", [], [])
         if not has_aws_credentials():
@@ -1698,12 +1683,14 @@ def run_doctor(args):
             return _ConnectivityResult("Azure Foundry (Entra ID)", [], [])
 
         try:
-            from agent.azure_identity_adapter import (
-                EntraIdentityConfig,
-                SCOPE_AI_AZURE_DEFAULT,
-                describe_active_credential,
-                has_azure_identity_installed,
-            )
+            from agent.plugin_registries import registries
+            _azure_ns = registries.get_provider_namespace("azure")
+            EntraIdentityConfig = _azure_ns.get("EntraIdentityConfig")
+            SCOPE_AI_AZURE_DEFAULT = _azure_ns.get("SCOPE_AI_AZURE_DEFAULT")
+            describe_active_credential = _azure_ns.get("describe_active_credential")
+            has_azure_identity_installed = _azure_ns.get("has_azure_identity_installed")
+            if not all([EntraIdentityConfig, SCOPE_AI_AZURE_DEFAULT, describe_active_credential, has_azure_identity_installed]):
+                raise ImportError("azure provider services not fully registered")
         except Exception as exc:
             return _ConnectivityResult(
                 "Azure Foundry (Entra ID)",

hermes_cli/gateway.py

@@ -3960,6 +3960,18 @@ def _setup_whatsapp():
     cmd_whatsapp(argparse.Namespace())
 
 
+def _setup_email():
+    """Configure Email via the standard platform setup."""
+    email_platform = next(p for p in _PLATFORMS if p["key"] == "email")
+    _setup_standard_platform(email_platform)
+
+
+def _setup_sms():
+    """Configure SMS (Twilio) via the standard platform setup."""
+    sms_platform = next(p for p in _PLATFORMS if p["key"] == "sms")
+    _setup_standard_platform(sms_platform)
+
+
 def _setup_dingtalk():
     """Configure DingTalk — QR scan (recommended) or manual credential entry."""
     from hermes_cli.setup import (
@@ -4132,6 +4144,12 @@ def _setup_wecom():
     print_success("💬 WeCom configured!")
 
 
+def _setup_yuanbao():
+    """Configure Yuanbao via the standard platform setup."""
+    yuanbao_platform = next(p for p in _PLATFORMS if p["key"] == "yuanbao")
+    _setup_standard_platform(yuanbao_platform)
+
+
 def _is_service_installed() -> bool:
     """Check if the gateway is installed as a system service."""
     if supports_systemd_services():
@@ -4352,7 +4370,9 @@ def _setup_feishu():
     if method_idx == 0:
         # ── QR scan-to-create ──
         try:
-            from gateway.platforms.feishu import qr_register
+            from agent.plugin_registries import registries
+            _feishu_entry = registries.get_platform("feishu")
+            qr_register = _feishu_entry.helper_functions.get("qr_register") if _feishu_entry else None
         except Exception as exc:
             print_error(f"  Feishu / Lark onboard import failed: {exc}")
             qr_register = None
@@ -4393,8 +4413,13 @@ def _setup_feishu():
         # Try to probe the bot with manual credentials
         bot_name = None
         try:
-            from gateway.platforms.feishu import probe_bot
-            bot_info = probe_bot(app_id, app_secret, domain)
+            from agent.plugin_registries import registries
+            _feishu_entry = registries.get_platform("feishu")
+            probe_bot = _feishu_entry.helper_functions.get("probe_bot") if _feishu_entry else None
+            if probe_bot:
+                bot_info = probe_bot(app_id, app_secret, domain)
+            else:
+                bot_info = None
             if bot_info:
                 bot_name = bot_info.get("bot_name")
                 print_success(f"  Credentials verified — bot: {bot_name or 'unnamed'}")

hermes_cli/kanban.py

@@ -548,11 +548,6 @@ def build_parser(parent_subparsers: argparse._SubParsersAction) -> argparse.Argu
                             help="Additional task ids to schedule with the same reason (bulk mode)")
 
     p_unblock = sub.add_parser("unblock", help="Return one or more blocked/scheduled tasks to ready")
-    p_unblock.add_argument(
-        "--reason",
-        default=None,
-        help="Optional reason/note — recorded as a comment before unblocking. Quote multi-word reasons.",
-    )
     p_unblock.add_argument("task_ids", nargs="+")
 
     p_promote = sub.add_parser(
@@ -1983,20 +1978,14 @@ def _cmd_unblock(args: argparse.Namespace) -> int:
     if not ids:
         print("at least one task_id is required", file=sys.stderr)
         return 1
-    reason = getattr(args, "reason", None)
-    if reason is not None:
-        reason = reason.strip() or None
-    author = _profile_author() if reason else None
     failed: list[str] = []
     with kb.connect_closing() as conn:
         for tid in ids:
-            if reason:
-                kb.add_comment(conn, tid, author, f"UNBLOCK: {reason}")
             if not kb.unblock_task(conn, tid):
                 failed.append(tid)
                 print(f"cannot unblock {tid} (not blocked/scheduled?)", file=sys.stderr)
             else:
-                print(f"Unblocked {tid}" + (f": {reason}" if reason else ""))
+                print(f"Unblocked {tid}")
     return 0 if not failed else 1
 
 
@@ -2098,52 +2087,12 @@ def _cmd_tail(args: argparse.Namespace) -> int:
 
 
 def _cmd_dispatch(args: argparse.Namespace) -> int:
-    # Honour kanban.default_assignee as the fallback for unassigned ready
-    # tasks (#27145), kanban.max_in_progress as the global concurrency cap
-    # (#33488), kanban.max_in_progress_per_profile as the per-profile
-    # cap (#21582), and kanban.max_spawn as the per-tick spawn limit
-    # (#28805). Same semantics as the gateway dispatch path so behavior
-    # matches whether the user runs the CLI directly or relies on the
-    # gateway-embedded dispatcher.
-    try:
-        from hermes_cli.config import load_config
-        _cfg = load_config()
-        _kanban_cfg = _cfg.get("kanban", {}) if isinstance(_cfg, dict) else {}
-        default_assignee = (_kanban_cfg.get("default_assignee") or "").strip() or None
-
-        def _coerce_positive_int(value):
-            if value is None:
-                return None
-            try:
-                ival = int(value)
-            except (TypeError, ValueError):
-                return None
-            return ival if ival >= 1 else None
-
-        max_in_progress_per_profile = _coerce_positive_int(
-            _kanban_cfg.get("max_in_progress_per_profile")
-        )
-        max_in_progress = _coerce_positive_int(_kanban_cfg.get("max_in_progress"))
-        # CLI --max overrides config kanban.max_spawn when both are present;
-        # CLI is the more explicit signal so it wins.
-        cli_max = getattr(args, "max", None)
-        max_spawn = cli_max if cli_max is not None else _coerce_positive_int(
-            _kanban_cfg.get("max_spawn")
-        )
-    except Exception:
-        default_assignee = None
-        max_in_progress_per_profile = None
-        max_in_progress = None
-        max_spawn = getattr(args, "max", None)
     with kb.connect_closing() as conn:
         res = kb.dispatch_once(
             conn,
             dry_run=args.dry_run,
-            max_spawn=max_spawn,
-            max_in_progress=max_in_progress,
+            max_spawn=args.max,
             failure_limit=getattr(args, "failure_limit", kb.DEFAULT_SPAWN_FAILURE_LIMIT),
-            default_assignee=default_assignee,
-            max_in_progress_per_profile=max_in_progress_per_profile,
         )
     if getattr(args, "json", False):
         print(json.dumps({
@@ -2159,11 +2108,6 @@ def _cmd_dispatch(args: argparse.Namespace) -> int:
             ],
             "skipped_unassigned": res.skipped_unassigned,
             "skipped_nonspawnable": res.skipped_nonspawnable,
-            "skipped_per_profile_capped": [
-                {"task_id": tid, "assignee": who, "current": current}
-                for (tid, who, current) in res.skipped_per_profile_capped
-            ],
-            "auto_assigned_default": res.auto_assigned_default,
         }, indent=2))
         return 0
     print(f"Reclaimed:    {res.reclaimed}")
@@ -2184,18 +2128,8 @@ def _cmd_dispatch(args: argparse.Namespace) -> int:
     for tid, who, ws in res.spawned:
         tag = " (dry)" if args.dry_run else ""
         print(f"  - {tid}  ->  {who}  @ {ws or '-'}{tag}")
-    if res.auto_assigned_default:
-        print(
-            f"Auto-assigned to kanban.default_assignee={default_assignee!r}: "
-            f"{', '.join(res.auto_assigned_default)}"
-        )
     if res.skipped_unassigned:
         print(f"Skipped (unassigned): {', '.join(res.skipped_unassigned)}")
-    if res.skipped_per_profile_capped:
-        for tid, who, current in res.skipped_per_profile_capped:
-            print(
-                f"Deferred ({who} at per-profile cap, {current} running): {tid}"
-            )
     if res.skipped_nonspawnable:
         print(
             f"Skipped (non-spawnable assignee — terminal lane, OK): "

hermes_cli/kanban_db.py

@@ -84,6 +84,7 @@ import threading
 import logging
 import time
 from dataclasses import dataclass, field
+from datetime import datetime
 from pathlib import Path
 from typing import Any, Iterable, Optional
 
@@ -110,16 +111,6 @@ _IS_WINDOWS = sys.platform == "win32"
 # long single-call MCP workflows.
 DEFAULT_CLAIM_TTL_SECONDS = 15 * 60
 
-# If a worker's PID is still alive but its ``last_heartbeat_at`` is
-# older than this when ``release_stale_claims`` runs, treat the worker
-# as wedged and reclaim regardless of PID liveness (#29747 gap 3).
-# This catches the logic-loop case where the process is technically
-# running but not making observable progress.  ``_touch_activity``
-# bridges chunk-level liveness into ``last_heartbeat_at`` via #31752,
-# so any genuinely active worker keeps its heartbeat fresh as a side
-# effect of normal API traffic.
-DEFAULT_CLAIM_HEARTBEAT_MAX_STALE_SECONDS = 60 * 60
-
 
 def _resolve_claim_ttl_seconds(ttl_seconds: Optional[int] = None) -> int:
     """Return the effective claim TTL, honoring the kanban env override.
@@ -2750,19 +2741,9 @@ def release_stale_claims(
     then-immediately-reclaim loop seen on slow models that spend longer
     than ``DEFAULT_CLAIM_TTL_SECONDS`` inside a single tool-free LLM
     call (#23025): no tool calls means no ``kanban_heartbeat``, even
-    though the subprocess is healthy.
-
-    Backstop (#29747 gap 3): if the worker's PID is still alive but its
-    ``last_heartbeat_at`` is stale by more than
-    ``DEFAULT_CLAIM_HEARTBEAT_MAX_STALE_SECONDS`` (1h), the worker has
-    been making no observable progress and we reclaim anyway — even if
-    ``_pid_alive`` is still true. This catches the wedged-in-a-logic-loop
-    case where the process is technically running but accomplishing
-    nothing. ``_touch_activity`` (run_agent.py) bridges chunk-level
-    liveness into ``last_heartbeat_at`` via #31752, so any genuinely
-    active worker keeps its heartbeat fresh as a side effect of normal
-    API traffic. ``enforce_max_runtime`` and ``detect_crashed_workers``
-    remain the upper bounds for genuinely wedged or dead workers.
+    though the subprocess is healthy. ``enforce_max_runtime`` and
+    ``detect_crashed_workers`` remain the upper bounds for genuinely
+    wedged or dead workers.
 
     Returns the number of stale claims actually reclaimed (live-pid
     extensions don't count). Safe to call often.
@@ -2780,21 +2761,7 @@ def release_stale_claims(
     for row in stale:
         lock = row["claim_lock"] or ""
         host_local = lock.startswith(host_prefix)
-        hb = row["last_heartbeat_at"]
-        # Heartbeat staleness backstop: if we have a heartbeat at all
-        # and it's older than the max-stale threshold, the worker is
-        # not making observable progress.  Reclaim instead of extending,
-        # even if the PID is still alive (it's likely in a logic loop).
-        heartbeat_stale = (
-            hb is not None
-            and (now - int(hb)) > DEFAULT_CLAIM_HEARTBEAT_MAX_STALE_SECONDS
-        )
-        if (
-            host_local
-            and row["worker_pid"]
-            and _pid_alive(row["worker_pid"])
-            and not heartbeat_stale
-        ):
+        if host_local and row["worker_pid"] and _pid_alive(row["worker_pid"]):
             new_expires = now + _resolve_claim_ttl_seconds()
             with write_txn(conn):
                 cur = conn.execute(
@@ -2863,7 +2830,6 @@ def release_stale_claims(
                 ),
                 "now": now,
                 "host_local": host_local,
-                "heartbeat_stale": bool(heartbeat_stale),
             }
             payload.update(termination)
             _append_event(
@@ -4323,12 +4289,6 @@ class DispatchResult:
     skipped_unassigned: list[str] = field(default_factory=list)
     """Ready task ids skipped because they have no assignee at all.
     Operator-actionable — usually a misfiled task waiting for routing."""
-    auto_assigned_default: list[str] = field(default_factory=list)
-    """Task ids that were unassigned in the DB and had
-    ``kanban.default_assignee`` applied this tick before spawning (#27145).
-    Surfaces the auto-assignment to telemetry / CLI / dashboard so the
-    operator can see when the dispatcher is acting on the fallback rule
-    rather than on explicit per-task assignments."""
     skipped_nonspawnable: list[str] = field(default_factory=list)
     """Ready task ids skipped because their assignee names a control-plane
     lane (a Claude Code terminal like ``orion-cc``) rather than a Hermes
@@ -4336,14 +4296,6 @@ class DispatchResult:
     operator-actionable failure. Tracked separately so health telemetry
     can distinguish "real stuck" (nothing spawned but spawnable work
     available) from "correctly idle" (nothing spawnable in the queue)."""
-    skipped_per_profile_capped: list[tuple[str, str, int]] = field(default_factory=list)
-    """Tasks deferred this tick because their assignee is already at
-    ``kanban.max_in_progress_per_profile`` (#21582). Each entry is
-    ``(task_id, assignee, current_running_count)``. NOT an
-    operator-actionable failure — the task will be picked up on a
-    subsequent tick when the assignee has capacity. Separate bucket so
-    telemetry / dashboards can show "this profile is busy" vs
-    "task is genuinely stuck"."""
     crashed: list[str] = field(default_factory=list)
     """Task ids reclaimed because their worker PID disappeared."""
     auto_blocked: list[str] = field(default_factory=list)
@@ -4777,6 +4729,7 @@ def detect_stale_running(
     if stale_timeout_seconds <= 0:
         return []
 
+    import signal as _signal_mod
 
     now = int(time.time())
     host_prefix = f"{_claimer_id().split(':', 1)[0]}:"
@@ -4865,6 +4818,21 @@ def detect_stale_running(
     return reclaimed
 
 
+def set_max_runtime(
+    conn: sqlite3.Connection,
+    task_id: str,
+    seconds: Optional[int],
+) -> bool:
+    """Set or clear the per-task max_runtime_seconds. Returns True on
+    success."""
+    with write_txn(conn):
+        cur = conn.execute(
+            "UPDATE tasks SET max_runtime_seconds = ? WHERE id = ?",
+            (int(seconds) if seconds is not None else None, task_id),
+        )
+    return cur.rowcount == 1
+
+
 def _error_fingerprint(error_text: str) -> str:
     """Normalize an error message for grouping identical failures.
 
