The change classifier treated package.json / package-lock.json as
python-irrelevant, so a lockfile-only PR skipped the Python lane entirely.
But several Python invariant tests read these files (assistant-ui tap cluster,
electron pin, lazy-deps, lockfile churn) — so a lockfile change can break the
Python suite. #63970 merged green (Python skipped on the PR) then reddened main
(push fails open and runs everything).
Drop root npm from the _py_irrelevant denylist so lockfile changes run Python,
honoring the classifier's own contract: never skip a lane a change could break.
Root npm still triggers the frontend lane as before.
Community reports of GPT 'infinitely thinking' are usually a slow or
overloaded provider plus silent retry machinery: the CLI/TUI/Desktop
spinner shows a generic 'cogitating...' verb for the whole wait and the
gateway heartbeat says only 'Working — N min'.
Add AIAgent._emit_wait_notice(): rewrites the live spinner/status line
(thinking_callback → CLI prompt_toolkit widget, thinking.delta → TUI +
Desktop) and updates the activity tracker (included in the gateway's
'⏳ Working — N min' heartbeat). Wired at the four wait points:
- non-streaming wait loop: after 30s with no response, the line becomes
'⏳ waiting on <model> — Ns with no response yet (provider may be slow
or overloaded; auto-reconnect at Ns)'
- streaming wait loop: same explanation after 30s with no chunks,
including the long-thinking case
- TTFB / stale-stream kills: '⚠ no response from provider in Ns —
reconnecting...'
- Codex continuation retries: '↻ model returned reasoning with no final
answer — asking it to continue (n/3)' instead of silence
Notices are fail-open (display errors never break the wait loop) and
gateway sessions without a display callback still get the improved
activity description.
Follow-up to the salvaged #63690: when the interim assistant message is
too empty to append (no content and no reasoning of any kind), the last
message in history is still the prior user/tool turn — appending the
user-role nudge there would create a user→user or tool→user sequence
that strict providers reject. Only append the nudge when the last
message is an assistant turn. Also add IpastorSan to AUTHOR_MAP.
grok-4.x on the xAI /v1/responses surface sometimes ends a turn with only
reasoning items — no message output item, no tool calls — and those
reasoning items carry no encrypted_content. Two compounding problems:
1. The model occasionally emits its final answer INSIDE the reasoning
channel, delimited by grok's internal "<response>" tag. The answer
exists but is classified reasoning-only → finish_reason=incomplete.
2. An interim assistant message holding only plain-text reasoning replays
as nothing in _chat_messages_to_responses_input, so every continuation
request is byte-identical to the one that just failed. The model
deterministically repeats the reasoning-only response until the retry
budget is exhausted and the turn dies with "Codex response remained
incomplete after 3 continuation attempts".
Fixes:
- _normalize_codex_response (xai_responses only): salvage the
<response>-delimited tail from the reasoning text and promote it to
assistant content; the untagged prefix stays as thinking text.
- Codex-incomplete continuation path: when the interim message has
nothing the input converter will replay (no content, no encrypted
reasoning items, no message items), append a user-role nudge so the
retry actually differs and explicitly asks for the final answer /
pending tool call. Mirrors the existing _get_continuation_prompt
pattern used for length truncation.
Observed live with grok-4.20 on xai-oauth (2026-07-13); sibling of the
grok-composer web_search incomplete-loop fix in transports/codex.py.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The #64434 change makes unrecognized issuers trust
response.status='completed' for reasoning-only turns, so this sibling
test (which exercised the old default-path behavior) now pins the Codex
backend explicitly — the surface where reasoning-only still means
'still thinking'.
Follow-up to the salvaged #64449: the status-trusting branch flipped
github_responses to 'stop' alongside unknown relays. Copilot fronts the
same OpenAI model family as codex_backend and shows the same
reasoning-only 'still thinking' degeneration, so it stays on the
continuation path. Only unrecognized (other:*) backends trust
response.status='completed' as terminal.
The aggregator is MoA's acting model, but the main loop's reasoning
gates key off the virtual moa://local identity and never fire — so with
no per-slot reasoning_effort the aggregator silently ran at the backend
default, ignoring the user's reasoning config entirely (#64187).
New _aggregator_reasoning_config(): slot value > full acting-model
resolution via the shared chokepoint (agent.reasoning_overrides for the
slot's model > global agent.reasoning_effort; YAML False stays
'disabled'). Applied to both aggregator call sites (acting turn +
one-shot /moa synthesis).
Reference advisors intentionally keep slot-or-default: inheriting a
global xhigh into every advisor fan-out would silently multiply cost.
Fixes#64187.
The remote model catalog (website/static/api/model-catalog.json) now labels
exactly one entry per provider block with "default": true — z-ai/glm-5.2 for
both OpenRouter and Nous Portal. That labeled entry is the model Hermes
silently lands on when the user never picked one, and it can be rotated by
editing the manifest alone: no release needed.
- model_catalog.py: get_default_model_from_cache() reads the label from the
in-process/disk cache only — never triggers a network fetch, so hot
resolution paths (agent build, gateway session setup) stay network-free.
- models.py: get_preferred_silent_default_model() resolves catalog label
first, PREFERRED_SILENT_DEFAULT_MODEL constant second (offline/fresh
install). _PROVIDER_SILENT_DEFAULT_OVERRIDES dict replaced by
_SILENT_DEFAULT_PROVIDERS routing through the shared resolver.
fetch_openrouter_models() preserves the "default" badge through live
/v1/models refreshes so the picker shows it.
- scripts/build_model_catalog.py: generator emits the default label so
regeneration can't drop it.
- website/docs/reference/model-catalog.md: schema documents the new field.
- Salvaged from PR #61141 (@HumphreySun98): bare-provider /model switches
(/model nous) route through the cost-safe default instead of curated
entry [0].
- tests: catalog-label precedence, constant fallback, stale-label fallback,
cache-only (no network) guarantee, and a shipped-manifest contract test
pinning the labeled entry to PREFERRED_SILENT_DEFAULT_MODEL.
E2E (temp HERMES_HOME): fresh-install constant fallback, shipped-manifest
label read, release-free rotation (relabeled cache -> new default across
models.py, tui_gateway, and gateway empty-model paths) all verified.
`detect_static_provider_for_model` handles a bare provider name typed as a
model (e.g. `/model nous`) by returning `_PROVIDER_MODELS[provider][0]` — the
first curated entry. For metered aggregators whose curated list is ordered
most-capable-first (Nous Portal), entry [0] is the priciest flagship, so
`/model nous` silently switched to it.
This is exactly the billing footgun `_PROVIDER_SILENT_DEFAULT_OVERRIDES` /
`get_default_model_for_provider` exist to prevent (per their docstring, a
missing model "escalated to Opus and billed 863 requests before the user
noticed"). The non-interactive fallback already routes through that cost-safe
helper; the interactive `/model <provider>` path did not.
Route this path through `get_default_model_for_provider` too. Providers
without a silent-default override are unchanged (the helper returns
`models[0]`), so only overridden providers (currently `nous`) change — from
the flagship to the low-cost default.
Adds regression tests: `/model nous` resolves to the cost-safe default, and
non-overridden providers still resolve to their first catalog model.
Consolidation follow-up on top of @liuwei666888's compressor fix (#52431)
and @Frowtek's ACP render guard (#62588) — completes the class fix across
every display-layer consumer of tool-call arguments:
- agent/context_compressor.py: wrap _summarize_tool_result in a
never-raises backstop (same pattern as get_cute_tool_message and the
ACP guard). The per-branch _str_arg coercions keep summaries
informative; the wrapper guarantees compression can never crash-loop
on a summary branch we didn't anticipate. Also reject non-dict parsed
args (a JSON list/scalar would crash every args.get call).
- agent/display.py: build_tool_preview's process branch sliced
session_id/data without coercion — crashed build_tool_preview and
build_tool_label on the live tool-progress callback (probed live:
TypeError 'int' object is not subscriptable). Coerce like the
sibling branches.
- tests: backstop fuzz matrix (16 tools x 6 hostile value shapes),
fallback-shape contracts, display process-preview regressions,
non-dict args guard.
build_tool_start renders every ACP (Zed) tool call — on the live tool-progress
callback (acp_adapter/events.py) and during session history replay
(acp_adapter/server.py). It called build_tool_title and extract_locations
directly, so a model that emits a malformed argument crashed the render:
- terminal `command` as null/number -> TypeError (len() in build_tool_title)
- delegate_task `goal` as a number -> TypeError (len())
- read_file `path` as a non-string -> pydantic ValidationError building a
ToolCallLocation
A live crash breaks the tool-call event; a persisted one breaks history replay
on every resume of that session. The sibling CLI label builder
get_cute_tool_message was already wrapped for exactly this reason
(agent/display.py: "display must never abort a turn").
Wrap build_tool_start the same way: on any builder failure, fall back to a
minimal, valid start event (tool name as title, resolved kind). The happy path
is unchanged.
Adds tests for the non-string command, path, and goal cases.
When LLMs return non-string parameter values (e.g. bool, int) in tool call
arguments, _summarize_tool_result() crashes with TypeError because it calls
len(), .count(), or slicing directly on args.get() return values.
This causes an infinite crash loop in the TUI — context compression
triggers on session resume, which crashes, which restarts, which triggers
compression again.
Add _str_arg() helper that coerces any value to str, and use it in all 5
vulnerable call sites:
- terminal: len(cmd)
- write_file: content.count()
- delegate_task: len(goal)
- execute_code: len(code)
- vision_analyze: question[:50]
* test: deflake async-delegation interrupt test under CI load
test_interrupt_all_signals_running_children failed twice on a loaded CI
worker: the blocker's ev.wait(timeout=5) expired before interrupt_all()
ran, the record finalized on its own, and interrupt_all() found nothing
running (n == 0, interrupted count 0 — the exact CI assertion failure,
reproduced locally by inserting a 5.6s dispatch->interrupt gap).
Raise the internal safety timeouts from 5s to 60s across the file's
gated runners — they exist only as runaway guards (every test releases
its gate explicitly); the pytest-level timeout is the real backstop.
Same flake class as the removed test_crashed_runner_produces_error_
completion (#64431).
* test: fix cross-test completion-event leak (second flake mechanism)
The first CI failure was the 5s guard-timeout race; the rerun exposed a
SECOND mechanism with a different signature: 'completed' == 'interrupted'.
Prior tests (e.g. test_dispatch_rejected_at_capacity) release their gate
and return immediately, but their workers finalize asynchronously — on a
loaded runner the teardown drain races the in-flight _finalize, and the
straggler 'completed' events leak into the NEXT test's queue, where
_drain_one() picks one up instead of the interrupt event. Reproduced
locally: gate release + immediate drain + 0.15s finalize delay leaked 2
events.