@@ -5374,8 +5342,6 @@ def dispatch_once(
     failure_limit: int = DEFAULT_SPAWN_FAILURE_LIMIT,
     stale_timeout_seconds: int = 0,
     board: Optional[str] = None,
-    default_assignee: Optional[str] = None,
-    max_in_progress_per_profile: Optional[int] = None,
 ) -> DispatchResult:
     """Run one dispatcher tick.
 
@@ -5461,89 +5427,12 @@ def dispatch_once(
         if max_spawn is None or max_spawn > remaining:
             max_spawn = remaining
     spawned = 0
-    # Per-profile concurrency cap (#21582): when set, track how many
-    # workers each assignee already has in flight, and refuse to spawn
-    # when this would push that assignee past the cap. Prevents
-    # fan-out workloads from melting a single profile's local model /
-    # API quota / browser pool while leaving other profiles idle.
-    # Tasks blocked this way go to skipped_per_profile_capped (not
-    # skipped_unassigned — the operator-actionable signal is different:
-    # "this profile is busy, try again later" not "this needs routing").
-    _per_profile_cap = max_in_progress_per_profile if (
-        isinstance(max_in_progress_per_profile, int)
-        and max_in_progress_per_profile > 0
-    ) else None
-    _per_profile_running: dict[str, int] = {}
-    if _per_profile_cap is not None:
-        for prow in conn.execute(
-            "SELECT assignee, COUNT(*) AS n FROM tasks "
-            "WHERE status = 'running' AND assignee IS NOT NULL "
-            "GROUP BY assignee"
-        ):
-            _per_profile_running[prow["assignee"]] = int(prow["n"])
-    # Normalize default_assignee once: empty/whitespace string → None so the
-    # rest of the loop can use ``if default_assignee:`` as a single check.
-    # We also resolve profile_exists once here for the same reason.
-    _default_assignee = (default_assignee or "").strip() or None
-    _default_assignee_resolved = False
-    if _default_assignee:
-        try:
-            from hermes_cli.profiles import profile_exists as _pe
-            _default_assignee_resolved = bool(_pe(_default_assignee))
-        except Exception:
-            # Profiles module not importable (test stubs, exotic envs).
-            # Trust the operator's config and try the assignment; the
-            # downstream profile_exists check on the assigned row will
-            # bucket it as nonspawnable if the profile genuinely isn't
-            # there, with the existing diagnostic.
-            _default_assignee_resolved = True
     for row in ready_rows:
         if max_spawn is not None and running_count + spawned >= max_spawn:
             break
-        row_assignee = row["assignee"]
-        if not row_assignee:
-            # Honour kanban.default_assignee: when the dispatcher hits an
-            # unassigned ready task and an operator-configured fallback
-            # exists, persist the assignment and proceed. This removes the
-            # dashboard footgun where a task created without an assignee
-            # parks in 'ready' forever even though the operator's intent
-            # ("default") was perfectly clear (#27145). Mutating the row
-            # (not just the in-memory view) keeps diagnostics and the
-            # board state consistent: the task is now legitimately owned
-            # by ``kanban.default_assignee``, not "unassigned but secretly
-            # routed".
-            if _default_assignee and _default_assignee_resolved:
-                # Dry-run: show what WOULD happen (auto-assign + spawn) without
-                # mutating the DB. Real run: mutate the row + emit the
-                # 'assigned' event so the board state matches what just happened.
-                if not dry_run:
-                    try:
-                        with write_txn(conn):
-                            conn.execute(
-                                "UPDATE tasks SET assignee = ? WHERE id = ? "
-                                "AND (assignee IS NULL OR assignee = '')",
-                                (_default_assignee, row["id"]),
-                            )
-                            _append_event(
-                                conn, row["id"], "assigned",
-                                {
-                                    "assignee": _default_assignee,
-                                    "source": "kanban.default_assignee",
-                                },
-                            )
-                    except Exception:
-                        _log.debug(
-                            "kanban dispatch: failed to apply default_assignee=%r "
-                            "to task %s",
-                            _default_assignee, row["id"], exc_info=True,
-                        )
-                        result.skipped_unassigned.append(row["id"])
-                        continue
-                row_assignee = _default_assignee
-                result.auto_assigned_default.append(row["id"])
-            else:
-                result.skipped_unassigned.append(row["id"])
-                continue
+        if not row["assignee"]:
+            result.skipped_unassigned.append(row["id"])
+            continue
         # Skip ready tasks whose assignee is not a real Hermes profile.
         # `_default_spawn` invokes ``hermes -p <assignee>`` which fails
         # with "Profile 'X' does not exist" when the assignee names a
@@ -5558,7 +5447,7 @@ def dispatch_once(
             from hermes_cli.profiles import profile_exists  # local import: avoids cycle
         except Exception:
             profile_exists = None  # type: ignore[assignment]
-        if profile_exists is not None and not profile_exists(row_assignee):
+        if profile_exists is not None and not profile_exists(row["assignee"]):
             # Bucket separately from skipped_unassigned: the operator
             # cannot fix this by assigning a profile (the assignee IS the
             # intended owner — a terminal lane). Health telemetry uses
@@ -5567,19 +5456,6 @@ def dispatch_once(
             # of human-pulled work.
             result.skipped_nonspawnable.append(row["id"])
             continue
-        # Per-profile concurrency cap (#21582): even if there's global
-        # headroom, refuse to spawn for an assignee that's already at
-        # its in-flight cap. Prevents one profile's local model / API
-        # quota / browser pool from being overwhelmed by a fan-out
-        # while the global max_in_progress / max_spawn caps still allow
-        # work on OTHER profiles.
-        if _per_profile_cap is not None:
-            current = _per_profile_running.get(row_assignee, 0)
-            if current >= _per_profile_cap:
-                result.skipped_per_profile_capped.append(
-                    (row["id"], row_assignee, current)
-                )
-                continue
         # Respawn guard: refuse to re-spawn when useful work is already
         # in-flight/recent, or when the last failure is a deterministic
         # blocker (quota / auth). The guard defers the spawn this tick so
@@ -5602,15 +5478,7 @@ def dispatch_once(
                     )
             continue
         if dry_run:
-            result.spawned.append((row["id"], row_assignee, ""))
-            # Increment per-profile counter even in dry_run so the cap
-            # check sees the would-be spawn on subsequent iterations.
-            # Without this, dry_run reports every task as spawnable and
-            # under-reports the capped subset (#21582).
-            if _per_profile_cap is not None and row_assignee:
-                _per_profile_running[row_assignee] = (
-                    _per_profile_running.get(row_assignee, 0) + 1
-                )
+            result.spawned.append((row["id"], row["assignee"], ""))
             continue
         claimed = claim_task(conn, row["id"], ttl_seconds=ttl_seconds)
         if claimed is None:
@@ -5653,13 +5521,6 @@ def dispatch_once(
             # complete_task).
             result.spawned.append((claimed.id, claimed.assignee or "", str(workspace)))
             spawned += 1
-            # Track the new in-flight count for this profile so later
-            # iterations in this same tick respect the per-profile cap
-            # (#21582). Subsequent ticks re-query from the DB.
-            if _per_profile_cap is not None and claimed.assignee:
-                _per_profile_running[claimed.assignee] = (
-                    _per_profile_running.get(claimed.assignee, 0) + 1
-                )
         except Exception as exc:
             auto = _record_spawn_failure(
                 conn, claimed.id, str(exc),
@@ -6501,7 +6362,7 @@ def _to_epoch(val) -> Optional[int]:
         pass
     # ISO-8601 fallback (e.g. '2026-05-10T15:00:00Z')
     try:
-        from datetime import datetime
+        from datetime import datetime, timezone
         dt = datetime.fromisoformat(s.replace("Z", "+00:00"))
         return int(dt.timestamp())
     except (ValueError, OSError):
@@ -6952,6 +6813,16 @@ def get_run(conn: sqlite3.Connection, run_id: int) -> Optional[Run]:
     return Run.from_row(row) if row else None
 
 
+def active_run(conn: sqlite3.Connection, task_id: str) -> Optional[Run]:
+    """Return the currently-open run for ``task_id`` (``ended_at IS NULL``)."""
+    row = conn.execute(
+        "SELECT * FROM task_runs WHERE task_id = ? AND ended_at IS NULL "
+        "ORDER BY started_at DESC LIMIT 1",
+        (task_id,),
+    ).fetchone()
+    return Run.from_row(row) if row else None
+
+
 def latest_run(conn: sqlite3.Connection, task_id: str) -> Optional[Run]:
     """Return the most recent run regardless of outcome (active or closed)."""
     row = conn.execute(

hermes_cli/kanban_diagnostics.py

@@ -191,6 +191,23 @@ def _active_hallucination_events(
         elif k == kind:
             active.append(ev)
     return active
+
+
+def _latest_clean_event_ts(events: Iterable[Any]) -> int:
+    """Timestamp of the most recent clean completion / edit event.
+
+    Kept for general "has this task ever been successfully completed"
+    lookups; hallucination rules use ``_active_hallucination_events``
+    instead because they need strict ordering.
+    """
+    latest = 0
+    for ev in events:
+        if _event_kind(ev) in {"completed", "edited"}:
+            t = _event_ts(ev)
+            latest = max(latest, t)
+    return latest
+
+
 # Standard always-available actions. Every diagnostic can offer these as
 # fallbacks regardless of kind — they're the two baseline recovery
 # primitives the kernel supports.
@@ -774,83 +791,6 @@ def _rule_stuck_in_blocked(task, events, runs, now, cfg) -> list[Diagnostic]:
     )]
 
 
-def _rule_block_unblock_cycling(task, events, runs, now, cfg) -> list[Diagnostic]:
-    """Task has cycled through blocked → unblocked many times — the
-    ``unblock`` is not fixing the underlying problem and the worker
-    keeps re-blocking for substantially the same reason.
-
-    ``_rule_stuck_in_blocked`` resets its timer on any ``commented`` /
-    ``unblocked`` event, so a task that cycles every few minutes is
-    invisible to it regardless of how many times it cycles (#29747
-    gap 1). This rule complements that one by counting block→unblock
-    cycles in a sliding window.
-
-    Threshold: cfg["block_cycle_threshold"] (default 3) cycles within
-    cfg["block_cycle_window_seconds"] (default 24h).
-    """
-    threshold = _positive_int(cfg.get("block_cycle_threshold"), 3)
-    window_seconds = float(cfg.get("block_cycle_window_seconds", 24 * 3600))
-    cycle_cutoff = now - window_seconds
-
-    # Walk events chronologically (arrival order — callers pre-sort by
-    # id, which is the canonical chronological order; ``created_at``
-    # alone is insufficient because multiple events can share the same
-    # second).  Count "blocked after unblocked" transitions: every time
-    # a blocked event follows at least one unblocked event since the
-    # last cycle was counted, that's a new cycle.
-    cycles = 0
-    seen_unblock_since_last_cycle = False
-    initial_blocked_ts = 0
-    last_cycle_blocked_ts = 0
-    for ev in events:
-        ts = _event_ts(ev)
-        if ts < cycle_cutoff:
-            continue
-        kind = _event_kind(ev)
-        if kind == "blocked":
-            if initial_blocked_ts == 0:
-                initial_blocked_ts = ts
-            if seen_unblock_since_last_cycle:
-                cycles += 1
-                last_cycle_blocked_ts = ts
-                seen_unblock_since_last_cycle = False
-        elif kind == "unblocked":
-            seen_unblock_since_last_cycle = True
-
-    if cycles < threshold:
-        return []
-
-    task_id = _task_field(task, "id")
-    actions: list[DiagnosticAction] = []
-    if task_id:
-        actions.append(DiagnosticAction(
-            kind="cli_hint",
-            label=f"Check block reasons: hermes kanban events {task_id}",
-            payload={"command": f"hermes kanban events {task_id}"},
-            suggested=True,
-        ))
-    return [Diagnostic(
-        kind="block_unblock_cycling",
-        severity="warning",
-        title=f"Task block→unblock cycled {cycles}x in {int(window_seconds/3600)}h",
-        detail=(
-            f"This task has been blocked {cycles} times after being "
-            "unblocked, suggesting the unblock is not addressing the "
-            "root cause and the worker keeps hitting the same wall. "
-            "Review the block reasons in the event history; a different "
-            "intervention (reassign, change scope, archive) may be needed."
-        ),
-        actions=actions,
-        first_seen_at=int(initial_blocked_ts) if initial_blocked_ts else int(now),
-        last_seen_at=int(last_cycle_blocked_ts) if last_cycle_blocked_ts else int(now),
-        count=cycles,
-        data={
-            "cycles": cycles,
-            "window_seconds": int(window_seconds),
-        },
-    )]
-
-
 def _rule_stranded_in_ready(task, events, runs, now, cfg) -> list[Diagnostic]:
     """Task has been in ``ready`` status for too long without any worker
     claiming it.
@@ -983,7 +923,6 @@ _RULES: list[RuleFn] = [
     _rule_repeated_failures,
     _rule_repeated_crashes,
     _rule_stuck_in_blocked,
-    _rule_block_unblock_cycling,
     _rule_stranded_in_ready,
 ]
 