Fixes:
- teardown waits (bounded 2s) for active workers to finalize before
draining, so events land in the owning test
- the interrupt test matches its OWN delegation_id via _drain_for()
instead of taking whatever event arrives first
The 0.14 upgrade (#63970) dropped the @assistant-ui/store override, so the
whole cluster de-hoisted from root node_modules into apps/desktop/node_modules
under a single shared tap@0.9.3. The test only looked at the root hoist path
(node_modules/@assistant-ui/tap), which no longer exists, and failed on main.
Resolve tap wherever npm places it (root or workspace-nested), and assert a
single shared version across all install sites — strengthening the invariant to
also catch a split tap install, not just split declared ranges.
The assistant-ui upgrade lockfile omitted standalone @esbuild/* packages.
CI runs npm ci --ignore-scripts, so esbuild's postinstall never runs and
desktop/ui-tui check (build:ink, bundle-electron-main) fail without them.
Graft the 26 platform packages from main's lockfile.
@assistant-ui/react 0.14 makes respondToApproval required on
ToolCallMessagePartProps; the settledClarifyProps helper still lacked it
after the upgrade cherry-picks, so tsc failed on clarify-tool.test.tsx.
a reader of this subclass can't recover from hermes code alone that the metadata.isOptimistic flag drives core's off-branch eviction and export() omission, so a future core change to it would silently break placeholder cleanup. flagged in the upgrade review.
lock the four behaviors the built-in normalizeMathDelimiters/escapeCurrencyDollars introduce over the deleted custom helpers: $$<digit>$$ display math stays intact, double-backslash brackets and [/math]/[/inline] tag pairs rewrite to dollar delimiters, and currency dollars in prose are escaped. the existing preprocessMarkdown suite had no math cases.
the parseIncompleteMarkdown comment implied the reveal frontier is repaired; repair runs on the full accumulated text, so reword it to say that. drop the now-dead "multiple surfaces render the same content" clause from the block-cache comment (the smooth and defer wrappers that caused it were removed), and trim the math-preprocess comment to the load-bearing prose-only constraint.
@assistant-ui/store renamed its index-out-of-bounds throw from tapClientLookup/tapClientResource to useClientLookup in the 0.14 upgrade, so the boundary's /tapClient.../ filter stopped matching and re-threw the transient session-switch and reconnect race to root, blanking the app. broaden the regex to accept the new prefix (keeping the old one for older store versions) and point the test at the real message so it exercises the live path instead of the dead string.
delete the custom rewriteLatexBracketDelimiters and escapeCurrencyDollars
implementations from markdown-preprocess.ts (~40 lines). the built-in
exports from @assistant-ui/react-streamdown 0.3.4 are strict
improvements:
- normalizeMathDelimiters combines rewriteLatexBracketDelimiters (now
handles double backslashes and trims body whitespace) with
rewriteCustomMathTags (handles [/math]...[/math] and
[/inline]...[/inline] tags that some models emit — new capability
HA didn't have before)
- escapeCurrencyDollars excludes $ as a preceding character, so
display math $$5 is no longer incorrectly escaped (bugfix)
the call site in preprocessMarkdown changes from
rewriteLatexBracketDelimiters(escapeCurrencyDollars(part)) to
normalizeMathDelimiters(escapeCurrencyDollars(part)).
verified: tsc 0 errors, eslint clean, all 16 preprocessMarkdown tests
pass (including currency dollar escaping), vitest 0 new failures,
manual verification of currency amounts, LaTeX bracket delimiters,
display math, and dollar signs inside code blocks.
delete lib/remend-tail.ts (108 lines) and lib/remend-tail.test.ts (105
lines). the tailBoundedRemend export from @assistant-ui/react-streamdown
0.3.4 is algorithmically identical — same findRemendWindowStart boundary
scan, same fence/math tracking, same slice-and-repair strategy. the only
differences are improvements: the built-in handles \r (CR) in line
endings for Windows compatibility, and accepts an optional RemendOptions
parameter passed through to remend.
the import in markdown-text.tsx moves from @/lib/remend-tail to
@assistant-ui/react-streamdown. the call site
(preprocessWithTailRepair) is unchanged.
verified: tsc 0 errors, eslint clean, vitest 0 new failures (15
pre-existing, 786 passing — 6 fewer than before because the deleted
remend-tail.test.ts had 6 cases), manual verification of incomplete
markdown repair during streaming.
delete SmoothStreamingText, DeferStreamingText, and useSmoothReveal
(~174 lines) from markdown-text.tsx. the built-in defer and smooth
props on StreamdownTextPrimitive now handle the same work:
- defer: routes streaming text through useDeferredValue so markdown
re-parsing runs at lower priority (typing/scrolling stay responsive)
- smooth: typewriter-style reveal via useSmooth with SmoothOptions
{ drainMs: 500, maxCharsPerFrame: 30, minCommitMs: 33 }, matching
the old useSmoothReveal constants exactly
MarkdownTextContent (reasoning text) gets both defer and smooth.
MarkdownText (assistant text) gets defer only, matching the previous
behavior where text messages had no typewriter effect.
the internal pipeline order changes from smooth → defer → preprocess
to preprocess → smooth → defer (the built-in primitive runs preprocess
first). this is functionally equivalent: the tail-bounded remend repair
runs once on the full text instead of per revealed prefix, and the
smooth reveal operates on already-repaired markdown. end result is
identical.
verified: tsc 0 errors, eslint clean, vitest 0 new failures (15
pre-existing, 792 passing), manual verification of 6 streaming
scenarios (defer, smooth reveal, typing-while-streaming, code blocks,
math, long text performance).
bumps @assistant-ui/react from ^0.12.28 to ^0.14.23 and
@assistant-ui/react-streamdown from ^0.1.11 to ^0.3.4. this crosses
two minor bumps on each package and unlocks the built-in defer, smooth,
and tail-bounded remend primitives for PR 2.
breaking change from core 0.2.x: MessageRepository.appendOptimisticMessage
was removed (assistant-ui#4162). inline the three steps it did (generateId
+ fromThreadMessageLike + addOrUpdateMessage) in
incremental-external-store-runtime.ts, and set metadata.isOptimistic so
the new off-branch eviction logic cleans up the placeholder correctly.
fromThreadMessageLike and generateId graduated to the public API in
0.14.22 (assistant-ui#4414), so they now import from @assistant-ui/react
instead of @assistant-ui/core/internal. ExportedMessageRepository in the
test file moves to the public import for the same reason. the remaining
internal imports (AssistantRuntimeImpl, BaseAssistantRuntimeCore,
ExternalStoreThreadListRuntimeCore, ExternalStoreThreadRuntimeCore,
hasUpcomingMessage) are runtime construction internals with no public
equivalent and stay on @assistant-ui/core/internal.
the @assistant-ui/store npm override is removed: all transitive ranges
now resolve to 0.2.18 without it.
verified: tsc --noEmit passes, vitest shows zero new failures (15
pre-existing, 792 passing, identical to baseline before the upgrade).
The chat_completions path raises EmptyStreamError when a stream yields
no chunks and no finish_reason (#64420). _call_anthropic() had no
equivalent, and the eventless failure surfaces differently by client:
- Real Anthropic SDK: no message_start means no final-message snapshot,
so get_final_message() raises a bare AssertionError — not in the
retry loop's transient set, so it burned no retries and surfaced raw.
- OpenAI-compat shims: may fabricate a contentless Message with no
stop_reason (or return None), flowing out as a 'successful' empty turn.
Track whether any stream event arrived and normalize both shapes to
EmptyStreamError, giving the anthropic path the same transient retry
budget in the shared _call() retry loop. A real completed response
always carries a stop_reason, so the guard cannot fire on legitimate
turns (including eventless mocks with stop_reason='end_turn').
Follow-up to #64420.
An exhausted EmptyStreamError previously reported 'Connection to provider
failed' — misleading, since the connection succeeded (stream opened) and
the provider simply sent nothing. Add a dedicated third branch so users
debugging a misconfigured endpoint aren't sent chasing network issues.
Follow-up to #64420.
Three-layer companion to the salvaged CLI drain-ownership fix (#64240):
1. restore_undelivered_completions stamps restored=True (in-memory only)
on every durable completion re-enqueued at process start.
2. drain_notifications' legacy unfiltered branch re-queues restored
events instead of consuming them — a fresh process can no longer
adopt a dead session's delegation results (#64484). Same-process
keyless events keep the legacy behavior.
3. delegate_tool's async dispatch now falls back to the parent agent's
durable session_id when the approval-context key resolves empty (the
CLI case), so the CLI's new positive-ownership drain can actually
claim its own completions instead of failing closed on ''.
Review finding on the salvaged collector: _wait_for_process is the shared
drain for EVERY env.execute() consumer, not just the terminal tool. Applying
tool_output.max_bytes there silently truncated file-operation cat reads
(read_file_raw feeds the patch engine — read-modify-write on any file >50KB
would corrupt it), paginated read_file, code-execution RPC reads, and log
reads.
bounded_capture is now an explicit opt-in on execute()/_wait_for_process,
set only by the foreground terminal tool. Default preserves the historical
full-fidelity capture via an effectively-unbounded collector (single code
path). Modal transports accept the kwarg for signature parity.
New regression test: default execute() returns a 200KB payload complete and
untruncated. E2E: 20MB internal read intact; ShellFileOperations
read_file_raw round-trips byte-exact; terminal path still bounded at 50KB.
Follow-up to @michaelHMK's cherry-picked fix for #50892:
- agent/tool_dispatch_helpers.py: guard the segment planner's except-path
debug log against non-string arguments (the planner replaced the old
_should_parallelize_tool_batch body after #64460 and inherited the same
latent arguments[:200] slice).
- tests: the PR's executor-coercion hunks were dropped as redundant —
both executors now route through _parse_tool_arguments, which already
rejects null/non-object args with a structured error result instead of
coercing to {} (the 'we do not repair bad model outputs' contract).
Reworked the salvaged tests to pin the current behavior: None args are
rejected without dispatch, valid siblings still run, the planner treats
them as a barrier without raising, and the mainline run_conversation
path (which normalizes None to '{}' before dispatch) stays crash-free
under verbose logging.
Review nit from verification: the comment claimed newer FastMCP accepts a
JSON schema kwarg — the installed SDK's add_tool has no such parameter; the
synthesized __signature__ is what drives schema generation on both paths.
Fixes#64025
The hermes-tools MCP server was fetching each tool's JSON schema
into params_schema but never passing it to FastMCP's add_tool(),
so all published tools had an empty **kwargs signature. MCP clients
couldn't see parameters and arguments were dropped at dispatch.