@@ -997,7 +936,6 @@ DIAGNOSTIC_KINDS = (
     "repeated_failures",
     "repeated_crashes",
     "stuck_in_blocked",
-    "block_unblock_cycling",
     "stranded_in_ready",
 )
 
@@ -1105,3 +1043,16 @@ def compute_task_diagnostics(
         )
     )
     return out
+
+
+def severity_of_highest(diagnostics: Iterable[Diagnostic]) -> Optional[str]:
+    """Highest severity present in the list, or None if empty. Useful
+    for card badges that need a single color."""
+    highest_idx = -1
+    highest = None
+    for d in diagnostics:
+        idx = SEVERITY_ORDER.index(d.severity) if d.severity in SEVERITY_ORDER else -1
+        if idx > highest_idx:
+            highest_idx = idx
+            highest = d.severity
+    return highest

hermes_cli/kanban_swarm.py

@@ -209,7 +209,7 @@ def create_swarm(
         priority=priority,
         workspace_kind=workspace_kind,
         workspace_path=workspace_path,
-        skills=["humanizer"],
+        skills=["avoid-ai-writing"],
     )
 
     created = SwarmCreated(root, worker_ids, verifier, synthesizer)

hermes_cli/main.py

@@ -622,10 +622,12 @@ def _has_any_provider_configured() -> bool:
     # being installed doesn't mean the user wants Hermes to use their tokens.
     if _has_hermes_config:
         try:
-            from agent.anthropic_adapter import (
-                read_claude_code_credentials,
-                is_claude_code_token_valid,
-            )
+            from agent.plugin_registries import registries
+            _anthropic = registries.get_provider_namespace("anthropic")
+            read_claude_code_credentials = _anthropic.get("read_claude_code_credentials")
+            is_claude_code_token_valid = _anthropic.get("is_claude_code_token_valid")
+            if read_claude_code_credentials is None or is_claude_code_token_valid is None:
+                raise ImportError("anthropic plugin not registered")
 
             creds = read_claude_code_credentials()
             if creds and (
@@ -3004,6 +3006,7 @@ def _model_flow_nous(config, current_model="", args=None):
     """Nous Portal provider: ensure logged in, then pick model."""
     from hermes_cli.auth import (
         get_provider_auth_state,
+        NOUS_INFERENCE_AUTH_MODE_LEGACY,
         _prompt_model_selection,
         _save_model_choice,
         _update_config_for_provider,
@@ -3071,7 +3074,7 @@ def _model_flow_nous(config, current_model="", args=None):
 
     # Verify credentials are still valid (catches expired sessions early)
     try:
-        creds = resolve_nous_runtime_credentials()
+        creds = resolve_nous_runtime_credentials(min_key_ttl_seconds=5 * 60)
     except Exception as exc:
         relogin = isinstance(exc, AuthError) and exc.relogin_required
         msg = format_auth_error(exc) if isinstance(exc, AuthError) else str(exc)
@@ -3105,13 +3108,14 @@ def _model_flow_nous(config, current_model="", args=None):
     if not free_tier:
         try:
             refreshed_creds = resolve_nous_runtime_credentials(
-                force_refresh=True,
+                min_key_ttl_seconds=5 * 60,
+                inference_auth_mode=NOUS_INFERENCE_AUTH_MODE_LEGACY,
             )
             if refreshed_creds:
                 creds = refreshed_creds
         except Exception:
             # Runtime inference has its own paid-entitlement recovery path; do
-            # not block model selection if this opportunistic refresh fails.
+            # not block model selection if this opportunistic remint fails.
             pass
 
     # Resolve portal URL early — needed both for upgrade links and for the
@@ -4102,13 +4106,15 @@ def _model_flow_azure_foundry(config, current_model=""):
 
     if use_entra:
         try:
-            from agent.azure_identity_adapter import (
-                EntraIdentityConfig,
-                SCOPE_AI_AZURE_DEFAULT,
-                build_token_provider,
-                describe_active_credential,
-                has_azure_identity_installed,
-            )
+            from agent.plugin_registries import registries
+            _azure = registries.get_provider_namespace("azure")
+            EntraIdentityConfig = _azure.get("EntraIdentityConfig")
+            SCOPE_AI_AZURE_DEFAULT = _azure.get("SCOPE_AI_AZURE_DEFAULT")
+            build_token_provider = _azure.get("build_token_provider")
+            describe_active_credential = _azure.get("describe_active_credential")
+            has_azure_identity_installed = _azure.get("has_azure_identity_installed")
+            if any(v is None for v in [EntraIdentityConfig, SCOPE_AI_AZURE_DEFAULT, build_token_provider, describe_active_credential, has_azure_identity_installed]):
+                raise ImportError("azure plugin not registered")
         except ImportError as exc:
             print()
             print(f"⚠ Could not import azure-identity adapter: {exc}")
@@ -5422,12 +5428,14 @@ def _model_flow_bedrock(config, current_model=""):
 
     # 1. Check for AWS credentials
     try:
-        from agent.bedrock_adapter import (
-            has_aws_credentials,
-            resolve_aws_auth_env_var,
-            resolve_bedrock_region,
-            discover_bedrock_models,
-        )
+        from agent.plugin_registries import registries
+        _bedrock = registries.get_provider_namespace("bedrock")
+        has_aws_credentials = _bedrock.get("has_aws_credentials")
+        resolve_aws_auth_env_var = _bedrock.get("resolve_aws_auth_env_var")
+        resolve_bedrock_region = _bedrock.get("resolve_bedrock_region")
+        discover_bedrock_models = _bedrock.get("discover_bedrock_models")
+        if any(v is None for v in [has_aws_credentials, resolve_aws_auth_env_var, resolve_bedrock_region, discover_bedrock_models]):
+            raise ImportError("bedrock plugin not registered")
     except ImportError:
         print("  ✗ boto3 is not installed. Install it with:")
         print("    pip install boto3")
@@ -5591,6 +5599,7 @@ def _model_flow_bedrock(config, current_model=""):
 def _model_flow_api_key_provider(config, provider_id, current_model=""):
     """Generic flow for API-key providers (z.ai, MiniMax, OpenCode, etc.)."""
     from hermes_cli.auth import (
+        LMSTUDIO_NOAUTH_PLACEHOLDER,
         PROVIDER_REGISTRY,
         _prompt_model_selection,
         _save_model_choice,
@@ -5874,11 +5883,13 @@ def _model_flow_api_key_provider(config, provider_id, current_model=""):
 
 def _run_anthropic_oauth_flow(save_env_value):
     """Run the Claude OAuth setup-token flow. Returns True if credentials were saved."""
-    from agent.anthropic_adapter import (
-        run_oauth_setup_token,
-        read_claude_code_credentials,
-        is_claude_code_token_valid,
-    )
+    from agent.plugin_registries import registries
+    _anthropic = registries.get_provider_namespace("anthropic")
+    run_oauth_setup_token = _anthropic.get("run_oauth_setup_token")
+    read_claude_code_credentials = _anthropic.get("read_claude_code_credentials")
+    is_claude_code_token_valid = _anthropic.get("is_claude_code_token_valid")
+    if run_oauth_setup_token is None:
+        raise ImportError("anthropic plugin not registered")
     from hermes_cli.config import (
         save_anthropic_oauth_token,
         use_anthropic_claude_code_credentials,
@@ -5986,11 +5997,13 @@ def _model_flow_anthropic(config, current_model=""):
     existing_key = get_anthropic_key()
     cc_available = False
     try:
-        from agent.anthropic_adapter import (
-            read_claude_code_credentials,
-            is_claude_code_token_valid,
-            _is_oauth_token,
-        )
+        from agent.plugin_registries import registries
+        _anthropic = registries.get_provider_namespace("anthropic")
+        read_claude_code_credentials = _anthropic.get("read_claude_code_credentials")
+        is_claude_code_token_valid = _anthropic.get("is_claude_code_token_valid")
+        _is_oauth_token = _anthropic.get("_is_oauth_token")
+        if any(v is None for v in [read_claude_code_credentials, is_claude_code_token_valid, _is_oauth_token]):
+            raise ImportError("anthropic plugin not registered")
 
         cc_creds = read_claude_code_credentials()
         if cc_creds and is_claude_code_token_valid(cc_creds):
@@ -6160,6 +6173,13 @@ def cmd_webhook(args):
     webhook_command(args)
 
 
+def cmd_portal(args):
+    """Nous Portal status and Tool Gateway routing surface."""
+    from hermes_cli.portal_cli import portal_command
+
+    return portal_command(args)
+
+
 def cmd_slack(args):
     """Slack integration helpers.
 
@@ -8100,71 +8120,13 @@ def _cleanup_quarantined_exes(scripts_dir: Path | None = None) -> None:
 
 
 def _refresh_active_lazy_features() -> None:
-    """Refresh lazy-installed backends after a code update.
+    """No-op — lazy deps removed.
 
-    When pyproject.toml's ``[all]`` extra was slimmed down (May 2026), most
-    optional backends moved to ``tools/lazy_deps.py`` and only install on
-    first use. ``hermes update`` runs ``uv pip install -e .[all]`` which
-    leaves those packages untouched — so if we bump a pin in
-    :data:`LAZY_DEPS` (CVE response, transitive bug fix), users who already
-    activated the backend keep the stale version forever.
-
-    This function asks lazy_deps which features the user has previously
-    activated and reinstalls them under the current pins. Features the
-    user never enabled stay quiet — no churn for cold backends.
-
-    Never raises. A failure here must not block the rest of the update.
+    Optional backends are now proper plugin packages (hermes-agent-anthropic,
+    hermes-agent-telegram, etc.) installed via extras. ``hermes update``
+    refreshes them through ``uv pip install -e .[all]`` like any other dep.
     """
-    try:
-        from tools import lazy_deps
-    except Exception as exc:
-        logger.debug("Lazy refresh skipped (import failed): %s", exc)
-        return
-
-    try:
-        active = lazy_deps.active_features()
-    except Exception as exc:
-        logger.debug("Lazy refresh skipped (active_features failed): %s", exc)
-        return
-
-    if not active:
-        return
-
-    print()
-    print(f"→ Refreshing {len(active)} active lazy backend(s)...")
-
-    try:
-        results = lazy_deps.refresh_active_features(prompt=False)
-    except Exception as exc:
-        # refresh_active_features is documented as never-raise, but defend
-        # the update flow against future regressions.
-        print(f"  ⚠ Lazy refresh failed unexpectedly: {exc}")
-        return
-
-    refreshed = [f for f, s in results.items() if s == "refreshed"]
-    current = [f for f, s in results.items() if s == "current"]
-    failed = [(f, s) for f, s in results.items() if s.startswith("failed:")]
-    skipped = [(f, s) for f, s in results.items() if s.startswith("skipped:")]
-
-    if refreshed:
-        print(f"  ↑ {len(refreshed)} refreshed: {', '.join(refreshed)}")
-    if current:
-        print(f"  ✓ {len(current)} already current")
-    if skipped:
-        # Most common reason: security.allow_lazy_installs=false. Show one
-        # line so the user knows why; not an error.
-        names = ", ".join(f for f, _ in skipped)
-        reason = skipped[0][1].split(": ", 1)[-1]
-        print(f"  · {len(skipped)} skipped ({reason}): {names}")
-    if failed:
-        for feature, status in failed:
-            reason = status.split(": ", 1)[-1]
-            # Clip noisy pip stderr to keep update output legible.
-            if len(reason) > 200:
-                reason = reason[:200] + "..."
-            print(f"  ⚠ {feature} failed to refresh: {reason}")
-        print("  Backends keep their previously-installed version; rerun")
-        print("  `hermes update` once the upstream issue is resolved.")
+    pass
 
 
 def _install_python_dependencies_with_optional_fallback(
@@ -10968,6 +10930,24 @@ def cmd_logs(args):
         since=getattr(args, "since", None),
         component=getattr(args, "component", None),
     )
+
+
+def _build_provider_choices() -> list[str]:
+    """Build the --provider choices list from CANONICAL_PROVIDERS + 'auto'."""
+    try:
+        from hermes_cli.models import CANONICAL_PROVIDERS as _cp
+        return ["auto"] + [p.slug for p in _cp]
+    except Exception:
+        # Fallback: static list guarantees the CLI always works
+        return [
+            "auto", "openrouter", "nous", "openai-codex", "xai-oauth", "copilot-acp", "copilot",
+            "anthropic", "gemini", "google-gemini-cli", "xai", "bedrock", "azure-foundry",
+            "ollama-cloud", "huggingface", "zai", "kimi-coding", "kimi-coding-cn",
+            "stepfun", "minimax", "minimax-cn", "kilocode", "novita", "xiaomi", "arcee",
+            "nvidia", "deepseek", "alibaba", "qwen-oauth", "opencode-zen", "opencode-go",
+        ]
+
+
 # Top-level subcommands that argparse knows about WITHOUT running plugin
 # discovery.  Used to short-circuit eager plugin imports (which can take
 # 500ms+ pulling in google.cloud.pubsub_v1, aiohttp, grpc, etc.) when the
@@ -12883,34 +12863,7 @@ Examples:
     )
     plugins_remove.add_argument("name", help="Plugin directory name to remove")
 