This fix:
- Adds _signature_from_schema() to convert JSON schemas to Python
function signatures with type annotations
- Attaches the generated signature/annotations to each handler closure
so FastMCP introspects the real parameter structure
- Filters out None values before dispatch to avoid forwarding unset
optional parameters
Impact: web_search, browser automation, vision, and other Hermes tools
are now properly callable from the codex_app_server runtime.
Salvaged from #32340 by @LeonSGP43, adapted to the workspace-scoped
status tracking that landed in #63709:
- /stop with no running agent now best-effort clears the platform
status indicator, so a phantom 'is thinking...' left by a gateway
restart or a turn that died without a final send can always be
dismissed (#32295).
- SlackAdapter.stop_typing clears an untracked thread when the caller
names it explicitly in metadata — clearing an unset status is a
harmless no-op on Slack's side. The fallback is skipped when multiple
Slack Connect workspaces track the same channel+thread and no team_id
is given, preserving #63709's cross-workspace safety guarantee.
The upstream migration to inference.nousresearch.com broke routing for
inference-api.nousresearch.com. Restore the correct base_url and drop
the stale alias match in _is_nous_inference_route().
Fixes#60715
The read-only premise only holds on Python 3.13+ where the full PTB request
MRO is slotted. CI runs 3.11/3.12 where BaseRequest instances still carry a
__dict__, so the unconditional pytest.raises failed. The behavioral half of
the test (subclass re-tag instruments and records) runs everywhere.
Adds a __slots__ request double that has no instance __dict__, mirroring
PTB's HTTPXRequest shape on Python 3.13. The test asserts the old
instance monkey-patch is rejected as read-only and that
_instrument_polling_request instead re-tags the class and still records
getUpdates progress. Fails on the pre-fix adapter with the exact
"'do_request' is read-only" AttributeError from the report.
PTB's HTTPXRequest/BaseRequest use __slots__. On Python 3.13 their
instances no longer carry a __dict__, so the getUpdates progress
instrumentation's `request.do_request = wrapper` monkey-patch raises
`AttributeError: 'HTTPXRequest' object attribute 'do_request' is
read-only`, failing every Telegram connect (#64482). It only worked on
Python 3.12, where the instance still had a __dict__ — the Docker image
ships Python 3.13, so the release broke Telegram outright.
Re-tag the request to a thin `__slots__ = ()` subclass that overrides
do_request instead of mutating the instance. This preserves the exact
progress-observation semantics, works on both 3.12 and 3.13, and covers
the real request and the test doubles alike.
When a user starts a chat without ever selecting a model (GUI Chat App
onboarding, provider-set-but-model-missing config, empty model.default),
every silent fallback path resolved to the first curated catalog entry —
anthropic/claude-fable-5, the priciest flagship. Users were silently
billed for the most expensive model without opting in.
- hermes_cli/models.py: add PREFERRED_SILENT_DEFAULT_MODEL (z-ai/glm-5.2)
+ pick_silent_default_model() helper; point the nous silent-default
override at it and add an openrouter override (previously resolved to
"" and let downstream paths land on the flagship).
- hermes_cli/web_server.py: /api/model/recommended-default (the endpoint
the Desktop onboarding confirm card reads) now picks GLM-5.2 when the
provider's list carries it instead of blindly taking entry [0].
- tui_gateway/server.py: _resolve_model()'s last-resort literal was
anthropic/claude-sonnet-4; now PREFERRED_SILENT_DEFAULT_MODEL.
- tests: update empty-model fallback tests for the new contract.
The just-merged auxiliary.<task>.reasoning_effort shorthand applied
ensemble-wide to MoA (one value for every advisor) — wrong granularity.
Per-slot preset config supersedes it:
moa:
presets:
deep_review:
reference_models:
- {provider: ..., model: ..., reasoning_effort: low}
- {provider: ..., model: ..., reasoning_effort: xhigh}
aggregator:
{provider: ..., model: ..., reasoning_effort: high}
- Remove reasoning_effort from the moa_reference/moa_aggregator
DEFAULT_CONFIG blocks; _get_task_extra_body now warns-and-ignores the
key on MoA tasks, pointing at the preset config
- Guard tests: MoA aux blocks must not regrow the key; task-level value
is rejected with the pointer warning
- Docs: configuration.md notes the MoA exception and links the MoA page
Add patterns 30-34: forced metaphors/figurative overwriting, dramatic fragmentation and punchy kickers, rhetorical questions answered immediately, sentence-opener tics, and reassurance kickers. These cover structural/rhythm tells the existing 29 patterns miss (short subjectless dramatic fragments, cutesy aphorisms, rhetorical Q-and-A).
Add a 'marketing and blog cliches' list to pattern 7 for the business/LinkedIn register (game-changer, circle back, deep dive, moving forward, ...) that the Wikipedia-derived vocabulary list does not catch.
Edit the skill's own instructional prose to follow its own guidance: remove em dashes and negative parallelism from the narration so the skill models the writing it asks for. Before/After examples are left intact so the demonstrations still show the tells.
Update the pattern count (29 -> 34) and the attribution note to mark 30-34 and the pattern-7 additions as Hermes additions beyond the blader/humanizer source.
Phase 3 of relay-channel-context (gateway/agent side, single PR). The
connector (gateway-gateway #122/#123/#124) now attaches read-only
surrounding channel/group context to an addressed relay turn; this wires
the gateway to consume it.
- descriptor.py: additive optional supports_context (default False) on
CapabilityDescriptor. from_json already filters unknown keys, so this is
back-compat both directions within contract_version 1.
- ws_transport.py: _event_from_wire maps the connector's read-only
context[] array into the EXISTING MessageEvent.channel_context field via
a new _render_relay_context() helper — reusing the same read-only
injection path history-backfill uses (run.py prepends channel_context
ahead of the trigger message). Never raises; absent/empty/malformed ->
channel_context unset (byte-identical to today).
- docs/relay-connector-contract.md: document supports_context in the §2
descriptor table (fixes the contract-doc conformance test) + the
context/context_error inbound fields in §3.
- tests: descriptor default/round-trip/forward-compat; _render_relay_context
rendering + malformed-safe; _event_from_wire context->channel_context
mapping + the read-only invariant (trigger text untouched).
RELAY-ONLY: only gateway/relay/* + the shared MessageEvent consumption via
its existing channel_context field. No native adapter touched.
The inbound cron-fire verifier constructed a fresh PyJWKClient on every
fire, discarding the client's key cache and forcing a synchronous JWKS
HTTP GET to the portal on each fire. Under a burst of concurrent fires
(a hosted instance with several cron jobs firing in the same window) this
fanned out into N simultaneous JWKS fetches that the portal rate-limited
(HTTP 403 -> verification fails -> agent 401), or that blocked the event
loop long enough that the fire webhook could not return its 202 before
the relay's 30s timeout (observed in prod as relay 504s concentrated on
high-job-count instances).
Cache one PyJWKClient per JWKS URL at module scope (double-checked lock)
so the signing keys are reused across fires; NAS keys rotate rarely, so
the steady state is zero JWKS fetches per fire.
Regression test proves 5 fires -> 1 client construction (was 5).
Every auxiliary task block (vision, web_extract, compression,
title_generation, curator, background_review, moa_reference, ...) now
accepts a reasoning_effort shorthand:
auxiliary:
compression:
reasoning_effort: low
vision:
reasoning_effort: none
_get_task_extra_body() folds it into extra_body.reasoning, which every
auxiliary wire already translates: chat.completions passes it through,
the Codex Responses adapter maps it to top-level reasoning/include, and
the Anthropic auxiliary adapter now forwards it into
build_anthropic_kwargs(reasoning_config=...) (previously hardcoded None).
An explicit extra_body.reasoning on the same task wins over the
shorthand. Invalid levels are ignored with a warning. Empty string
(the shipped default) is a no-op — zero behavior change.
Config: reasoning_effort added to all 16 auxiliary task blocks in
DEFAULT_CONFIG (no version bump — deep-merge handles new keys).
Follow-ups on top of #64061's salvage:
- ResourceLink markers now point at mcp__<server>__read_resource (the
actual registered tool name via mcp_prefixed_tool_name) instead of a
nonexistent <server>_read_resource the agent could hallucinate-call.
- The isError path now surfaces EmbeddedResource .resource.text blocks
instead of dropping them, so error payloads carried in resources no
longer collapse to a bare 'MCP tool returned an error'. (Same-class
fix flagged in #64061 and independently addressed in #63576 by
@alauer.)
- 3 new error-path tests + updated ResourceLink wire-name assertion.
MCP tool results with non-image binary resources (PDFs, archives, office
docs) were silently dropped: the success path only handled TextContent and
ImageContent, so a PDF-returning MCP tool appeared to return metadata only.
- EmbeddedResource blob contents are decoded (50MB cap), materialized into
the Hermes document cache via cache_document_from_bytes (sanitized
filename, traversal-safe), and surfaced as a local-path marker the agent
can read with file/terminal tools.
- EmbeddedResource text contents are inlined directly.
- ResourceLink blocks preserve the URI and point the agent at the server's
read_resource tool; no arbitrary network fetch outside the MCP session.
- AudioContent blocks are cached via cache_audio_from_bytes as MEDIA: tags.
- read_resource blob contents are materialized the same way instead of
returning '[binary data, N bytes]'.
- Unsupported blocks are logged instead of silently discarded.
- Existing ImageContent MEDIA: behavior unchanged.
Reported by an enterprise customer; reproduced against an HTTP MCP server
returning application/pdf resources.
Slack's June 30 Agent messaging experience changelog lists Bolt Python
1.29.0 / Python SDK 3.43.0 as the Agent View minimums. Bump the
messaging/slack extras and the platform.slack lazy-install pins to
match, and regenerate uv.lock. All adapter API surfaces verified
present against the new versions in a clean venv.
The docs state feedback_buttons requires rich_blocks: true, but
_maybe_blocks rendered full Block Kit whenever feedback_buttons alone
was enabled — implicitly turning on rich-block rendering the user never
opted into. Align the code with the documented contract and add a
regression test.
The faint statue backdrop behind the transcript was only switchable via
the DEV-only leva panel. Add a persisted Appearance toggle (default on)
so users can hide it; the Backdrop simply skips rendering when off.
The terminal environment is shared process-globally (collapsed to the
default key), so env.cwd tracks the LAST session that ran a command.
_resolve_command_cwd() trusted env.cwd unconditionally — no ownership
check — so when session A left env.cwd pointing at A's checkout,
session B's first terminal command inherited A's stale cwd and ran in
the wrong workspace.
The file tools already solved this exact shared-env problem with
_live_cwd_if_owned() checking env.cwd_owner. The terminal tool never
got the same guard.
Fix: capture env.cwd_owner BEFORE the current session claims it, and
pass it as prev_owner to _resolve_command_cwd. When the previous owner
was a different session, env.cwd is stale — fall through to default_cwd
(the config/override cwd for this session) instead. Once the session
has claimed the env, subsequent calls in the same session still trust
env.cwd so in-session state survives.
A model response containing several parallel-safe reads plus one unsafe
tool used to lose ALL concurrency: _should_parallelize_tool_batch was
all-or-nothing, so a single barrier call (terminal, clarify, unknown
tool, malformed args) forced the entire batch onto the sequential path.
_plan_tool_batch_segments now splits the batch into ordered segments:
maximal contiguous runs of parallel-safe calls execute on the existing
concurrent path, barrier calls on the sequential path, strictly in the
model's emission order. Invariants preserved:
- one tool result per call, appended in emission order (segments are
contiguous, so no result reordering across a barrier)
- side-effect boundaries: no call starts before an earlier barrier ends
- overlapping file targets split into separate ordered parallel runs
- turn-end budget enforcement + /steer injection run exactly once per
batch (segment executors run with finalize=False; the segmented
dispatcher owns the whole-turn finalize)
- interrupt during segment k drains segments k+1..n with cancelled
results, keeping one result per tool_call_id
Homogeneous batches keep their original single-path dispatch (zero
behavior delta); _should_parallelize_tool_batch remains as a thin view
over the planner for existing callers and tests.
Two test mocks stubbed the old zero-arg signature; the chokepoint refactor
added an optional model param that call sites now pass. Swept the full test
tree for other stale stubs of the changed functions — the rest use
MagicMock/patch(return_value=...), which tolerate the new arg.
Collapse the six per-surface copies of override-then-global resolution
(CLI startup, gateway, TUI, cron, /model switch, fallback activation)
onto one shared resolve_reasoning_config() in hermes_constants.
Also fixes the gateway resolving reasoning against config model.default
instead of the session's effective model: after a session-only /model
switch, the switched model's override now applies (gateway message paths
pass the resolved session model through _resolve_session_reasoning_config;
/reasoning status reads the session model override).
Cleanup: drop docs/PER_MODEL_REASONING.md (duplicates the website docs
page), drop the change-detector _config_version test (no bump needed —
deep-merge handles new keys), remove a stale plan-reference comment.
Adds chokepoint contract tests (13) and gateway session-effective-model
regression tests (2).
Add agent.reasoning_overrides dict to config.yaml. Users can now set
a reasoning_effort per model, overriding the global agent.reasoning_effort.
Example:
agent:
reasoning_effort: "medium" # global default
reasoning_overrides:
"openrouter/anthropic/claude-opus-4.5": "xhigh"
"openai/gpt-5": "low"
"claude-sonnet-4.6": "high" # bare model name also works
The helper is spelling-tolerant: override keys match regardless of
provider prefix or dots-vs-dashes normalization, so users can write
keys in any sensible form and they'll match.
Resolution priority:
1. Session-scoped /reasoning --session override (gateway only; unchanged)
2. Per-model override from agent.reasoning_overrides (spelling-tolerant)
3. Global agent.reasoning_effort (existing)
4. Provider default (unchanged)
Wired into:
- CLI startup (cli.py)
- Messaging gateway agent construction (gateway/run.py)
- Desktop/TUI _load_reasoning_config (tui_gateway/server.py)
- Cron job scheduler (cron/scheduler.py)
- /model mid-session switch (agent/agent_runtime_helpers.py)
+ _primary_runtime now tracks reasoning_config for correct fallback recovery
- Fallback activation (agent/chat_completion_helpers.py::try_activate_fallback)
+ Re-resolves reasoning_config for the fallback model (best-effort)
Closes#21256 (per-model reasoning_effort defaults).
Note: no hermes config set agent.reasoning_overrides.<model> support;
users edit the YAML directly. _set_nested splits on "." and would
corrupt model keys containing version dots.
Review findings from the 4-angle pass:
- Unknown-but-enabled effort levels now collapse to Solar's strongest
(high) instead of silently downgrading to the medium default — guards
against the next #62650-style vocabulary addition. Explicit-empty
effort keeps the medium default.
- fallback_models test now asserts the behavior contract (non-empty, no
denied families) instead of freezing the exact model tuple
(change-detector, AGENTS.md reject reason).
- Drop unused pytest import in test_upstage_provider.py.
Main added max/ultra effort levels (#62650) after this PR branched;
without the mapping 'ultra' silently fell through to the medium default.
Matches the xhigh/max collapse-to-strongest convention used by other
profiles.
PROVIDER_REGISTRY, its alias map, and CANONICAL_PROVIDERS all auto-extend
from registered ProviderProfiles since the provider-modules refactor
(20a4f79ed). Verified with real imports: registry entry, 'solar' alias
resolution via resolve_provider(), and the picker entry are identical
with the manual entries removed. The hermes_cli/providers.py overlay
stays (models.dev has a stale /v1/solar base URL and no UPSTAGE_BASE_URL
var), and the manual OPTIONAL_ENV_VARS entries stay (non-advanced key +
curated prompt text, matching the fireworks convention).
Pin the Upstage default to the concrete solar-pro3 instead of the
solar-pro rolling alias:
- plugin fallback_models is now ("solar-pro3",); entry [0] is the setup default
- drop the "solar-pro" context-window fallback entry (solar-pro3 covers it)
- update the reasoning default-on docstring and profile tests accordingly
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Remove the `solar-open2-preview` context-window entry; `solar-open2`
covers the Open 2 family at the same 256K window.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
`UPSTAGE_API_KEY` / `UPSTAGE_BASE_URL` were wired through the provider
resolver, auth registry, and the EnvPage grouping, but never added to
`OPTIONAL_ENV_VARS` in hermes_cli/config.py. The dashboard/desktop
Providers page builds its list from that catalog (`/api/env` iterates
`OPTIONAL_ENV_VARS`), so with no entry the keys were never emitted and
"Upstage Solar" never rendered — the EnvPage prefix group stayed empty.
Add both keys under `category: "provider"` (matching gmi/minimax) so they
show up in `hermes dashboard` / `hermes desktop` under "Upstage Solar".
Adds a regression test asserting the catalog contains them, mirroring the
existing GMI coverage.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Invert the reasoning-support check from an allow-list (solar-pro,
solar-open) to a deny-list of the known non-reasoning families
(solar-mini, syn-pro). Newly released Solar models now get
reasoning_effort by default instead of having it silently dropped.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Adds Upstage Solar as a bundled model-provider plugin. Solar exposes an
OpenAI-compatible chat-completions endpoint at https://api.upstage.ai/v1, so
the generic chat_completions transport handles request/response/streaming/tool
calls — the profile is the core integration.
Provider registration (Upstage isn't in models.dev, so each registry that does
not auto-wire from the plugin layer needs an explicit entry — same pattern as
nvidia/gmi):
- plugins/model-providers/upstage/: UpstageProfile + plugin.yaml. Picker default
and offline catalog list only the agentic Solar Pro models, led by `solar-pro`
(rolling alias for the latest Pro). default_aux_model empty so aux tasks use
the main model. `solar` alias. UPSTAGE_BASE_URL overrides the host.
- hermes_cli/providers.py: HERMES_OVERLAYS + label + `solar` alias, so
resolve_provider_full('upstage') resolves (without this, an explicit
`provider: upstage` in config was dropped and fell through to auto-detect).
- hermes_cli/auth.py: PROVIDER_REGISTRY entry + `solar` alias, so `hermes
doctor` / resolve_provider recognise upstage (the static-registry path the
lazy profile-extension doesn't reliably cover at validation time).
- hermes_cli/models.py: CANONICAL_PROVIDERS entry places Upstage Solar in the
curated picker order (above the auto-appended `custom`).
- agent/model_metadata.py: context-window fallbacks (/v1/models omits
context_length); `solar-pro` carries the 128K Pro context as the catch-all.
Reasoning: UpstageProfile.build_api_kwargs_extras wires Solar's top-level
`reasoning_effort` (low|medium|high; xhigh/max→high). Reasoning-capable families
are solar-pro* and solar-open*; solar-mini/syn-pro never receive it. Defaults ON
at medium when unset (matches the /reasoning "medium (default)" label);
`/reasoning none` disables; explicit/saved settings are honored. No
reasoning_content echo handling needed (unlike DeepSeek/Kimi).
Web dashboard:
- web/src/pages/EnvPage.tsx: add an "Upstage Solar" provider group so
UPSTAGE_API_KEY / UPSTAGE_BASE_URL appear under LLM Providers (not "Other").
Docs/tests:
- .env.example: documents UPSTAGE_API_KEY / UPSTAGE_BASE_URL.
- tests: profile wiring, reasoning_effort mapping (pro/open/mini, efforts,
disabled, default-on), provider-resolver regression (resolve_provider_full /
get_provider / solar alias / overlay), `solar-pro` default.
Testing: pytest tests/providers tests/plugins/model_providers
tests/hermes_cli/test_upstage_provider.py tests/run_agent/test_provider_parity.py
tests/hermes_cli/test_api_key_providers.py; ruff clean. Verified end-to-end:
`hermes doctor` shows "Upstage Solar", and live chat works via both
`--provider upstage` and `--provider solar`. Reasoning wire format per
https://console.upstage.ai/api/docs/for-agents/raw. Platforms tested: macOS.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Follow-up to the cherry-picked empty-user-turn drop: the placeholder
introduced in 8582f35d9 fired for whitespace-only STRING turns too
(content=' ' flattens to non-stripping text but isn't in the
(None, '', []) exclusion set), fabricating an attachment note for a turn
that carried nothing. Gate the placeholder on isinstance(content, list)
so only genuinely structured (e.g. image-only) turns get it; empty and
whitespace-only string turns now fall through to the drop path.
Edge cases verified: trailing empty user turn still ends the view on the
synthetic advisory marker; an all-empty transcript degenerates to [].
MoA's _reference_messages() unconditionally appended every user-role
message to the advisory view sent to reference models, even when the
message content was an empty string or a non-string/multimodal payload
that the text-extraction step flattens to "".
Strict providers (Kimi/Moonshot, and others that enforce non-empty user
content) reject such a message with:
400 Invalid request: the message at position N with role 'user'
must not be empty
Lenient providers (DeepSeek) accept it, so an identical rendered view
passes on one reference and 400s on another within the same fan-out —
the user sees "kimi doesn't support MoA" when the real cause is an empty
user turn leaking into the advisory transcript.
Skip empty user turns, mirroring the existing behavior for empty
assistant turns (which are already dropped when they carry no parts).
The end-on-user invariant is preserved: the synthetic advisory-request
user turn is still appended when the view would otherwise end on an
assistant turn.
Adds a regression test asserting the advisory view contains no empty
user turn and still ends on a user turn.