-    plugins_list = plugins_subparsers.add_parser(
-        "list", aliases=["ls"], help="List installed plugins"
-    )
-    plugins_list.add_argument(
-        "--enabled",
-        action="store_true",
-        help="Show only enabled plugins",
-    )
-    plugins_list.add_argument(
-        "--user",
-        action="store_true",
-        help="Show only user-installed plugins (including git plugins)",
-    )
-    plugins_list.add_argument(
-        "--no-bundled",
-        action="store_true",
-        help="Hide bundled plugins",
-    )
-    plugins_list.add_argument(
-        "--plain",
-        action="store_true",
-        help="Print compact plain-text output instead of a Rich table",
-    )
-    plugins_list.add_argument(
-        "--json",
-        action="store_true",
-        help="Print machine-readable JSON",
-    )
+    plugins_subparsers.add_parser("list", aliases=["ls"], help="List installed plugins")
 
     plugins_enable = plugins_subparsers.add_parser(
         "enable", help="Enable a disabled plugin"

hermes_cli/mcp_catalog.py

@@ -23,6 +23,7 @@ See references/mcp-catalog.md (this repo's skill) for the manifest schema.
 
 from __future__ import annotations
 
+import os
 import re
 import shutil
 import subprocess
@@ -40,7 +41,7 @@ from hermes_cli.config import (
     get_env_value,
     save_env_value,
 )
-from hermes_cli.cli_output import prompt as _prompt_input
+from hermes_cli.cli_output import prompt as _prompt_input, prompt_yes_no
 
 _MANIFEST_VERSION = 1
 

hermes_cli/model_catalog.py

@@ -64,15 +64,6 @@ logger = logging.getLogger(__name__)
 DEFAULT_CATALOG_URL = (
     "https://hermes-agent.nousresearch.com/docs/api/model-catalog.json"
 )
-# Fallback fetch chain. The Docusaurus site is served through Vercel, which
-# occasionally returns HTTP 403 + x-vercel-mitigated: challenge for non-
-# browser clients (urllib, curl). When that happens the disk cache goes
-# stale and new model releases never reach the picker. The raw GitHub URL
-# is the same manifest published from the same repo and is not bot-gated,
-# so we fall through to it whenever the primary URL fails.
-DEFAULT_CATALOG_FALLBACK_URLS: tuple[str, ...] = (
-    "https://raw.githubusercontent.com/NousResearch/hermes-agent/main/website/static/api/model-catalog.json",
-)
 DEFAULT_TTL_HOURS = 24
 DEFAULT_FETCH_TIMEOUT = 8.0
 SUPPORTED_SCHEMA_VERSION = 1
@@ -148,31 +139,6 @@ def _fetch_manifest(url: str, timeout: float) -> dict[str, Any] | None:
     return data
 
 
-def _fetch_manifest_with_fallback(
-    primary_url: str,
-    timeout: float,
-    fallback_urls: tuple[str, ...] = DEFAULT_CATALOG_FALLBACK_URLS,
-) -> dict[str, Any] | None:
-    """Try ``primary_url`` first, then walk ``fallback_urls``.
-
-    Returns the first manifest that fetches and validates, or None when
-    every URL fails. Skips fallback URLs identical to the primary so an
-    operator who configured the catalog URL to point at the raw GitHub
-    copy doesn't double-fetch.
-    """
-    data = _fetch_manifest(primary_url, timeout)
-    if data is not None:
-        return data
-    for url in fallback_urls:
-        if not url or url == primary_url:
-            continue
-        data = _fetch_manifest(url, timeout)
-        if data is not None:
-            logger.info("model catalog primary URL failed; using fallback %s", url)
-            return data
-    return None
-
-
 def _validate_manifest(data: Any) -> bool:
     """Return True when ``data`` matches the minimum manifest shape."""
     if not isinstance(data, dict):
@@ -269,7 +235,7 @@ def get_catalog(*, force_refresh: bool = False) -> dict[str, Any]:
         return disk_data
 
     # Need to (re)fetch. If it fails, fall back to any stale disk copy.
-    fetched = _fetch_manifest_with_fallback(cfg["url"], DEFAULT_FETCH_TIMEOUT)
+    fetched = _fetch_manifest(cfg["url"], DEFAULT_FETCH_TIMEOUT)
     if fetched is not None:
         _write_disk_cache(fetched)
         new_disk_data, new_mtime = _read_disk_cache()

hermes_cli/model_switch.py

@@ -277,6 +277,19 @@ class ModelSwitchResult:
     capabilities: Optional[ModelCapabilities] = None
     model_info: Optional[ModelInfo] = None
     is_global: bool = False
+
+
+@dataclass
+class CustomAutoResult:
+    """Result of switching to bare 'custom' provider with auto-detect."""
+
+    success: bool
+    model: str = ""
+    base_url: str = ""
+    api_key: str = ""
+    error_message: str = ""
+
+
 # ---------------------------------------------------------------------------
 # Flag parsing
 # ---------------------------------------------------------------------------
@@ -1072,7 +1085,8 @@ def list_authenticated_providers(
     from hermes_cli.auth import PROVIDER_REGISTRY
     from hermes_cli.models import (
         OPENROUTER_MODELS, _PROVIDER_MODELS,
-        _MODELS_DEV_PREFERRED, _merge_with_models_dev, cached_provider_model_ids,
+        _MODELS_DEV_PREFERRED, _merge_with_models_dev, provider_model_ids,
+        cached_provider_model_ids,
         get_curated_nous_model_ids,
     )
 
@@ -1145,8 +1159,12 @@ def list_authenticated_providers(
         if slug_norm != current_norm:
             return False
         try:
-            from agent.bedrock_adapter import has_aws_credentials
-            return bool(has_aws_credentials())
+            from agent.plugin_registries import registries
+            _bedrock_ns = registries.get_provider_namespace("bedrock")
+            has_aws_credentials = _bedrock_ns.get("has_aws_credentials")
+            if has_aws_credentials:
+                return bool(has_aws_credentials())
+            return False
         except Exception:
             return False
 
@@ -1328,10 +1346,12 @@ def list_authenticated_providers(
         # configured.
         if not has_creds and hermes_slug == "anthropic":
             try:
-                from agent.anthropic_adapter import (
-                    read_claude_code_credentials,
-                    read_hermes_oauth_credentials,
-                )
+                from agent.plugin_registries import registries
+                _anthropic_ns = registries.get_provider_namespace("anthropic")
+                read_claude_code_credentials = _anthropic_ns.get("read_claude_code_credentials")
+                read_hermes_oauth_credentials = _anthropic_ns.get("read_hermes_oauth_credentials")
+                if read_claude_code_credentials is None or read_hermes_oauth_credentials is None:
+                    raise ImportError("anthropic credential readers not registered")
                 hermes_creds = read_hermes_oauth_credentials()
                 cc_creds = read_claude_code_credentials()
                 if (hermes_creds and hermes_creds.get("accessToken")) or \

hermes_cli/models.py

@@ -53,7 +53,7 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
     ("google/gemini-3.1-pro-preview",          ""),
     ("google/gemini-3.1-flash-lite-preview",   ""),
     ("qwen/qwen3.6-35b-a3b",                   ""),
-    ("stepfun/step-3.7-flash",                 ""),
+    ("stepfun/step-3.5-flash",                 ""),
     ("minimax/minimax-m2.7",                   ""),
     ("z-ai/glm-5.1",                           ""),
     ("x-ai/grok-4.20",                         ""),
@@ -160,7 +160,7 @@ _PROVIDER_MODELS: dict[str, list[str]] = {
         "google/gemini-3.1-pro-preview",
         "google/gemini-3.1-flash-lite-preview",
         "qwen/qwen3.6-35b-a3b",
-        "stepfun/step-3.7-flash",
+        "stepfun/step-3.5-flash",
         "minimax/minimax-m2.7",
         "z-ai/glm-5.1",
         "x-ai/grok-4.3",
@@ -484,6 +484,41 @@ def _is_model_free(model_id: str, pricing: dict[str, dict[str, str]]) -> bool:
 # ---------------------------------------------------------------------------
 # Nous Portal account tier detection
 # ---------------------------------------------------------------------------
+
+def fetch_nous_account_tier(access_token: str, portal_base_url: str = "") -> dict[str, Any]:
+    """Fetch the user's Nous Portal account/subscription info.
+
+    Calls ``<portal>/api/oauth/account`` with the OAuth access token.
+
+    Returns the parsed JSON dict on success, e.g.::
+
+        {
+            "subscription": {
+                "plan": "Plus",
+                "tier": 2,
+                "monthly_charge": 20,
+                "credits_remaining": 1686.60,
+                ...
+            },
+            ...
+        }
+
+    Returns an empty dict on any failure (network, auth, parse).
+    """
+    base = (portal_base_url or "https://portal.nousresearch.com").rstrip("/")
+    url = f"{base}/api/oauth/account"
+    headers = {
+        "Authorization": f"Bearer {access_token}",
+        "Accept": "application/json",
+    }
+    try:
+        req = urllib.request.Request(url, headers=headers)
+        with urllib.request.urlopen(req, timeout=8) as resp:
+            return json.loads(resp.read().decode())
+    except Exception:
+        return {}
+
+
 def is_nous_free_tier(account_info: dict[str, Any]) -> bool:
     """Return True if the account info indicates a free (unpaid) tier.
 
@@ -1188,6 +1223,68 @@ def _format_price_per_mtok(per_token_str: str) -> str:
     return f"${per_m:.2f}"
 
 
+def format_model_pricing_table(
+    models: list[tuple[str, str]],
+    pricing_map: dict[str, dict[str, str]],
+    current_model: str = "",
+    indent: str = "      ",
+) -> list[str]:
+    """Build a column-aligned model+pricing table for terminal display.
+
+    Returns a list of pre-formatted lines ready to print.
+    *models* is ``[(model_id, description), ...]``.
+    """
+    if not models:
+        return []
+
+    # Build rows: (model_id, input_price, output_price, cache_price, is_current)
+    rows: list[tuple[str, str, str, str, bool]] = []
+    has_cache = False
+    for mid, _desc in models:
+        is_cur = mid == current_model
+        p = pricing_map.get(mid)
+        if p:
+            inp = _format_price_per_mtok(p.get("prompt", ""))
+            out = _format_price_per_mtok(p.get("completion", ""))
+            cache_read = p.get("input_cache_read", "")
+            cache = _format_price_per_mtok(cache_read) if cache_read else ""
+            if cache:
+                has_cache = True
+        else:
+            inp, out, cache = "", "", ""
+        rows.append((mid, inp, out, cache, is_cur))
+
+    name_col = max(len(r[0]) for r in rows) + 2
+    # Compute price column widths from the actual data so decimals align
+    price_col = max(
+        max((len(r[1]) for r in rows if r[1]), default=4),
+        max((len(r[2]) for r in rows if r[2]), default=4),
+        3,  # minimum: "In" / "Out" header
+    )
+    cache_col = max(
+        max((len(r[3]) for r in rows if r[3]), default=4),
+        5,  # minimum: "Cache" header
+    ) if has_cache else 0
+    lines: list[str] = []
+
+    # Header
+    if has_cache:
+        lines.append(f"{indent}{'Model':<{name_col}} {'In':>{price_col}}  {'Out':>{price_col}}  {'Cache':>{cache_col}}  /Mtok")
+        lines.append(f"{indent}{'-' * name_col} {'-' * price_col}  {'-' * price_col}  {'-' * cache_col}")
+    else:
+        lines.append(f"{indent}{'Model':<{name_col}} {'In':>{price_col}}  {'Out':>{price_col}}  /Mtok")
+        lines.append(f"{indent}{'-' * name_col} {'-' * price_col}  {'-' * price_col}")
+
+    for mid, inp, out, cache, is_cur in rows:
+        marker = "  ← current" if is_cur else ""
+        if has_cache:
+            lines.append(f"{indent}{mid:<{name_col}} {inp:>{price_col}}  {out:>{price_col}}  {cache:>{cache_col}}{marker}")
+        else:
+            lines.append(f"{indent}{mid:<{name_col}} {inp:>{price_col}}  {out:>{price_col}}{marker}")
+
+    return lines
+
+
 def fetch_models_with_pricing(
     api_key: str | None = None,
     base_url: str = "https://openrouter.ai/api",
@@ -2019,7 +2116,11 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
     # below — bedrock is not expected to appear in that table.
     if normalized == "bedrock":
         try:
-            from agent.bedrock_adapter import bedrock_model_ids_or_none
+            from agent.plugin_registries import registries
+            _bedrock_ns = registries.get_provider_namespace("bedrock")
+            bedrock_model_ids_or_none = _bedrock_ns.get("bedrock_model_ids_or_none")
+            if bedrock_model_ids_or_none is None:
+                raise ImportError("bedrock_model_ids_or_none not found in bedrock provider")
             ids = bedrock_model_ids_or_none()
             if ids is not None:
                 return ids
@@ -2266,7 +2367,14 @@ def _fetch_anthropic_models(timeout: float = 5.0) -> Optional[list[str]]:
     Claude Code auto-discovery).  Returns sorted model IDs or None.
     """
     try:
-        from agent.anthropic_adapter import resolve_anthropic_token, _is_oauth_token
+        from agent.plugin_registries import registries
+        _anthropic_ns = registries.get_provider_namespace("anthropic")
+        resolve_anthropic_token = _anthropic_ns.get("resolve_anthropic_token")
+        _is_oauth_token = _anthropic_ns.get("_is_oauth_token")
+        # Beta header constants live in core agent.anthropic_format.
+        from agent.anthropic_format import _COMMON_BETAS, _OAUTH_ONLY_BETAS, _CONTEXT_1M_BETA
+        if resolve_anthropic_token is None or _is_oauth_token is None:
+            raise ImportError("anthropic provider services not registered")
     except ImportError:
         return None
 
@@ -2278,7 +2386,6 @@ def _fetch_anthropic_models(timeout: float = 5.0) -> Optional[list[str]]:
     is_oauth = _is_oauth_token(token)
     if is_oauth:
         headers["Authorization"] = f"Bearer {token}"
-        from agent.anthropic_adapter import _COMMON_BETAS, _OAUTH_ONLY_BETAS, _CONTEXT_1M_BETA
         headers["anthropic-beta"] = ",".join(_COMMON_BETAS + _OAUTH_ONLY_BETAS)
     else:
         headers["x-api-key"] = token
@@ -3610,7 +3717,12 @@ def validate_requested_model(
     # AWS SDK control plane (ListFoundationModels + ListInferenceProfiles).
     if normalized == "bedrock":
         try:
-            from agent.bedrock_adapter import discover_bedrock_models, resolve_bedrock_region
+            from agent.plugin_registries import registries
+            _bedrock_ns = registries.get_provider_namespace("bedrock")
+            discover_bedrock_models = _bedrock_ns.get("discover_bedrock_models")
+            resolve_bedrock_region = _bedrock_ns.get("resolve_bedrock_region")
+            if discover_bedrock_models is None or resolve_bedrock_region is None:
+                raise ImportError("bedrock discovery functions not registered")
             region = resolve_bedrock_region()
             discovered = discover_bedrock_models(region)
             discovered_ids = {m["id"] for m in discovered}

hermes_cli/plugins.py

@@ -34,6 +34,7 @@ so plugin-defined tools appear alongside the built-in tools.
 from __future__ import annotations
 
 import asyncio
+import importlib
 import importlib.metadata
 import importlib.util
 import inspect
@@ -817,6 +818,270 @@ class PluginContext:
             name,
         )
 
+    # -- auth provider registration -------------------------------------------
+
+    def register_platform_entry(
+        self,
+        name: str,
+        adapter_class: type,
+        check_requirements: Callable,
+        available_flag: str = "",
+        constants: dict | None = None,
+        helper_functions: dict | None = None,
+    ) -> None:
+        """Register a platform adapter entry in the capability registries.
+
+        This populates ``agent.plugin_registries.registries.platform_adapters``
+        so core code can look up adapter classes, constants, and helper
+        functions without importing from ``hermes_agent_*`` packages directly.
+
+        Call this **in addition to** :meth:`register_platform` — the two
+        registries serve different consumers:
+
+        * ``register_platform``  → ``gateway.platform_registry``  (gateway
+          adapter creation, setup wizard, status)
+        * ``register_platform_entry`` → ``agent.plugin_registries`` (adapter
+          class access, constants, helpers for send_message_tool, etc.)
+
+        Args:
+            name: Platform identifier (e.g. ``"telegram"``).
+            adapter_class: The adapter class itself (e.g. ``TelegramAdapter``).
+            check_requirements: Callable returning ``bool`` — are deps installed?
+            available_flag: Name of the module-level AVAILABLE boolean, if any.
+            constants: Platform-specific constants (e.g.
+                ``{"FEISHU_DOMAIN": ..., "LARK_DOMAIN": ...}``).
+            helper_functions: Platform-specific helpers (e.g.
+                ``{"_strip_mdv2": _strip_mdv2, "qr_register": qr_register}``).
+        """
+        from agent.plugin_registries import registries, PlatformAdapterEntry
+
+        entry = PlatformAdapterEntry(
+            name=name,
+            adapter_class=adapter_class,
+            check_requirements=check_requirements,
+            available_flag=available_flag,
+            constants=constants or {},
+            helper_functions=helper_functions or {},
+        )
+        registries.register_platform(entry)
+        logger.debug(
+            "Plugin %s registered platform entry: %s",
+            self.manifest.name,
+            name,
+        )
+
+    def register_tool_provider_entry(
+        self,
+        name: str,
+        tool_functions: dict | None = None,
+        check_fn: Callable | None = None,
+        constants: dict | None = None,
+        config_functions: dict | None = None,
+        environment_classes: dict | None = None,
+    ) -> None:
+        """Register a tool provider entry in the capability registries.
+
+        This populates ``agent.plugin_registries.registries.tool_providers``
+        so core code can look up tool functions, constants, and config
+        helpers without importing from ``hermes_agent_*`` packages directly.
+
+        Args:
+            name: Tool identifier (e.g. ``"tts"``, ``"stt"``).
+            tool_functions: Dict of function name → callable
+                (e.g. ``{"text_to_speech_tool": text_to_speech_tool}``).
+            check_fn: Optional callable returning ``bool`` — are deps
+                installed and configured?
+            constants: Tool-specific constants
+                (e.g. ``{"MAX_FILE_SIZE": 25 * 1024 * 1024}``).
+            config_functions: Config/utility functions
+                (e.g. ``{"is_stt_enabled": is_stt_enabled}``).
+            environment_classes: Environment classes for terminal backends
+                (e.g. ``{"DaytonaEnvironment": DaytonaEnvironment}``).
+        """
+        from agent.plugin_registries import registries, ToolProviderEntry
+
+        entry = ToolProviderEntry(
+            name=name,
+            tool_functions=tool_functions or {},
+            check_fn=check_fn,
+            constants=constants or {},
+            config_functions=config_functions or {},
+            environment_classes=environment_classes or {},
+        )
+        registries.register_tool_provider(entry)
+        logger.debug(
+            "Plugin %s registered tool provider entry: %s",
+            self.manifest.name,
+            name,
+        )
+
+    def register_provider_services(
+        self,
+        name: str,
+        services: dict,
+    ) -> None:
+        """Register a namespace dict of provider-specific services.
+
+        This is the escape hatch for model-provider plugins that expose many
+        symbols (anthropic has 50+).  Each plugin registers its public surface
+        as a flat dict of ``{symbol_name: callable_or_value}``.  Core code
+        looks up specific symbols instead of importing from the plugin
+        package directly.
+
+        Args:
+            name: Provider identifier (e.g. ``"anthropic"``, ``"bedrock"``).
+            services: Dict of symbol name → callable or value.
+        """
+        from agent.plugin_registries import registries
+
+        registries.register_provider_services(name, services)
+        logger.debug(
+            "Plugin %s registered provider services: %s (%d symbols)",
+            self.manifest.name,
+            name,
+            len(services),
+        )
+
+    def register_auth_provider(
+        self,
+        name: str,
+        provider: Any,
+        *,
+        cli_group: str = "",
+        setup_subcommands: bool = False,
+    ) -> None:
+        """Register an authentication provider.
+
+        ``provider`` must implement the :class:`agent.plugin_registries.AuthProvider`
+        protocol (``name``, ``has_credentials``, ``check_env_vars``,
+        ``resolve_token``, ``refresh_token``).  It may also expose
+        provider-specific attributes (``_is_oauth_token``,
+        ``_HERMES_OAUTH_FILE``, ``read_claude_code_credentials``, etc.)
+        that core code accesses via the registry.
+
+        Registered providers are queried by core code via
+        ``registries.get_auth_provider(name)`` instead of importing
+        directly from ``hermes_agent_*`` packages.
+        """
+        from agent.plugin_registries import registries
+
+        registries.register_auth_provider(
+            name, provider,
+            cli_group=cli_group,
+            setup_subcommands=setup_subcommands,
+        )
+        logger.debug(
+            "Plugin %s registered auth provider: %s",
+            self.manifest.name, name,
+        )
+
+    def register_provider_resolver(
+        self,
+        name: str,
+        resolver: Any,
+    ) -> None:
+        """Register a provider resolver callable.
+
+        The resolver handles ALL provider-specific client construction
+        logic for auxiliary tasks.  Core's ``resolve_provider_client()``
+        dispatches to it instead of using per-provider if/elif branches.
+
+        Signature::
+
+            def resolver(
+                *,
+                model: str | None,
+                explicit_api_key: str | None,
+                explicit_base_url: str | None,
+                async_mode: bool,
+                is_vision: bool,
+                main_runtime: dict | None,
+                api_mode: str | None,
+            ) -> tuple[Any, str] | tuple[None, None]:
+                ...
+
+        Returns ``(client, default_model)`` or ``(None, None)``.
+        """
+        from agent.plugin_registries import registries
+
+        registries.register_provider_resolver(name, resolver)
+        logger.debug(
+            "Plugin %s registered provider resolver: %s",
+            self.manifest.name, name,
+        )
+
+    def register_transport(
+        self,
+        api_mode: str,
+        transport_cls: type,
+    ) -> None:
+        """Register a ProviderTransport class for an api_mode string.
+
+        This lets the transport registry discover provider transports
+        from plugins without core needing to import the plugin package.
+        """
+        from agent.plugin_registries import registries
+
+        registries._transports[api_mode] = transport_cls
+        logger.debug(
+            "Plugin %s registered transport: %s → %s",
+            self.manifest.name, api_mode, transport_cls.__name__,
+        )
+
+    def register_credential_pool_hook(
+        self,
+        name: str,
+        hook: Any,
+    ) -> None:
+        """Register a credential pool hook for provider-specific pool operations.
+
+        The hook should be a :class:`agent.plugin_registries.CredentialPoolHook`
+        instance with optional ``sync_from_credentials_file``,
+        ``refresh_oauth``, and ``should_include_in_pool`` callables.
+        """
+        from agent.plugin_registries import registries
+
+        registries.register_credential_pool_hook(name, hook)
+        logger.debug(
+            "Plugin %s registered credential pool hook: %s",
+            self.manifest.name, name,
+        )
+
+    def register_pricing_provider(
+        self,
+        name: str,
+        entries: list,
+    ) -> None:
+        """Register pricing entries for a provider.
+
+        ``entries`` should be a list of
+        :class:`agent.plugin_registries.PricingEntry` instances.
+        """
+        from agent.plugin_registries import registries
+
+        registries.register_pricing_provider(name, entries)
+        logger.debug(
+            "Plugin %s registered pricing provider: %s (%d entries)",
+            self.manifest.name, name, len(entries),
+        )
+
+    def register_provider_overlay(
+        self,
+        entry: Any,
+    ) -> None:
+        """Register a provider overlay entry.
+
+        ``entry`` should be a :class:`agent.plugin_registries.ProviderOverlayEntry`
+        instance.
+        """
+        from agent.plugin_registries import registries
+
+        registries.register_provider_overlay(entry)
+        logger.debug(
+            "Plugin %s registered provider overlay: %s",
+            self.manifest.name, entry.provider_name,
+        )
+
     # -- hook registration --------------------------------------------------
 
     # -- auxiliary task registration ---------------------------------------
@@ -1073,6 +1338,11 @@ class PluginManager:
         )
         logger.debug("  bundled/platforms: %d manifest(s)", len(bundled_platforms))
         manifests.extend(bundled_platforms)
+        bundled_providers = self._scan_directory(
+            repo_plugins / "model-providers", source="bundled"
+        )
+        logger.debug("  bundled/model-providers: %d manifest(s)", len(bundled_providers))
+        manifests.extend(bundled_providers)
 
         # 2. User plugins (~/.hermes/plugins/)
         user_dir = get_hermes_home() / "plugins"
@@ -1109,7 +1379,16 @@ class PluginManager:
         enabled = _get_enabled_plugins()  # None = opt-in default (nothing enabled)
         winners: Dict[str, PluginManifest] = {}
         for manifest in manifests:
-            winners[manifest.key or manifest.name] = manifest
+            key = manifest.key or manifest.name
+            existing = winners.get(key)
+            # Bundled/workspace plugins take precedence over entry-points
+            # for the same key — the local source is the one we're
+            # actively developing; the entry-point is the published
+            # version.  Only let entry-points fill gaps where no bundled
+            # version exists.
+            if existing is not None and existing.source == "bundled" and manifest.source != "bundled":
+                continue
+            winners[key] = manifest
         for manifest in winners.values():
             lookup_key = manifest.key or manifest.name
 
@@ -1137,30 +1416,12 @@ class PluginManager:
                 )
                 continue
 
-            # Model provider plugins are loaded by providers/__init__.py
-            # (its own lazy discovery keyed off first get_provider_profile()
-            # call). We record the manifest here for introspection but do
-            # not import the module — a second import would create two
-            # ProviderProfile instances and break the "last writer wins"
-            # override semantics between bundled and user plugins.
-            if manifest.kind == "model-provider":
-                loaded = LoadedPlugin(manifest=manifest, enabled=True)
-                self._plugins[lookup_key] = loaded
-                logger.debug(
-                    "Skipping '%s' (model-provider, handled by providers/ discovery)",
-                    lookup_key,
-                )
-                continue
-
-            # Built-in backends auto-load — they ship with hermes and must
-            # just work. Selection among them (e.g. which image_gen backend
-            # services calls) is driven by ``<category>.provider`` config,
-            # enforced by the tool wrapper.
-            #
-            # Bundled platform plugins (gateway adapters like IRC) auto-load
-            # for the same reason: every platform Hermes ships must be
-            # available out of the box without the user having to opt in.
-            if manifest.source == "bundled" and manifest.kind in {"backend", "platform"}:
+            # Model provider plugins auto-load just like backends and
+            # platforms. They register their provider services (auth,
+            # transport, metadata) via ctx.register_provider_services()
+            # in their register() function, which populates the
+            # capability registries that core code queries.
+            if manifest.source == "bundled" and manifest.kind in {"backend", "platform", "model-provider"}:
                 self._load_plugin(manifest)
                 continue
 

hermes_cli/plugins_cmd.py

@@ -10,7 +10,6 @@ rendered with Rich Markdown.  Otherwise a default confirmation is shown.
 from __future__ import annotations
 
 import functools
-import json
 import logging
 import os
 import shutil
@@ -811,29 +810,7 @@ def _discover_all_plugins() -> list:
     return list(seen.values())
 