After #53825's fix removed the auto-rich table bypass from
_rich_delivery_enabled(), _content_is_pipe_table_primary() had zero
callers. Remove it and simplify _rich_delivery_enabled() to the bare
rich_messages opt-in check (content param no longer used).
The platform hint in PLATFORM_HINTS['telegram'] always encouraged rich
Markdown constructs (tables, task lists, math, collapsible details) even
when rich_messages: false (the default). This caused the agent to produce
formatting that MarkdownV2 cannot render, especially broken on Telegram Web.
Split the hint into a base hint (MarkdownV2-compatible) and a
TELEGRAM_RICH_MESSAGES_HINT extension. The extension is conditionally
appended in system_prompt.py only when
platforms.telegram.extra.rich_messages is true.
Fixes#57122
Remove the pipe-table bypass from _rich_delivery_enabled() so that
rich_messages: false is fully honoured. Previously, pipe tables were
auto-routed to sendRichMessage regardless of the config flag, breaking
delivery on clients without Bot API 10.1 support (AyuGram, Telegram
Web, some desktop clients).
Fixes#53824
Flaked 3 times today across 3 unrelated PRs (#64321, #64319, #64409),
on two different CI shards (slice 1 and slice 8), while passing
deterministically on local runs of the same SHAs. The test polls
process_registry.completion_queue for 5s waiting for a daemon-thread
completion event; since the durable completion delivery work
(67f4e1b4a, d0e9a42ce) the crashed-runner path also writes through the
sqlite-backed persistence layer, and on slow CI runners the in-memory
enqueue can lose the 5s race.
Coverage note: the durable-delivery suite in this file covers the
completed-runner and submit-failure paths through persistence, but not
a runner that raises mid-flight — that specific path loses its direct
test with this removal. A deterministic (non-racing) replacement can
follow separately if wanted.
* fix(desktop): clear stale compaction status
Clear the compaction phase when a turn resumes with model or tool activity, and key response timers by session and turn so switching chats preserves elapsed time.\n\nSupersedes #48115 by porting its resumed-content approach to the current split stream hook and covering tool-first resumptions.\n\nCo-authored-by: liuhao1024 <sunsky.lau@gmail.com>
* fix(desktop): resume after thinking activity
* fix(desktop): clear turn timer on stop
CI test slices don't install python-telegram-bot (optional dep), causing
a ModuleNotFoundError on collection. Add pytest.importorskip('telegram')
before the PTB imports.
Review follow-up to the reasoning_config cache-parity fix:
- Only inherit the parent's reasoning_config when the fork runs on the
parent's model (not routed). On the routed aux path
(auxiliary.background_review.{provider,model}) the cache is cold
regardless, so parity buys nothing, and the parent's effort vocabulary
can be invalid for the routed model/provider: OpenRouter
extra_body.reasoning.effort is forwarded unclamped
(chat_completions.py) and codex_responses only maps max/ultra for
gpt-5.6 — an exotic parent effort routed to a strict provider could
400 the review. Mirrors the existing 'not _routed' gate on
_cached_system_prompt / session_start three lines below.
- Add a routed-path regression test asserting reasoning_config is
omitted from the fork kwargs when _resolve_review_runtime returns
routed=True.
- Extract the four copy-pasted recorder stubs in
test_background_review_cache_parity.py into a single
_make_recorder_class() factory so a new fork attribute needs one stub
edit, not four.
PR #17276 painstakingly pinned `_cached_system_prompt`, `session_start`,
`session_id`, and the toolset config on the background-review fork so its
outbound request body would byte-match the parent's and hit Anthropic's
exact-prefix cache. The contributor measured a ~26% end-to-end cost
reduction on Sonnet 4.5.
That optimization is currently being silently undone by a missing
`reasoning_config` kwarg. The fork's `AIAgent(...)` call omits it, so the
fork's `reasoning_config` defaults to `None`. `anthropic_adapter.build_anthropic_kwargs`
(line ~2165) then short-circuits the `thinking` / `output_config` block,
and the fork's request body lands in a DIFFERENT Anthropic cache namespace
from the parent's.
Result on the wire: 0 `cache_read_input_tokens`, full `cache_creation_input_tokens`
of the entire parent prefix — every single background review.
7 days of midagent.db traffic from one host running stock Hermes against
Anthropic Sonnet:
```
Background-review FIRST calls (the moment a review fork is born):
count = 68
cache_write tokens = 7,004,297
cache_read tokens = 1,016,335
Cost on Sonnet ($3.75/M write vs $0.30/M read):
Spent on these writes: $26.27
Cost if they had hit parent cache instead: $2.10
WASTED: $24.16 / week / user
```
That is from one user. Multiply by Hermes's installed base for the full
impact.
Tested against api.anthropic.com directly (see refs/api-tests/ in the
attached investigation repo if needed):
| pair | cache_r | cache_w |
|---------------------------------------------|---------|---------|
| parent fresh | 0 | 24,047 |
| parent same again | 24,047 | 0 |
| fork: appends 2 new tail msgs, thinking ON | 24,047 | 22 |
| fork: appends 2 new tail msgs, thinking OFF | 0 | 24,047 |
Same fork-shape request, only difference is `thinking`. With the fix,
the fork hits the parent's full prefix and only writes the delta
(the `Review the conversation above…` prompt block, ~3-5K tokens).
One line in `agent/background_review.py`: pass
`reasoning_config=getattr(agent, "reasoning_config", None)` to the
`AIAgent(...)` constructor of the review fork. A short comment block
above it explains why so the next person who reads this code doesn't
re-introduce the regression.
`tests/run_agent/test_background_review_cache_parity.py` already covers
the system-prompt / session-id / toolset-config parity contracts that
PR #17276 introduced. I added:
* a `reasoning_config` attribute to `_make_agent_stub` so the stub has
a non-None parent value the test can verify is propagated.
* `test_review_fork_inherits_parent_reasoning_config()` — asserts the
fork's `AIAgent(...)` kwargs carry the parent's `reasoning_config`.
Pre-fix this test fails with `None vs expected {'enabled': True, 'effort': 'medium'}`;
post-fix all 4 tests in the file pass.
```
$ python -m pytest tests/run_agent/test_background_review_cache_parity.py -v
test_review_fork_inherits_parent_cached_system_prompt PASSED
test_review_fork_pins_session_start_and_session_id PASSED
test_review_fork_inherits_parent_toolset_config PASSED
test_review_fork_inherits_parent_reasoning_config PASSED ← new
```
Also runs against the broader background-review test suite:
`test_background_review.py` (4), `test_background_review_summary.py` (8),
`test_background_review_toolset_restriction.py` (3) — 19/19 pass.
`agent/curator.py:1691` has the same omission for the umbrella-curation
fork, but curator's prompt is "curate all skills" — it shares no prefix
with any user conversation, so cache-parity is a non-issue there. Worth
auditing if the curator ever takes a parent conversation as input, but
not part of this PR.
The `agent/auxiliary_client.py:1006` `reasoning_config=None` hardcode is
intentional (title/summary one-shots on short prompts — per-call cost
of namespace flip is negligible) and is also out of scope.
prune_old_entries' active-process guard failed open: when
has_active_processes_fn raised, the except block logged at debug and
fell through to the age check, so sessions with live background
processes attached could still be pruned — violating the documented
invariant that such sessions are never dropped. Add a continue so an
exception in the safety check fails safe (the entry is kept).
Commit 6b408e131 fixed the session_key/session_id mismatch in this
same guard but left the exception path failing open.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The #63309 hang class — gateway stuck at 'Connecting to Telegram
(attempt 1/8)' with no retry, no timeout, for minutes — can only occur
when the event loop thread itself is blocked in a synchronous call:
_await_with_thread_deadline's timer fires off-loop, but its expiry
hand-off (call_soon_threadsafe) still needs the loop to run, and the
gateway's outer wait_for is a pure loop timer. When the loop is pinned,
every layer goes silent simultaneously and the process wedges with no
evidence of where.
Two changes:
1. Loop-blocked watchdog in _await_with_thread_deadline: a second
daemon timer fires one grace period (5s) after the deadline; if the
loop still hasn't processed the expiry, it logs a WARNING from the
timer thread and faulthandler-dumps all thread stacks to stderr —
converting the silent hang into a trace that names the exact
blocking frame. A threading.Event set by the expiry callback (and on
normal exit) keeps completed awaits from ever being misreported.
2. discover_fallback_ips: the system-resolver leg runs
socket.getaddrinfo in a worker thread with no timeout, and
asyncio.gather waited on it unboundedly — a wedged OS resolver
stalled discovery for minutes between the two startup log lines. Its
result only feeds a log message, so it no longer gates discovery:
DoH legs (already client-bounded) are gathered alone and the system
leg is awaited with a _DOH_TIMEOUT cap, best-effort.
Refs #63309
Tests: 3 watchdog regressions (blocked-loop dump fires; responsive-loop
timeout does not; completed await does not) + 2 hung-resolver
regressions (DoH results returned promptly; worst-case seed fallback
stays bounded).
Exercises the actual ShellFileOperations.write_file and patch_replace
code paths (not just the helper in isolation) to verify that
safe-root denials surface 'outside HERMES_WRITE_SAFE_ROOT' and
credential-path denials surface 'protected system/credential file'.
Adapted from PR #55615 by @liuhao1024.
Return actionable errors when HERMES_WRITE_SAFE_ROOT blocks a path instead of
labeling every denial as a protected credential file. Wire the helper through
write_file, patch, delete/move, and the Copilot ACP shim; sync docs examples.
Document that safe-root violations are hard-blocked (not approval-gated),
add a security guide section for write_file/patch guards, and link cron
and verifier docs so users trust the footer over agent summaries.
Regression tests for find_latest_gateway_session_for_peer and
SessionStore stale-routing self-heal when end_reason is ws_orphan_reap.
Pin manual approval mode in blocking E2E tests so smart aux-LLM
resolution does not flake CI.
Whitelist ws_orphan_reap alongside agent_close in
find_latest_gateway_session_for_peer so gateway stale-routing
self-heal can reopen wrongly-reaped messaging sessions instead of
minting empty replacements. Layer A prevention already landed in #60609.
Review round 2 from @ethernet8023 on #61580:
1. The manifest list was a hardcoded root/ui-tui/web trio — desktop and
any future workspace escaped the skip key even though step 1's root
install hoists deps for every workspace. The list is now expanded
from the root package.json 'workspaces' globs (npm's own source of
truth): on the real repo that yields all 8 manifests incl.
apps/desktop, apps/bootstrap-installer, apps/shared, and the nested
ui-tui/packages/hermes-ink. Unreadable package.json falls back to
root manifests only (never skips more than main would install).