 
-def _plugin_status(name: str, enabled: set, disabled: set) -> str:
-    """Return the user-facing activation state for a plugin name."""
-    if name in disabled:
-        return "disabled"
-    if name in enabled:
-        return "enabled"
-    return "not enabled"
-
-
-def _filter_plugin_entries(entries: list, args: Any, enabled: set, disabled: set) -> list:
-    """Apply ``hermes plugins list`` CLI filters."""
-    filtered = entries
-    if getattr(args, "no_bundled", False) or getattr(args, "user", False):
-        filtered = [entry for entry in filtered if entry[3] != "bundled"]
-    if getattr(args, "enabled", False):
-        filtered = [
-            entry for entry in filtered
-            if _plugin_status(entry[0], enabled, disabled) == "enabled"
-        ]
-    return filtered
-
-
-def cmd_list(args: Any | None = None) -> None:
+def cmd_list() -> None:
     """List all plugins (bundled + user) with enabled/disabled state."""
     from rich.console import Console
     from rich.table import Table
@@ -847,31 +824,6 @@ def cmd_list(args: Any | None = None) -> None:
 
     enabled = _get_enabled_set()
     disabled = _get_disabled_set()
-    entries = _filter_plugin_entries(entries, args, enabled, disabled)
-
-    if getattr(args, "json", False):
-        payload = [
-            {
-                "name": name,
-                "status": _plugin_status(name, enabled, disabled),
-                "version": str(version),
-                "description": description,
-                "source": source,
-            }
-            for name, version, description, source, _dir in entries
-        ]
-        print(json.dumps(payload, indent=2))
-        return
-
-    if getattr(args, "plain", False):
-        for name, version, _description, source, _dir in entries:
-            status = _plugin_status(name, enabled, disabled)
-            print(f"{status:12} {source:8} {str(version):8} {name}")
-        return
-
-    if not entries:
-        console.print("[dim]No plugins matched the selected filters.[/dim]")
-        return
 
     table = Table(title="Plugins", show_lines=False)
     table.add_column("Name", style="bold")
@@ -881,10 +833,9 @@ def cmd_list(args: Any | None = None) -> None:
     table.add_column("Source", style="dim")
 
     for name, version, description, source, _dir in entries:
-        status_name = _plugin_status(name, enabled, disabled)
-        if status_name == "disabled":
+        if name in disabled:
             status = "[red]disabled[/red]"
-        elif status_name == "enabled":
+        elif name in enabled:
             status = "[green]enabled[/green]"
         else:
             status = "[yellow]not enabled[/yellow]"
@@ -893,7 +844,6 @@ def cmd_list(args: Any | None = None) -> None:
     console.print()
     console.print(table)
     console.print()
-    console.print("[dim]Compact view:[/dim] hermes plugins list --plain --no-bundled")
     console.print("[dim]Interactive toggle:[/dim] hermes plugins")
     console.print("[dim]Enable/disable:[/dim] hermes plugins enable/disable <name>")
     console.print("[dim]Plugins are opt-in by default — only 'enabled' plugins load.[/dim]")
@@ -1160,7 +1110,7 @@ def _run_composite_ui(curses, plugin_names, plugin_labels, plugin_selected,
                 stdscr.addnstr(0, 0, "Plugins", max_x - 1, hattr)
                 stdscr.addnstr(
                     1, 0,
-                    "  ↑↓/j/k navigate  PgUp/PgDn page  SPACE toggle  ENTER configure/confirm  ESC done",
+                    "  \u2191\u2193 navigate  SPACE toggle  ENTER configure/confirm  ESC done",
                     max_x - 1, curses.A_DIM,
                 )
             except curses.error:
@@ -1200,9 +1150,7 @@ def _run_composite_ui(curses, plugin_names, plugin_labels, plugin_selected,
                         pass
                     y += 1
 
-                plugin_start = scroll_offset
-                plugin_stop = min(n_plugins, scroll_offset + max(visible_rows, 0))
-                for i in range(plugin_start, plugin_stop):
+                for i in range(n_plugins):
                     if y >= max_y - 1:
                         break
                     check = "\u2713" if i in chosen else " "
@@ -1260,16 +1208,6 @@ def _run_composite_ui(curses, plugin_names, plugin_labels, plugin_selected,
             elif key in {curses.KEY_DOWN, ord("j")}:
                 if total_items > 0:
                     cursor = (cursor + 1) % total_items
-            elif key in {curses.KEY_NPAGE, ord("f")}:
-                if total_items > 0:
-                    cursor = min(total_items - 1, cursor + max(1, max_y - 5))
-            elif key in {curses.KEY_PPAGE, ord("b")}:
-                if total_items > 0:
-                    cursor = max(0, cursor - max(1, max_y - 5))
-            elif key == curses.KEY_HOME:
-                cursor = 0
-            elif key == curses.KEY_END:
-                cursor = max(0, total_items - 1)
             elif key == ord(" "):
                 if cursor < n_plugins:
                     # Toggle general plugin
@@ -1711,7 +1649,7 @@ def plugins_command(args) -> None:
     elif action == "disable":
         cmd_disable(args.name)
     elif action in {"list", "ls"}:
-        cmd_list(args)
+        cmd_list()
     elif action is None:
         cmd_toggle()
     else:

hermes_cli/portal_cli.py

@@ -13,6 +13,7 @@ from __future__ import annotations
 
 import sys
 import webbrowser
+from typing import Optional
 
 from hermes_cli.colors import Colors, color
 from hermes_cli.config import load_config
@@ -22,6 +23,19 @@ SUBSCRIPTION_URL = "https://portal.nousresearch.com/manage-subscription"
 DOCS_URL = "https://hermes-agent.nousresearch.com/docs/user-guide/features/tool-gateway"
 
 
+def _nous_portal_base_url() -> str:
+    """Resolve the Portal base URL from auth state or default."""
+    try:
+        from hermes_cli.auth import get_nous_auth_status
+        status = get_nous_auth_status() or {}
+        url = status.get("portal_base_url")
+        if isinstance(url, str) and url.strip():
+            return url.rstrip("/")
+    except Exception:
+        pass
+    return DEFAULT_PORTAL_URL
+
+
 def _cmd_status(args) -> int:
     """Show Portal auth + Tool Gateway routing summary."""
     from hermes_cli.auth import get_nous_auth_status

hermes_cli/profile_describer.py

@@ -28,6 +28,7 @@ from __future__ import annotations
 
 import json
 import logging
+import os
 import re
 from dataclasses import dataclass
 from pathlib import Path

hermes_cli/profiles.py

@@ -940,6 +940,7 @@ def delete_profile(name: str, yes: bool = False) -> Path:
             ``sys.exc_info()`` tuple).
             """
             import stat as _stat
+            import sys as _sys
 
             # Normalise the two callback signatures:
             #   onexc(func, path, exc_instance)   — 3.12+

hermes_cli/providers.py

@@ -99,10 +99,8 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
         transport="openai_chat",
         extra_env_vars=("COPILOT_GITHUB_TOKEN", "GH_TOKEN"),
     ),
-    "anthropic": HermesOverlay(
-        transport="anthropic_messages",
-        extra_env_vars=("ANTHROPIC_TOKEN", "CLAUDE_CODE_OAUTH_TOKEN"),
-    ),
+    # "anthropic" overlay moved to plugin: hermes_agent_anthropic register()
+    # Plugin registers via ctx.register_provider_overlay() and core merges lazily.
     "zai": HermesOverlay(
         transport="openai_chat",
         extra_env_vars=("GLM_API_KEY", "ZAI_API_KEY", "Z_AI_API_KEY"),
@@ -204,17 +202,45 @@ HERMES_OVERLAYS: Dict[str, HermesOverlay] = {
     ),
     # Azure Foundry: supports both OpenAI-style and Anthropic-style endpoints.
     # The transport is determined at runtime from config.yaml model.api_mode.
-    "azure-foundry": HermesOverlay(
-        transport="openai_chat",  # default; overridden by api_mode in config
-        base_url_env_var="AZURE_FOUNDRY_BASE_URL",
-    ),
-    "bedrock": HermesOverlay(
-        transport="bedrock_converse",
-        auth_type="aws_sdk",
-    ),
+    # "azure-foundry" overlay moved to plugin: hermes_agent_azure register()
+    # "bedrock" overlay moved to plugin: hermes_agent_bedrock register()
+    # Plugins register via ctx.register_provider_overlay() and core merges lazily.
 }
 
 
+def _merge_plugin_overlays() -> None:
+    """Merge plugin-registered provider overlays into HERMES_OVERLAYS.
+
+    Called lazily from ``resolve_provider`` so that plugins have had a
+    chance to register by the time we need the overlay data.
+    """
+    global _plugin_overlays_merged
+    if _plugin_overlays_merged:
+        return
+    _plugin_overlays_merged = True
+    try:
+        from agent.plugin_registries import registries
+        for _name, _entry in registries.all_provider_overlays().items():
+            if _name not in HERMES_OVERLAYS:
+                HERMES_OVERLAYS[_name] = HermesOverlay(
+                    transport=_entry.transport,
+                    is_aggregator=_entry.is_aggregator,
+                    auth_type=_entry.auth_type,
+                    extra_env_vars=_entry.extra_env_vars,
+                    base_url_override=_entry.base_url_override,
+                    base_url_env_var=_entry.base_url_env_var,
+                )
+            # Also merge aliases from the plugin overlay entry
+            for _alias in _entry.aliases:
+                if _alias not in ALIASES:
+                    ALIASES[_alias] = _name
+    except Exception:
+        pass
+
+
+_plugin_overlays_merged = False
+
+
 # -- Resolved provider -------------------------------------------------------
 # The merged result of models.dev + overlay + user config.
 
@@ -335,11 +361,7 @@ ALIASES: Dict[str, str] = {
     "tencent-cloud": "tencent-tokenhub",
     "tencentmaas": "tencent-tokenhub",
 
-    # bedrock
-    "aws": "bedrock",
-    "aws-bedrock": "bedrock",
-    "amazon-bedrock": "bedrock",
-    "amazon": "bedrock",
+    # bedrock aliases moved to plugin: hermes_agent_bedrock register()
 
     # arcee
     "arcee-ai": "arcee",
@@ -426,6 +448,7 @@ def get_provider(name: str) -> Optional[ProviderDef]:
     except Exception:
         mdev_info = None
 
+    _merge_plugin_overlays()
     overlay = HERMES_OVERLAYS.get(canonical)
 
     if mdev_info is not None:

hermes_cli/proxy/adapters/base.py

@@ -69,11 +69,11 @@ class UpstreamAdapter(ABC):
 
     @abstractmethod
     def get_credential(self) -> UpstreamCredential:
-        """Return a fresh credential, refreshing or rotating if necessary.
+        """Return a fresh credential, refreshing/minting if necessary.
 
         Implementations should:
           - refresh the access token if it's near expiry
-          - rotate the upstream bearer key if it's near expiry
+          - mint/rotate the upstream bearer key if it's near expiry
           - persist any refreshed state back to disk
 
         Raises:
@@ -90,7 +90,8 @@ class UpstreamAdapter(ABC):
         """Return an alternate credential after an upstream auth failure.
 
         The default is no retry. Providers can override this for one-shot
-        fallback paths after the upstream rejects the first request.
+        fallback paths, such as switching from a preferred token type to a
+        legacy bearer after the upstream rejects the first request.
         """
         _ = failed_credential, status_code
         return None

hermes_cli/proxy/adapters/nous_portal.py

@@ -1,8 +1,13 @@
 """Nous Portal upstream adapter.
 
 Reads the user's Nous OAuth state from ``~/.hermes/auth.json`` through the
-shared runtime resolver, validates or refreshes the inference JWT, then exposes
-the upstream base URL plus bearer for the proxy server to forward to.
+shared runtime resolver, refreshes the access token and resolves the
+``agent_key`` compatibility credential when needed, then exposes the upstream
+base URL plus bearer for the proxy server to forward to.
+
+The ``agent_key`` field may hold either a NAS invoke JWT or the legacy
+opaque session key. The refresh helper handles both — see
+:func:`hermes_cli.auth.resolve_nous_runtime_credentials`.
 """
 
 from __future__ import annotations
@@ -14,6 +19,8 @@ from typing import Any, Dict, FrozenSet, Optional
 from hermes_cli.auth import (
     AuthError,
     DEFAULT_NOUS_INFERENCE_URL,
+    NOUS_INFERENCE_AUTH_MODE_AUTO,
+    NOUS_INFERENCE_AUTH_MODE_LEGACY,
     _load_auth_store,
     _auth_store_lock,
     _is_terminal_nous_refresh_error,
@@ -65,15 +72,17 @@ class NousPortalAdapter(UpstreamAdapter):
         state = self._read_state()
         if state is None:
             return False
-        # We need either a usable inference JWT OR (refresh_token + access_token)
-        # to recover. The refresh helper validates and refreshes as needed.
+        # We need either a usable agent_key OR (refresh_token + access_token)
+        # to recover. The refresh helper will mint/refresh as needed.
         return bool(
             state.get("agent_key")
             or (state.get("refresh_token") and state.get("access_token"))
         )
 
     def get_credential(self) -> UpstreamCredential:
-        return self._get_credential()
+        return self._get_credential(
+            inference_auth_mode=NOUS_INFERENCE_AUTH_MODE_AUTO,
+        )
 
     def get_retry_credential(
         self,
@@ -81,19 +90,16 @@ class NousPortalAdapter(UpstreamAdapter):
         failed_credential: UpstreamCredential,
         status_code: int,
     ) -> Optional[UpstreamCredential]:
-        _ = failed_credential
         if status_code != 401:
             return None
-        logger.info("proxy: Nous upstream rejected bearer; force-refreshing invoke JWT")
+        if failed_credential.bearer.count(".") != 2:
+            return None
+        logger.info("proxy: Nous upstream rejected bearer; retrying with legacy session key")
         return self._get_credential(
-            force_refresh=True,
+            inference_auth_mode=NOUS_INFERENCE_AUTH_MODE_LEGACY,
         )
 
-    def _get_credential(
-        self,
-        *,
-        force_refresh: bool = False,
-    ) -> UpstreamCredential:
+    def _get_credential(self, *, inference_auth_mode: str) -> UpstreamCredential:
         with self._lock:
             state = self._read_state()
             if state is None:
@@ -103,7 +109,7 @@ class NousPortalAdapter(UpstreamAdapter):
 
             try:
                 refreshed = resolve_nous_runtime_credentials(
-                    force_refresh=force_refresh,
+                    inference_auth_mode=inference_auth_mode,
                 )
             except AuthError as exc:
                 if _is_terminal_nous_refresh_error(exc):
@@ -125,10 +131,10 @@ class NousPortalAdapter(UpstreamAdapter):
                     f"Failed to refresh Nous Portal credentials: {exc}"
                 ) from exc
 
-            runtime_key = refreshed.get("api_key")
-            if not runtime_key:
+            agent_key = refreshed.get("api_key")
+            if not agent_key:
                 raise RuntimeError(
-                    "Nous Portal refresh did not return a usable inference JWT. "
+                    "Nous Portal refresh did not return a usable agent_key. "
                     "Try `hermes auth add nous` to re-authenticate."
                 )
 
@@ -139,7 +145,7 @@ class NousPortalAdapter(UpstreamAdapter):
             base_url = base_url.rstrip("/")
 
             return UpstreamCredential(
-                bearer=runtime_key,
+                bearer=agent_key,
                 base_url=base_url,
                 expires_at=refreshed.get("expires_at"),
             )

hermes_cli/proxy/server.py

@@ -12,6 +12,7 @@ or rewrite request/response bodies. It's a credential-attaching forwarder.
 from __future__ import annotations
 
 import asyncio
+import json
 import logging
 import signal
 from typing import Optional
@@ -104,6 +105,17 @@ def create_app(adapter: UpstreamAdapter) -> "web.Application":
             }
         )
 
+    async def handle_models_fallback(request: "web.Request") -> "web.Response":
+        # Most clients hit /v1/models on startup. If the upstream doesn't
+        # serve /models, synthesize a minimal response so clients don't
+        # crash. The actual forwarding path handles /models when allowed.
+        return web.json_response(
+            {
+                "object": "list",
+                "data": [],
+            }
+        )
+
     async def handle_proxy(request: "web.Request") -> "web.StreamResponse":
         # Extract the path *after* /v1
         rel_path = request.match_info.get("tail", "")

hermes_cli/pt_input_extras.py

@@ -81,40 +81,3 @@ def install_ctrl_enter_alias() -> int:
             ANSI_SEQUENCES[seq] = alt_enter
             changed += 1
     return changed
-
-
-def install_ignored_terminal_sequences() -> int:
-    """Map terminal-emitted noise sequences to ``Keys.Ignore`` so they
-    are consumed by the VT100 parser before they reach key bindings or
-    the input buffer.
-
-    Currently covers focus reports:
-      - ``\\x1b[I`` — terminal regained focus (focus in)
-      - ``\\x1b[O`` — terminal lost focus (focus out)
-
-    Ghostty, iTerm2, and some xterm builds can emit these sequences when
-    the user switches tabs / windows or when a multiplexer toggles focus
-    tracking upstream. prompt_toolkit does not map these by default, so
-    its parser falls back to literal key presses (ESC, ``[``, ``I``/``O``)
-    and inserts ``[I``/``[O`` into the prompt buffer after the ESC byte
-    is handled.
-
-    Registering them as ``Keys.Ignore`` is parser-level — strictly
-    cleaner than post-hoc regex stripping in the input sanitizer because
-    the bytes never reach the buffer. ``setdefault`` is used so any user
-    or downstream registration wins.
-
-    Returns the number of sequences whose mapping was changed.
-    """
-    try:
-        from prompt_toolkit.input.ansi_escape_sequences import ANSI_SEQUENCES
-        from prompt_toolkit.keys import Keys
-    except Exception:
-        return 0
-
-    changed = 0
-    for seq in ("\x1b[I", "\x1b[O"):
-        if seq not in ANSI_SEQUENCES:
-            ANSI_SEQUENCES[seq] = Keys.Ignore
-            changed += 1
-    return changed

hermes_cli/runtime_provider.py

@@ -976,11 +976,13 @@ def _resolve_azure_foundry_runtime(
             auth_mode = "api_key"
         else:
             try:
-                from agent.azure_identity_adapter import (
-                    EntraIdentityConfig,
-                    SCOPE_AI_AZURE_DEFAULT,
-                    build_token_provider,
-                )
+                from agent.plugin_registries import registries
+                _azure_ns = registries.get_provider_namespace("azure")
+                EntraIdentityConfig = _azure_ns.get("EntraIdentityConfig")
+                SCOPE_AI_AZURE_DEFAULT = _azure_ns.get("SCOPE_AI_AZURE_DEFAULT")
+                build_token_provider = _azure_ns.get("build_token_provider")
+                if not all([EntraIdentityConfig, SCOPE_AI_AZURE_DEFAULT, build_token_provider]):
+                    raise ImportError("azure provider services not fully registered")
             except Exception as exc:
                 raise AuthError(
                     "Azure Foundry Entra ID auth requires the 'azure-identity' "
@@ -1072,7 +1074,11 @@ def _resolve_explicit_runtime(
         base_url = explicit_base_url or cfg_base_url or "https://api.anthropic.com"
         api_key = explicit_api_key
         if not api_key:
-            from agent.anthropic_adapter import resolve_anthropic_token
+            from agent.plugin_registries import registries
+            _anthropic_ns = registries.get_provider_namespace("anthropic")
+            resolve_anthropic_token = _anthropic_ns.get("resolve_anthropic_token")
+            if resolve_anthropic_token is None:
+                raise ImportError("anthropic provider services not registered")
 
             api_key = resolve_anthropic_token()
             if not api_key:
@@ -1115,20 +1121,14 @@ def _resolve_explicit_runtime(
             explicit_base_url
             or str(state.get("inference_base_url") or auth_mod.DEFAULT_NOUS_INFERENCE_URL).strip().rstrip("/")
         )
-        # Only use the agent_key compatibility field for inference when it
-        # contains a NAS invoke JWT; raw OAuth access_token fallback is handled
-        # by resolve_nous_runtime_credentials().
-        api_key = explicit_api_key or (
-            str(state.get("agent_key") or "").strip()
-            if _agent_key_is_usable(
-                state,
-                max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800"))),
-            )
-            else ""
-        )
+        # Only use the agent_key compatibility field for inference. It may be
+        # either a NAS invoke JWT or a legacy opaque session key; raw OAuth
+        # access_token fallback is handled by resolve_nous_runtime_credentials().
+        api_key = explicit_api_key or str(state.get("agent_key") or "").strip()
         expires_at = state.get("agent_key_expires_at") or state.get("expires_at")
         if not api_key:
             creds = resolve_nous_runtime_credentials(
+                min_key_ttl_seconds=max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800"))),
                 timeout_seconds=float(os.getenv("HERMES_NOUS_TIMEOUT_SECONDS", "15")),
             )
             api_key = creds.get("api_key", "")
@@ -1315,11 +1315,12 @@ def resolve_runtime_provider(
                 or getattr(entry, "access_token", "")
             )
         # For Nous, the pool entry's runtime_api_key is the agent_key
-        # compatibility field. It must be an invoke JWT. The pool doesn't
+        # compatibility field: either an invoke JWT or legacy opaque key.
+        # The pool doesn't
         # refresh it during selection (that would trigger network calls in
         # non-runtime contexts like `hermes auth list`).  If the key is
         # expired, clear pool_api_key so we fall through to
-        # resolve_nous_runtime_credentials() which handles refresh.
+        # resolve_nous_runtime_credentials() which handles refresh + fallback.
         if provider == "nous" and entry is not None and pool_api_key:
             min_ttl = max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800")))
             nous_state = {
@@ -1343,6 +1344,7 @@ def resolve_runtime_provider(
     if provider == "nous":
         try:
             creds = resolve_nous_runtime_credentials(
+                min_key_ttl_seconds=max(60, int(os.getenv("HERMES_NOUS_MIN_KEY_TTL_SECONDS", "1800"))),
                 timeout_seconds=float(os.getenv("HERMES_NOUS_TIMEOUT_SECONDS", "15")),
             )
             return {
@@ -1516,7 +1518,11 @@ def resolve_runtime_provider(
                     "config.yaml model section at a custom env var."
                 )
         else:
-            from agent.anthropic_adapter import resolve_anthropic_token
+            from agent.plugin_registries import registries
+            _anthropic_ns = registries.get_provider_namespace("anthropic")
+            resolve_anthropic_token = _anthropic_ns.get("resolve_anthropic_token")
+            if resolve_anthropic_token is None:
+                raise ImportError("anthropic provider services not registered")
             token = resolve_anthropic_token()
             if not token:
                 raise AuthError(
@@ -1534,12 +1540,14 @@ def resolve_runtime_provider(
 
     # AWS Bedrock (native Converse API via boto3)
     if provider == "bedrock":
-        from agent.bedrock_adapter import (
-            has_aws_credentials,
-            resolve_aws_auth_env_var,
-            resolve_bedrock_region,
-            is_anthropic_bedrock_model,
-        )
+        from agent.plugin_registries import registries
+        _bedrock_ns = registries.get_provider_namespace("bedrock")
+        has_aws_credentials = _bedrock_ns.get("has_aws_credentials")
+        resolve_aws_auth_env_var = _bedrock_ns.get("resolve_aws_auth_env_var")
+        resolve_bedrock_region = _bedrock_ns.get("resolve_bedrock_region")
+        is_anthropic_bedrock_model = _bedrock_ns.get("is_anthropic_bedrock_model")
+        if not all([has_aws_credentials, resolve_aws_auth_env_var, resolve_bedrock_region, is_anthropic_bedrock_model]):
+            raise ImportError("bedrock provider services not fully registered")
         # When the user explicitly selected bedrock (not auto-detected),
         # trust boto3's credential chain — it handles IMDS, ECS task roles,
         # Lambda execution roles, SSO, and other implicit sources that our

hermes_cli/secrets_cli.py

@@ -14,8 +14,9 @@ import argparse
 import json
 import os
 import subprocess
+import sys
 from pathlib import Path
-from typing import List, Optional
+from typing import List, Optional, Tuple
 
 from rich.console import Console
 from rich.panel import Panel

hermes_cli/security_advisories.py

@@ -36,7 +36,7 @@ from __future__ import annotations
 import logging
 import os
 import sys
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from pathlib import Path
 from typing import Iterable, Optional
 

hermes_cli/security_audit.py

@@ -28,7 +28,7 @@ import urllib.error
 import urllib.request
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Iterable, Optional
+from typing import Any, Iterable, Optional
 
 from hermes_constants import get_hermes_home
 

hermes_cli/setup.py

@@ -12,6 +12,7 @@ Config files are stored in ~/.hermes/ for easy access.
 """
 
 import importlib.util
+import json
 import logging
 import os
 import re
@@ -781,6 +782,7 @@ def setup_model_provider(config: dict, *, quick: bool = False):
                         timeout=15.0,
                         insecure=False,
                         ca_bundle=None,
+                        min_key_ttl_seconds=5 * 60,
                     )
                 )
                 pool = load_pool(selected_provider)
@@ -2050,59 +2052,32 @@ def _setup_matrix():
             save_env_value("MATRIX_ENCRYPTION", "true")
             print_success("E2EE enabled")
 
-        matrix_pkg = "mautrix[encryption]" if want_e2ee else "mautrix"
-        # Use the central lazy-deps feature group so we install ALL of
-        # platform.matrix's dependencies (mautrix, Markdown, aiosqlite,
-        # asyncpg, aiohttp-socks) — not just mautrix itself.  The previous
-        # hand-rolled ``pip install mautrix[encryption]`` left asyncpg /
-        # aiosqlite uninstalled and broke E2EE connect with
-        # ``No module named 'asyncpg'`` on every fresh install (#31116).
+        matrix_pkg = "hermes-agent[matrix]"
+        # Matrix deps are now a proper plugin package. Install it the normal way.
         try:
-            from tools.lazy_deps import ensure as _lazy_ensure, feature_missing
-            _missing_before = feature_missing("platform.matrix")
-            if _missing_before:
-                print_info(
-                    f"Installing {matrix_pkg} (+ {len(_missing_before)} runtime deps)..."
-                )
-                try:
-                    _lazy_ensure("platform.matrix", prompt=False)
-                    print_success(f"{matrix_pkg} installed")
-                except Exception as exc:
-                    print_warning(
-                        f"Install failed — run manually: pip install "
-                        f"'mautrix[encryption]' asyncpg aiosqlite Markdown "
-                        f"aiohttp-socks"
-                    )
-                    print_info(f"  Error: {exc}")
+            __import__("hermes_agent_matrix")
         except ImportError:
-            # tools.lazy_deps unavailable (extreme edge case — partial
-            # install).  Fall back to the legacy single-package install
-            # path so the wizard still does *something*.
-            try:
-                __import__("mautrix")
-            except ImportError:
-                print_info(f"Installing {matrix_pkg}...")
-                import subprocess
-                uv_bin = shutil.which("uv")
-                if uv_bin:
-                    result = subprocess.run(
-                        [uv_bin, "pip", "install", "--python", sys.executable, matrix_pkg],
-                        capture_output=True, text=True,
-                    )
-                else:
-                    result = subprocess.run(
-                        [sys.executable, "-m", "pip", "install", matrix_pkg],
-                        capture_output=True, text=True,
-                    )
-                if result.returncode == 0:
-                    print_success(f"{matrix_pkg} installed")
-                else:
-                    print_warning(
-                        f"Install failed — run manually: pip install "
-                        f"'{matrix_pkg}' asyncpg aiosqlite Markdown aiohttp-socks"
-                    )
-                    if result.stderr:
-                        print_info(f"  Error: {result.stderr.strip().splitlines()[-1]}")
+            print_info(f"Installing {matrix_pkg}...")
+            import subprocess
+            uv_bin = shutil.which("uv")
+            if uv_bin:
+                result = subprocess.run(
+                    [uv_bin, "pip", "install", "--python", sys.executable, matrix_pkg],
+                    capture_output=True, text=True,
+                )
+            else:
+                result = subprocess.run(
+                    [sys.executable, "-m", "pip", "install", matrix_pkg],
+                    capture_output=True, text=True,
+                )
+            if result.returncode == 0:
+                print_success(f"{matrix_pkg} installed")
+            else:
+                print_warning(
+                    f"Install failed — run manually: pip install '{matrix_pkg}'"
+                )
+                if result.stderr:
+                    print_info(f"  Error: {result.stderr.strip().splitlines()[-1]}")
 
         print()
         print_info("🔒 Security: Restrict who can use your bot")
@@ -2974,6 +2949,7 @@ def _run_portal_one_shot(config: dict) -> None:
             timeout=None,
             insecure=False,
             ca_bundle=None,
+            min_key_ttl_seconds=5 * 60,
         )
         try:
             auth_add_command(ns)

hermes_cli/status.py

@@ -7,6 +7,7 @@ Shows the status of all Hermes Agent components.
 import os
 import sys
 import subprocess  # noqa: F401 — re-exported for tests that monkeypatch status.subprocess to guard against regressions
+import importlib.util
 from pathlib import Path
 