2. --prefer-offline dropped entirely (this branch no longer carries
#39399): local 3-run benchmarks on the repo's real manifests show
the flag is noise on npm ci with a warm cache (root: 0.90s vs 0.84s
avg; ws: 4.02s vs 4.00s avg) — npm ci does no resolution and the
content-addressed cache already serves tarballs locally. It also
carried the stale-resolution risk on the npm install fallback the
reviewer flagged. All the real win is the skip itself (0s vs ~5s+).
Tests: workspace-glob edit (desktop), literal-listed edit, and
new-workspace-under-glob all defeat the skip; verified against the
real repo's workspace config (8 manifests picked up).
Provider auto-detection (URL-based inference for Anthropic, OpenAI Codex,
and xAI endpoints) runs before credential-pool validation in AIAgent init,
but #63048 placed the pool validation before auto-detection. When the agent
is constructed with provider=None and a recognized endpoint URL, the pool
is validated against an empty provider identity and discarded, even though
auto-detection correctly resolves the provider moments later.
Fix: move the credential-pool validation block to after the URL-based
auto-detection chain. The pool is stored on the agent before
auto-detection; validation now checks the resolved provider and only
nullifies agent._credential_pool when the pool's scoped provider genuinely
doesn't match.
Regression test covers all three auto-detection paths:
- Anthropic (api.anthropic.com)
- OpenAI Codex (chatgpt.com/backend-api/codex)
- xAI (api.x.ai)
Fixes#63425.
- Nudge text now warns that repeated protocol violations will block the
task and require manual intervention, so the model understands the
consequence of ignoring the nudge.
- Kanban docs restructured to clearly separate the two defense layers:
agent-side prevention (nudge, from #64350) and dispatcher-side
recovery (bounded retry, from this PR).
- Two new integration tests verifying the nudge mentions blocking and
that the agent-side and dispatcher-side budgets are independent.
Fold in kevinb361's suggested lifecycle wording (#61817 conceded in favor of
this PR) and update the second stale site his sweep didn't cover: the
task-events table still said the dispatcher 'auto-blocks immediately instead
of retrying'. Both now describe the violation-only streak: protocol_violation
fires on every violation (its payload marker feeds the budget), below-budget
runs return the task to ready, and gave_up + auto-block happen only when the
consecutive streak reaches _PROTOCOL_VIOLATION_FAILURE_LIMIT (default 3,
per-task max_retries overriding).
Address the hermes-sweeper review of #61233: the bounded retry budget
is now a clean-exit-specific streak, not a share of the unified
consecutive_failures counter.
- detect_crashed_workers stamps a protocol_violation marker into the
violation run's metadata (via the event payload _end_run copies);
_protocol_violation_streak derives the streak from run history:
consecutive most-recent violation runs, rate_limited runs neutral
(mirroring their unified-counter treatment), any other closed run
resets it. Mixed failure kinds can neither consume nor extend the
budget.
- Below-budget violations no longer call _record_task_failure at all:
the task returns to ready with last_failure_error stamped directly
(including the corrective retry guidance wording adopted from #61817,
which build_worker_context surfaces to the retry worker) and the
unified counter is untouched, keeping the two budgets independent.
- At the bound the trip funnels through _record_task_failure with a new
keyword-only force_trip=True: the reaper has already resolved the
per-task max_retries override against the violation streak itself, so
the threshold comparison is skipped rather than double-applied.
max_retries keeps its documented top precedence in both directions:
max_retries=1 blocks on the first violation, max_retries=5 blocks on
the fifth consecutive one, unset uses the default bound of 3.
- Replace the first-violation-blocks regression test with five tests:
first occurrence retries (ready + guidance stamped + no gave_up +
unified counter untouched); streak trips exactly at the bound with
protocol_violations/protocol_violation_limit in the gave_up payload
and the auto-blocked side channel set; a prior nonzero crash does not
consume the violation budget; a non-violation failure between
violations resets the streak; max_retries precedence both directions.
All five fail against the previously reviewed diff and pass with this
follow-up. The test harness resolves hermes_cli.kanban_db fresh and
uses that single module object for the exit registry, liveness patch,
and reaper — earlier suite tests reload the module, and the old
mixed-object harness made _classify_worker_exit return unknown (the
reason the old test failed in full-suite runs on main).
Kanban suite: zero introduced failures vs upstream/main tip (62 vs 63
pre-existing environmental failures — the one no longer failing is the
old violation test this replaces; 662 passed vs 657).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A worker that exits 0 without calling kanban_complete/kanban_block
(model stops early, transient tool wedge) tripped the failure breaker
on FIRST occurrence and the task was blocked. These are overwhelmingly
transient: with a bounded retry (limit 3, tracked via a violation
fingerprint) ~96%% of them complete on respawn. Genuine repeat
offenders still trip the breaker at the limit.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
scan_skill_commands() had two collision bugs in the same loop body:
1. Core-command collision: a skill whose normalized slug matches a core
Hermes command name or alias (e.g. "skills", "learn", "bg") would
get an auto-generated /command that shadows the core command in the
gateway dispatch path (skill map is consulted before built-in
handlers). The skill command silently overrode the core command.
2. Inter-skill slug collision: the seen_names set deduped on the raw
frontmatter name, but the command map was keyed by the normalized
slug. Two distinct names collapsing to the same slug (e.g.
"git_helper" vs "git-helper") both passed the dedup, and the second
silently clobbered the first.
Fix: add two guards in scan_skill_commands() after slug normalization:
- resolve_command(cmd_name) check skips skills colliding with any core
CommandDef (name or alias), logging a warning. Uses the existing
resolve_command() API so aliases and case variants are covered
without a separate cache. The skill remains loadable via /skill.
- cmd_key in _skill_commands check dedups on the resolved slug,
first-wins (preserving local-before-external precedence), logging
a warning naming the shadowed skill.
Combines and supersedes #31204 (@cyrkstudios), #53450 (@Gridzilla),
#50304 (@petrichor-op), and #63305 (@Vissirexa).
Co-authored-by: cyrkstudios <cyrkstudios@users.noreply.github.com>
Co-authored-by: Gridzilla <Gridzilla@users.noreply.github.com>
Co-authored-by: petrichor-op <petrichor-op@users.noreply.github.com>
Co-authored-by: Vissirexa <Vissirexa@users.noreply.github.com>
synchronous=FULL issues plain fsync(), not F_FULLFSYNC. The
F_FULLFSYNC barrier comes from checkpoint_fullfsync=1, set by the
separate _apply_macos_checkpoint_barrier(). The original docstring
conflated the two PRAGMAs.
On Darwin, the default synchronous=NORMAL only calls fsync(), which Apple
explicitly states does not guarantee data-on-platter or write-ordering.
During a WAL checkpoint race with process termination (e.g., launchd
shutdown), this can leave the main DB with half-written btree pages,
resulting in btreeInitPage error 11 corruption.
WAL mode's durability guarantee assumes the OS honors fsync barriers; macOS
does not unless we explicitly set synchronous=FULL (which issues fsync() and
F_FULLFSYNC via checkpoint_fullfsync=1).
Previously, apply_wal_with_fallback() skipped setting synchronous=FULL when
the DB was already in WAL mode, leaving connections at the unsafe
synchronous=NORMAL default. This commit adds _enforce_macos_synchronous_full()
to always enforce synchronous=FULL on macOS after any WAL activation.
Fixes#63531
Add a bounded turn-end stop guard for kanban workers. When a worker
tries to exit with finish_reason=stop without having called
kanban_complete or kanban_block, inject up to two synthetic nudges
so the conversation loop continues instead of exiting cleanly (which
the dispatcher records as protocol_violation).
Mirrors the existing verify-on-stop pattern: same ephemeral scaffolding
flag (_kanban_stop_synthetic), same role-alternation contract, same
_pending_verification_response fallback for budget exhaustion.
Disabled by default (gated on HERMES_KANBAN_TASK env var set by the
dispatcher); kill switch via HERMES_KANBAN_STOP_NUDGE=0.
Salvaged from #62262 by @mdc2122. The original branch was 272 commits
behind main with ~538 files of stale-base reversions; this salvage
applies only the 4 substantive files (agent/kanban_stop.py,
conversation_loop.py insertion, run_agent.py _EPHEMERAL_SCAFFOLDING_FLAGS,
tests/agent/test_kanban_stop.py).
Salvage of #63888. The original fix clears stale _last_content_with_tools
on substantive tool-only turns but doesn't clear _mute_post_response, which
a prior housekeeping turn may have set. This suppresses tool progress
output via _vprint until the no-tool-call branch resets it at line ~4834
— after all tools have finished executing.
Fix: also reset _mute_post_response = False when clearing stale fallback.
Added test: verify pure housekeeping turns (content + only housekeeping
tools) still set the fallback correctly — the original use case the
fallback was designed for.
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
A cached _last_content_with_tools response from a housekeeping-only turn
could survive a later substantive tool-only turn. When the model returned
an empty response, Hermes incorrectly finalized the older housekeeping
narration instead of invoking the post-tool empty-response nudge.
Production impact: scheduled cron jobs could return early without completing
their actual work (e.g., daily report job returning a housekeeping message
instead of producing the report artifact).
Root cause: The fallback state was only updated when a turn had both
content AND tool_calls. A turn with tool_calls but empty visible content
would skip state updates entirely, leaving stale fallback state intact.
Fix: Classify tools in every tool-call turn (regardless of visible content).
When any tool is substantive (non-housekeeping), clear the older fallback state
before processing later empty responses. This prevents two-turn-old housekeeping
narration from being treated as if it belonged to the immediately preceding
substantive tool turn.
Regression test added: tests/run_agent/test_conversation_fallback_state.py
Fixes#63860
OpenAI lets ChatGPT-plan Codex users bank rate-limit reset credits, but
until now they could only be redeemed from the Codex CLI/app or the
website. This wires the same backend API into Hermes:
- /usage on the openai-codex provider now shows "You have N resets
banked - use /usage reset to activate" (parsed from the
rate_limit_reset_credits field the /usage endpoint already returns).
- New /usage reset subcommand (CLI + gateway) redeems one banked
credit via POST .../rate-limit-reset-credits/consume with a UUID
idempotency key, mirroring codex-rs backend-client semantics
(PathStyle /wham vs /api/codex, ChatGPT-Account-Id header,
reset/nothing_to_reset/no_credit/already_redeemed outcomes).
- Guard: redemption is refused while no rate-limit window is fully
exhausted, since a banked reset restores the FULL 5h + weekly
allowance and spending it early wastes it. /usage reset --force
overrides. Zero banked credits and non-codex providers are refused
with clear messages; nothing_to_reset reports the credit was NOT
spent.
- i18n: new gateway.usage.unknown_subcommand / reset_wrong_provider
keys across all 16 locales; docs updated (cli.md, messaging index).