 PROJECT_ROOT = Path(__file__).parent.parent.resolve()

hermes_cli/stdio.py

@@ -216,6 +216,7 @@ def _augment_path_with_known_tools() -> None:
     if not is_windows():
         return
 
+    import shutil as _shutil
 
     local_appdata = os.environ.get("LOCALAPPDATA", "")
     if not local_appdata:

hermes_cli/voice.py

@@ -779,7 +779,9 @@ def speak_text(text: str) -> None:
     _debug(f"speak_text: TTS begin (paused_recording={paused_recording})")
 
     try:
-        from tools.tts_tool import text_to_speech_tool
+        from agent.plugin_registries import registries
+        _tts = registries.get_tool_provider("tts")
+        text_to_speech_tool = _tts.tool_functions.get("text_to_speech_tool") if _tts else None
 
         tts_text = text[:4000] if len(text) > 4000 else text
         tts_text = re.sub(r'```[\s\S]*?```', ' ', tts_text)             # fenced code blocks
@@ -806,6 +808,8 @@ def speak_text(text: str) -> None:
             f"tts_{time.strftime('%Y%m%d_%H%M%S')}.mp3",
         )
 
+        if text_to_speech_tool is None:
+            raise ImportError("TTS plugin not registered")
         _debug(f"speak_text: synthesizing {len(tts_text)} chars -> {mp3_path}")
         text_to_speech_tool(text=tts_text, output_path=mp3_path)
 

hermes_cli/web_server.py

@@ -58,22 +58,10 @@ try:
     from fastapi.staticfiles import StaticFiles
     from pydantic import BaseModel
 except ImportError:
-    # First try lazy-installing the dashboard extras. Only the user actually
-    # running `hermes dashboard` needs fastapi+uvicorn; lazy install keeps
-    # them out of every other install path. After install, re-import.
-    try:
-        from tools.lazy_deps import ensure as _lazy_ensure
-        _lazy_ensure("tool.dashboard", prompt=False)
-        from fastapi import FastAPI, HTTPException, Request, WebSocket, WebSocketDisconnect
-        from fastapi.middleware.cors import CORSMiddleware
-        from fastapi.responses import FileResponse, HTMLResponse, JSONResponse, Response
-        from fastapi.staticfiles import StaticFiles
-        from pydantic import BaseModel
-    except Exception:
-        raise SystemExit(
-            "Web UI requires fastapi and uvicorn.\n"
-            f"Install with: {sys.executable} -m pip install 'fastapi' 'uvicorn[standard]'"
-        )
+    raise SystemExit(
+        "Web UI requires fastapi and uvicorn.\n"
+        "Install with: pip install 'hermes-agent[dashboard]'"
+    )
 
 WEB_DIST = Path(os.environ["HERMES_WEB_DIST"]) if "HERMES_WEB_DIST" in os.environ else Path(__file__).parent / "web_dist"
 _log = logging.getLogger(__name__)
@@ -110,20 +98,17 @@ app.add_middleware(
 
 # ---------------------------------------------------------------------------
 # Endpoints that do NOT require the session token.  Everything else under
-# /api/ is gated by the auth middleware below.
-#
-# This list is defined in ``hermes_cli.dashboard_auth.public_paths`` so the
-# OAuth gate middleware can honour the same allowlist — keeping the two
-# gates in lockstep avoids drift like the wildcard-subdomain regression
-# where ``/api/status`` was public under the legacy gate but 401'd under
-# the OAuth gate (breaking the portal's liveness probe).
-#
-# Keep the upstream list minimal — only truly non-sensitive, read-only
-# endpoints belong there.
+# /api/ is gated by the auth middleware below.  Keep this list minimal —
+# only truly non-sensitive, read-only endpoints belong here.
 # ---------------------------------------------------------------------------
-from hermes_cli.dashboard_auth.public_paths import (
-    PUBLIC_API_PATHS as _PUBLIC_API_PATHS,
-)
+_PUBLIC_API_PATHS: frozenset = frozenset({
+    "/api/status",
+    "/api/config/defaults",
+    "/api/config/schema",
+    "/api/model/info",
+    "/api/dashboard/themes",
+    "/api/dashboard/plugins",
+})
 
 
 def _has_valid_session_token(request: Request) -> bool:
@@ -1374,11 +1359,13 @@ def _anthropic_oauth_status() -> Dict[str, Any]:
     The dashboard reports the highest-priority source that's actually present.
     """
     try:
-        from agent.anthropic_adapter import (
-            read_hermes_oauth_credentials,
-            read_claude_code_credentials,
-            _HERMES_OAUTH_FILE,
-        )
+        from agent.plugin_registries import registries
+        _anthropic = registries.get_provider_namespace("anthropic")
+        read_hermes_oauth_credentials = _anthropic.get("read_hermes_oauth_credentials")
+        read_claude_code_credentials = _anthropic.get("read_claude_code_credentials")
+        _HERMES_OAUTH_FILE = _anthropic.get("_HERMES_OAUTH_FILE")
+        if read_hermes_oauth_credentials is None:
+            raise ImportError("anthropic plugin not registered")
     except ImportError:
         read_claude_code_credentials = None  # type: ignore
         read_hermes_oauth_credentials = None  # type: ignore
@@ -1437,7 +1424,11 @@ def _claude_code_only_status() -> Dict[str, Any]:
     when they also have a separate Hermes-managed PKCE login.
     """
     try:
-        from agent.anthropic_adapter import read_claude_code_credentials
+        from agent.plugin_registries import registries
+        _anthropic = registries.get_provider_namespace("anthropic")
+        read_claude_code_credentials = _anthropic.get("read_claude_code_credentials")
+        if read_claude_code_credentials is None:
+            raise ImportError("anthropic plugin not registered")
         creds = read_claude_code_credentials()
     except Exception:
         creds = None
@@ -1623,8 +1614,10 @@ async def disconnect_oauth_provider(provider_id: str, request: Request):
     # want to undo a disconnect.
     if provider_id in {"anthropic", "claude-code"}:
         try:
-            from agent.anthropic_adapter import _HERMES_OAUTH_FILE
-            if _HERMES_OAUTH_FILE.exists():
+            from agent.plugin_registries import registries
+            _anthropic = registries.get_provider_namespace("anthropic")
+            _HERMES_OAUTH_FILE = _anthropic.get("_HERMES_OAUTH_FILE")
+            if _HERMES_OAUTH_FILE is not None and _HERMES_OAUTH_FILE.exists():
                 _HERMES_OAUTH_FILE.unlink()
         except Exception:
             pass
@@ -1691,13 +1684,15 @@ _oauth_sessions_lock = threading.Lock()
 # Guarded so hermes web still starts if anthropic_adapter is unavailable;
 # Phase 2 endpoints will return 501 in that case.
 try:
-    from agent.anthropic_adapter import (
-        _OAUTH_CLIENT_ID as _ANTHROPIC_OAUTH_CLIENT_ID,
-        _OAUTH_TOKEN_URL as _ANTHROPIC_OAUTH_TOKEN_URL,
-        _OAUTH_REDIRECT_URI as _ANTHROPIC_OAUTH_REDIRECT_URI,
-        _OAUTH_SCOPES as _ANTHROPIC_OAUTH_SCOPES,
-        _generate_pkce as _generate_pkce_pair,
-    )
+    from agent.plugin_registries import registries
+    _anthropic = registries.get_provider_namespace("anthropic")
+    _ANTHROPIC_OAUTH_CLIENT_ID = _anthropic.get("_OAUTH_CLIENT_ID")
+    _ANTHROPIC_OAUTH_TOKEN_URL = _anthropic.get("_OAUTH_TOKEN_URL")
+    _ANTHROPIC_OAUTH_REDIRECT_URI = _anthropic.get("_OAUTH_REDIRECT_URI")
+    _ANTHROPIC_OAUTH_SCOPES = _anthropic.get("_OAUTH_SCOPES")
+    _generate_pkce_pair = _anthropic.get("_generate_pkce")
+    if any(v is None for v in [_ANTHROPIC_OAUTH_CLIENT_ID, _ANTHROPIC_OAUTH_TOKEN_URL, _ANTHROPIC_OAUTH_REDIRECT_URI, _ANTHROPIC_OAUTH_SCOPES, _generate_pkce_pair]):
+        raise ImportError("anthropic plugin not registered")
     _ANTHROPIC_OAUTH_AVAILABLE = True
 except ImportError:
     _ANTHROPIC_OAUTH_AVAILABLE = False
@@ -1735,7 +1730,11 @@ def _save_anthropic_oauth_creds(access_token: str, refresh_token: str, expires_a
     Mirrors what auth_commands.add_command does so the dashboard flow leaves
     the system in the same state as ``hermes auth add anthropic``.
     """
-    from agent.anthropic_adapter import _HERMES_OAUTH_FILE
+    from agent.plugin_registries import registries
+    _anthropic = registries.get_provider_namespace("anthropic")
+    _HERMES_OAUTH_FILE = _anthropic.get("_HERMES_OAUTH_FILE")
+    if _HERMES_OAUTH_FILE is None:
+        raise ImportError("anthropic plugin not registered")
     payload = {
         "accessToken": access_token,
         "refreshToken": refresh_token,
@@ -1898,7 +1897,8 @@ async def _start_device_code_flow(provider_id: str) -> Dict[str, Any]:
     """
     if provider_id == "nous":
         from hermes_cli.auth import (
-            _request_device_code,
+            _nous_device_scope_with_env_override,
+            _request_nous_device_code_with_scope_fallback,
             PROVIDER_REGISTRY,
         )
         import httpx
@@ -1909,21 +1909,22 @@ async def _start_device_code_flow(provider_id: str) -> Dict[str, Any]:
             or pconfig.portal_base_url
         ).rstrip("/")
         client_id = pconfig.client_id
-        scope = pconfig.scope
+        scope, explicit_scope = _nous_device_scope_with_env_override(
+            None,
+            default_scope=pconfig.scope,
+        )
 
         def _do_nous_device_request():
             with httpx.Client(
                 timeout=httpx.Timeout(15.0),
                 headers={"Accept": "application/json"},
             ) as client:
-                return (
-                    _request_device_code(
-                        client=client,
-                        portal_base_url=portal_base_url,
-                        client_id=client_id,
-                        scope=scope,
-                    ),
-                    scope,
+                return _request_nous_device_code_with_scope_fallback(
+                    client=client,
+                    portal_base_url=portal_base_url,
+                    client_id=client_id,
+                    scope=scope,
+                    allow_legacy_fallback=not explicit_scope,
                 )
 
         device_data, effective_scope = await asyncio.get_running_loop().run_in_executor(
@@ -2065,6 +2066,7 @@ async def _start_device_code_flow(provider_id: str) -> Dict[str, Any]:
 def _nous_poller(session_id: str) -> None:
     """Background poller that drives a Nous device-code flow to completion."""
     from hermes_cli.auth import (
+        NOUS_INFERENCE_AUTH_MODE_FRESH,
         _poll_for_token,
         refresh_nous_oauth_from_state,
     )
@@ -2090,7 +2092,7 @@ def _nous_poller(session_id: str) -> None:
                 expires_in=expires_in,
                 poll_interval=interval,
             )
-        # Same post-processing as _nous_device_code_login (validate/refresh JWT)
+        # Same post-processing as _nous_device_code_login (mint agent key)
         now = datetime.now(timezone.utc)
         token_ttl = int(token_data.get("expires_in") or 0)
         auth_state = {
@@ -2110,8 +2112,10 @@ def _nous_poller(session_id: str) -> None:
         }
         full_state = refresh_nous_oauth_from_state(
             auth_state,
+            min_key_ttl_seconds=300,
             timeout_seconds=15.0,
             force_refresh=False,
+            inference_auth_mode=NOUS_INFERENCE_AUTH_MODE_FRESH,
         )
         from hermes_cli.auth import persist_nous_credentials
         persist_nous_credentials(full_state)
@@ -3346,6 +3350,7 @@ async def get_models_analytics(days: int = 30):
 # ---------------------------------------------------------------------------
 
 import re
+import asyncio
 
 # PTY bridge is POSIX-only (depends on fcntl/termios/ptyprocess).  On native
 # Windows the import raises; catch and leave PtyBridge=None so the rest of