Tested with unit tests plus a real-socket E2E against a local fake
Codex backend exercising redeem/guard/force and the /usage hint.
Cache-decorated turns (apply_anthropic_cache_control converts string
content to [{type: text, ..., cache_control}] lists — applied BEFORE the
MoA facade since the #57675 cache-cold fix) and multimodal turns
(text + image_url parts) flattened to empty strings in
_reference_messages, which only read str content. On turn 1 of a
provider:moa session with a Claude aggregator the references received a
single EMPTY user message: Anthropic-side providers 400'd ('messages: at
least one message is required') while tolerant models answered 'no user
request is present' (live incident Jul 14 2026, preset 'closed').
Fixes, in totality:
- _reference_messages: extract visible text via
agent/message_content.flatten_message_text for user/assistant/tool
turns (skips image parts, so no base64 leaks into the advisory view);
decorated and undecorated transcripts now produce a byte-identical
advisory view (advisor cache prefix stays stable).
- image-only user turns get a placeholder instead of an empty message
(Anthropic rejects empty text blocks) or a silently dropped turn
(would break user/assistant alternation).
- degenerate-case fallback flattens structured content too.
- _attach_reference_guidance: a decorated/multimodal trailing user turn
now receives the guidance as a NEW text part appended AFTER the
cache_control-marked part (cached prefix byte-stable) instead of
falling through to a second consecutive user message (strict providers
reject user/user).
- conversation_loop MoA injection: multimodal user turns get the MoA
context appended as a trailing text part instead of being dropped;
user_prompt for the one-shot path flattens content lists instead of
str()-ing them (which leaked base64 payloads into the prompt).
Live-verified on the 'closed' preset (real OpenRouter wire, 2 user
turns, tool loop): all 4 reference calls carry the full document +
rendered tool state, end on user, zero tool-role/tool_calls; advisor
cache_write 7968 then cache_read 5909+; aggregator cache_read
14880-15237 on iterations 2+.
Co-authored-by: bo.fu <bo.fu@meituan.com>
test_probe_sends_client_context_to_gemini and
test_probe_omits_gemini_client_context_for_other_providers (added in
b8eb89f5c) patch hermes_cli.models.urllib.request.urlopen, but
probe_api_models routes requests through the
_urlopen_model_catalog_request wrapper (open_credentialed_url from the
urllib_security hardening), so the mock is never invoked and
mock_urlopen.call_args is None -> TypeError. Every CI run on main and
every PR has been failing test slice 7/8 on these two tests.
Point the patches at _urlopen_model_catalog_request, the same target
every sibling test in TestProbeApiModelsUserAgent already uses.
89/89 tests in the file now pass.
Include the Hermes client name and version with Gemini inference, model and tier checks, and TTS requests. Add focused coverage for the request headers and keep the Gemini-specific context scoped to Google Gemini endpoints.
The desktop provider panel previously rendered the curated declarations
from hermes_cli/memory_providers.py: five hindsight fields, and no panel
at all for undeclared providers like honcho (OAuth connect only). The
dashboard provider-switching rework re-pointed the shared config route
at raw plugin schemas, so the desktop began dumping every internal field
(35 for hindsight) and grew a bespoke honcho panel.
Serve both surfaces from the same route: ?surface=declared returns the
curated schema (empty for undeclared providers) with the original
config-file + env-store write semantics; the dashboard keeps the raw
plugin schema unchanged. The desktop client opts into declared.
The dashboard's dedicated memory-provider UI (4b184cbe5) excluded
memory.provider from /api/config/schema server-side. Desktop's settings
page builds its field list from that schema, so the Memory Provider
dropdown silently vanished from Desktop after v0.18.1.
- web_server.py: restore memory.provider as a select in _SCHEMA_OVERRIDES,
with options built from plugins.memory discovery (was a stale hardcoded
[builtin, honcho] list before the removal)
- plugins/memory: add list_memory_provider_names() — directory-scan-only
name listing, safe at module import time (no provider imports)
- web ConfigPage: hide memory.provider client-side instead — the Plugins
page owns the dedicated provider-switching UI there
- tests: schema contract (select present, category memory, builtin
sentinel) + invariant that every discoverable provider is selectable
#63955 made Hermes survive a broken `bash -l` (Ainz's `Directory
\drivers\etc does not exist`) by falling back to non-login `bash -c`.
But a non-login shell never sources /etc/profile, so it never gets
`…\usr\bin` on PATH — and that dir holds every coreutil the file/terminal
tools shell out to (cat, mktemp, mv, wc, head, stat, chmod, mkdir, find).
Result: `write_file` returned bytes_written:0 with an EMPTY error (the
failure text went to a missing binary's stderr) and terminal commands
exited 127. The survive-broken-login-bash fix was only half-done: it
stopped crashing but silently failed every write.
Derive Git Bash's bin dirs (mingw64/bin, usr/bin, bin, …) from the
resolved bash.exe and prepend them to the subprocess PATH on Windows, in
/etc/profile precedence order so coreutils win over same-named System32
tools (find.exe, sort.exe) inside the shell. No-op off Windows and when a
login snapshot is healthy (the snapshot re-exports the full PATH inside
the shell), so this only bites on the broken-login fallback path.
Adds _git_bash_bin_dirs() (derivation, cached) + _prepend_git_bash_dirs()
(PATH merge), plus regression tests for PortableGit/MinGit layouts and
the run-env injection ordering.
Salvage of #63862. is_output_cap_error() returns False for vLLM/LM Studio
error messages that contain 'prompt contains ... input tokens' (treated as
input-overflow signal). But parse_available_output_tokens_from_error() CAN
extract a valid available_tokens from those same messages. The
compression-disabled guard only checked is_output_cap_error(), so vLLM/LM
Studio users with compression off still got a terminal failure instead of
the max-tokens retry.
Fix: also exempt when parse_available_output_tokens_from_error() returns a
value — that function determines whether the retry path can actually handle
the error, so it's the right predicate for the exemption.
Added test: verify vLLM-format error with compression_disabled=False still
triggers the max-tokens retry path.
Co-authored-by: dmabry <dmabry@users.noreply.github.com>
The branch computed safe_out from estimate_messages_tokens_rough(messages),
but the provider rejected the larger api_messages request (system prompt,
injected context, tool schemas). When API-only content is large, safe_out
could far exceed the provider's available_tokens.
Compute safe_out from estimate_request_tokens_rough(api_messages, tools=...)
and keep provider available_out as an upper bound. Do not alter context_length
or trigger compression for output-cap errors.
Add production-path run_conversation tests that assert the retry API call's
max_tokens, including a case where a large system prompt makes messages-only
estimation undercount the real request.
Fixes#55546
The retry loop computed safe_out from the error's available_tokens,
which reflected the *previous* request. Between retries the agent
appends tool results and error text, so the real input token count
grows. Deriving safe_out from the stale budget meant every retry
still exceeded the context ceiling by 1+ tokens, burning through the
3-attempt limit.
Compute safe_out from estimate_messages_tokens_rough(messages) so
the cap tracks the growing input on each retry attempt.
`_module_registers_tools()` reads each `tools/*.py` file and fully
AST-parses it to check for a top-level `registry.register()` call.
90 files are scanned on every process start — but only 32 actually
register tools.
Add a cheap text prefilter: after reading the file (which we need to
do anyway for AST), check that both `"registry"` and `"register"`
appear in the source before calling `ast.parse`. A file with a
top-level `registry.register()` call must contain both strings, so
this is a perfect superset — zero false negatives. 50 of 90 files
skip the AST parse entirely.
The `source=` parameter is not threaded through `discover_builtin_tools`;
the prefilter lives entirely inside `_module_registers_tools`, keeping
the public API unchanged.
Benchmark (median of 10 runs, scanning 90 files):
before (read + ast.parse all): 305.9ms
after (text prefilter + ast): 187.8ms
speedup: 1.6x (118ms saved)
Identical module set: 32 modules, same names, same order.
The _PROVIDER_PREFIXES frozenset in agent/model_metadata.py is static
and does not auto-extend from ProviderProfile. Removing deepinfra and
deep-infra from it broke provider:model prefix stripping for DeepInfra.
Preserve one durable staged input across terminal close and the worker's early turn flush, without duplicating resumed transcripts or creating a session with a null prompt. Fixes#63766.
Retain a distinct CLI history baseline during the signal window before a turn's normal persistence flush. When CLI history aliases the live agent list, use marker-only persistence so a genuinely unflushed tail is written.
Salvage of #63935. The original fix read HERMES_CRON_SESSION_DB_TIMEOUT
from a bare env var, but AGENTS.md requires non-secret behavioral
settings to live in config.yaml with an env var bridge only for
backward compatibility.
Changes:
- Add cron.session_db_timeout_seconds to DEFAULT_CONFIG (default 10s)
- Resolution order: HERMES_CRON_SESSION_DB_TIMEOUT env override →
cron.session_db_timeout_seconds in config.yaml → 10s default
(mirrors the existing script_timeout_seconds pattern)
- 0 = unlimited (opt-in for debugging, skips the bound)
- Strengthen test: assert the warning is logged on invalid env value
(caplog was taken but never asserted)
- Add test: verify config.yaml resolution path works end-to-end
Co-authored-by: LoicHmh <26006141+LoicHmh@users.noreply.github.com>
run_job() constructs SessionDB() synchronously with no timeout of its
own, unlike the agent's run_conversation call further down, which is
already bounded by HERMES_CRON_TIMEOUT. A wedged sqlite3.connect (e.g.
a stale flock from a crashed sibling process) hangs this call
indefinitely.
That hang is invisible to every existing cron safeguard because it
happens before _submit_with_guard's future exists: the finally block
that discards the job ID from _running_job_ids never runs. The job
stays wedged "running" — every later tick logs "already running —
skipping" — until the whole gateway process is restarted.
Observed in production: a cron job's worker thread was confirmed via
a live py-spy thread dump to be parked inside SessionDB.__init__'s
sqlite3.connect for 3+ days, silently skipping every scheduled fire
in between across a gateway process that otherwise stayed healthy.
Bound the SessionDB() construction with its own timeout
(HERMES_CRON_SESSION_DB_TIMEOUT, default 10s), following the same
bounded-thread-pool pattern already used elsewhere in this file (the
delivery retry path, and the agent inactivity watchdog just below).
On timeout, log at ERROR and proceed with session_db=None instead of
degrading silently to debug level, since an actual hang here is a new
condition worth surfacing.
Adds tests/cron/test_sessiondb_init_hang.py, including an end-to-end
regression proving the dispatch guard is released and a subsequent
tick can fire the same job again after a simulated hang.
Baseline bars were positioned at their absolute timeline offset, which
included the baseline run's own wait time — making duration comparisons
hard since the bars were visually offset. Now each baseline bar starts
at the same left position as its corresponding current job, so the two
bars directly overlap for at-a-glance duration comparison.
Also removed the now-unused bl_t0 / bl_max / bl_jobs_timed variables
that tracked the baseline timeline position.
Add wait time computation: for each job, wait_s = started_at - max(completed_at
of all jobs that finished before it started). This is a timestamp heuristic
(no workflow YAML dependency parse needed) that's accurate for pipeline-shaped
CI where the critical path is linear at each stage.
Shows up in:
- Job table: new Wait + Δ Wait columns
- Gantt chart: hatched bar segment before the run bar
- Step details: '(wait Xs)' annotation in the summary line
- Markdown summary: Total wait row with delta vs baseline
- Stats: total_wait / bl_total_wait in compute_stats
Also completes the skipped-jobs UI:
- Skipped stat card in stats cards
- Skipped row in markdown summary table
Backward compatible: old cached baselines without wait_s annotate on load.
Skipped jobs (conclusion == 'skipped') have null/zero-duration timestamps
that polluted every downstream computation: they counted as 'unchanged'
(0 vs 0) in faster/slower tallies, showed meaningless '0.0s (0%)' deltas
in the job table, rendered phantom gantt bars, and inflated wall/compute
totals.
Add is_skipped() helper and apply it consistently:
- compute_stats: exclude from wall/compute + faster/slower/unchanged;
add 'skipped' and 'bl_skipped' counts
- _gantt_bars: filter from current bars, baseline bars, and axis calc
- _job_table: show 'skipped' label instead of durations/deltas
- _step_details: skip entirely (no meaningful step data)
- _regressions: exclude from both current and baseline sides
alelpoan's fix (emit hermes:zoom:changed after restore) is correct, but the
bug's root is duplication: setAndPersistZoomLevel and restorePersistedZoomLevel
each independently did setZoomLevel + send, and restore forgot the send.
Collapse both (and the lifecycle re-assert) into a single applyZoomLevel()
helper in zoom.ts that always applies-then-notifies — the regression can't
recur by omitting a send. Replace the source-grep test (which broke on main:
the sibling source-assertion pet test it copied was refactored to a behavioral
one, dropping the fs/path imports it relied on) with behavioral coverage of the
funnel, matching zoom.ts's "unit-testable without booting a BrowserWindow"
convention.
Co-authored-by: alelpoan <alelpoan@proton.me>
classifyNativeBinary only checked big-endian Mach-O/Fat magic bytes
(feedfacf, feedface, cafebabe). Real Darwin .node files from node-pty
prebuilds are stored little-endian on disk (cffaedfe = MH_CIGAM_64),
so every Darwin prebuild classified as null, and validateStagedBinaries
threw a platform mismatch on macOS — breaking npm run check for every
macOS contributor. CI didn't catch it because runners are Linux (ELF
path was correct) and tests only planted big-endian fake headers.
Add recognition for all six Mach-O/Fat byte orderings:
- MH_CIGAM (cefaedfe) — LE 32-bit
- MH_CIGAM_64 (cffaedfe) — LE 64-bit [the one real prebuilds use]
- FAT_CIGAM (bebafeca) — LE universal
Update makeFakeNode to write LE CIGAM_64 bytes for the darwin fixture
(matching real on-disk format) and add regression tests for all new
magic forms.
The set-matrix step wrote the npm workspace query result directly to
$GITHUB_OUTPUT. If discovery ever produced [], the matrix would expand
to zero check jobs, leaving the reusable workflow green without running
any JS/TS checks.
Now the step validates the result is a non-empty array before emitting
it, and exits 1 with a GitHub annotation if it's empty or jq failed.
stageNodePty received electron-builder's { platform, arch } but unconditionally
copied host build/Release, staging a host binary (e.g. macOS Mach-O) for a
foreign target (e.g. linux-arm64). The fallback rebuild also didn't pass the
target arch to electron-rebuild.
Now:
- build/Release is only staged when target platform+arch match the host
- cross-platform targets with no matching prebuild fail closed
- same-platform different-arch rebuild passes --arch to electron-rebuild
- post-staging validation reads .node magic bytes (ELF/Mach-O/PE) and rejects
any binary whose platform doesn't match the target
Adds stageNodePtyInto() (testable core) and classifyNativeBinary() (pure),
plus 11 regression tests covering the cross-target scenarios.
Move setGatewayState + rerender calls inside act() blocks and make the
synchronous soft-switch test async so all state updates are wrapped.
Eliminates the last 4 act() warnings (44 → 0).
Extracted zoomWiringForWindowKind() + ZOOM_WINDOW_CONFIG into zoom.ts so
the pet-overlay-
opts-out / chat-windows-keep-zoom contract is tested via the pure
config,
not by reading source. Callers in main.ts now use
zoomWiringForWindowKind()
instead of inline { zoom: false } / default { zoom: true }.
When neither a prebuild nor a compiled build/Release/*.node is found for
the target platform-arch, stage-native-deps.mjs now runs
electron-rebuild -f -w node-pty to compile one from source before
re-copying build/Release into the staged dist.
This makes the staging script self-sufficient — it always produces a
working native binary dir regardless of whether npm ci --ignore-scripts
skipped postinstall or whether node-pty publishes prebuilds for the
target (e.g. linux-x64 has no prebuild).
Add vitest.setup.ts with IS_REACT_ACT_ENVIRONMENT=true + auto-cleanup,
and wrap render()/fireEvent() calls in act() across 8 test files:
- provider-config-panel.test.tsx: wrap renderPanel + fireEvent in act
- providers-settings.test.tsx: wrap renderProvidersSettings + fireEvent
in act
- use-prompt-actions/index.test.tsx: add actRender helper, wrap all 38
render
calls, wrap Harness handle methods (submitText/cancelRun/steerPrompt/
restoreToMessage) in act at the onReady callback level
- attachments.test.tsx: make renderWithI18n async + wrap in act
- skills/index.test.tsx: make renderSkills async + wrap fireEvent in act
- messaging/index.test.tsx: make renderMessaging async + wrap fireEvent
in act
- gateway-connecting-overlay.test.tsx: wrap all render/rerender in act
- preview-pane.test.tsx: wrap render calls in act, make tests async
Reduces act warnings from 44 to 4 (remaining are fake-timer + pre-render
store mutation edge cases). All 146 test files / 1180 tests still pass.
textInputCursorSourceOfTruth.test.ts read textInput.tsx as text and
regexed it to check that cursorLayout() is called with curRef.current
(not the stale cur React state), and that the fast-echo backspace/append
stdout writes are paired with noteCursorAdvance calls.
Extract three pure functions from textInput.tsx:
- resolveCursorLayout(display, cur, curRefCurrent, columns): wraps
cursorLayout(display, curRefCurrent, columns), making the
curRef.current-over-cur choice a directly testable pure call instead of
a regex match on the render-site call expression.
- fastBackspaceEffect(current, cursor) / fastAppendEffect(current, cursor,
text): return a single object bundling {newValue, newCursor, write,
advanceDelta} for each fast-echo path. Bundling the stdout write and the
noteCursorAdvance delta into one return value makes the pairing
impossible to silently drift apart (a caller can't get without
), instead of relying on the two call sites appearing near
each other in source text.
textInput.tsx's render site and backspace/append handlers now call these
helpers directly, preserving exact existing behavior (the same '\b \b'
write sequence, noteCursorAdvance(-1)/noteCursorAdvance(text.length) calls).
textInputCursorSourceOfTruth.test.ts imports and calls the three pure
functions directly with a deliberately stale cur vs a fresh curRefCurrent
to reconstruct the exact regression scenario, and asserts the bundled
effect objects -- no readFileSync, no regex against textInput.tsx's
source text. Full ui-tui suite (107 files, 1117 tests) still green.
oauth-session-request.test.ts regexed main.ts source text (extracting the
fetchJsonViaOauthSession function body and matching regexes against it) to
check Electron net.request doesn't set the forbidden Content-Length header
and does call request.write(body).
That behavior is already covered for real by oauth-net-request.test.ts,
which imports the actual serializeJsonBody/setJsonRequestHeaders helpers
from oauth-net-request.ts and asserts on a mock request object's setHeader
calls -- it only needed its relative import corrected to include the .ts
extension (Node's ESM loader doesn't resolve extensionless relative
specifiers). Removed the now-fully-superseded oauth-session-request.test.ts
and its dangling package.json wiring.
profile-delete-respawn.test.ts regexed main.ts source text to check that
prepareProfileDeleteRequest returns the torn-down profile name, and that
the hermes:api ipcMain handler captures that return value and routes to
the primary backend instead of respawning a pool backend for the just-
deleted profile.
Extract the pure decision logic into profile-delete-routing.ts (no
Electron import):
- profileNameFromDeleteRequest(request): parses a DELETE
/api/profiles/<name> path, moved verbatim (already pure).
- decideProfileDeleteAction(profile, deps): the branch decision (noop /
teardown-primary / teardown-pool) and the profile name to return,
parameterized over isDefaultProfile/isValidProfileName/primaryProfileKey.
- resolveRouteProfile(tornDownProfile, profile): the
routing ternary from the hermes:api
handler.
prepareProfileDeleteRequest in main.ts now calls decideProfileDeleteAction
for the decision and only performs the async side effects (teardown +
writeActiveDesktopProfile) the decision calls for.
profile-delete-routing.test.ts replaces profile-delete-respawn.test.ts
(which was never wired into test:desktop:platforms), importing the pure
functions directly and asserting real return values across every branch
-- no readFileSync, no regex-on-source. Wired the new test file into
test:desktop:platforms in package.json.
windows-hermes-resolution.test.ts regexed main.ts source text to check
three Windows resolution bugs that caused desktop reinstall loops:
1. findOnPath()'s PATHEXT extension order (must try real extensions before
the empty one, or an extensionless Git-Bash hermes shim shadows
hermes.cmd/.exe).
2. handOffWindowsBootstrapRecovery()'s --update vs --repair choice (must
gate on any real-install signal, not just the hermes.exe shim).
3. unwrapWindowsVenvHermesCommand()'s probe-before-trust behavior (must
canImportHermesCli() before returning a venv python, or a broken venv
gets re-selected forever).
Extract all three into pure, dependency-injected functions in
windows-hermes-path.ts (no Electron import): buildPathExtCandidates(),
chooseUpdaterArgs(), resolveVenvHermesCommand(). main.ts's
findOnPath/handOffWindowsBootstrapRecovery/unwrapWindowsVenvHermesCommand
now call these with their existing helpers (fileExists, canImportHermesCli,
getVenvPython, etc.) passed through as deps.
windows-hermes-path.test.ts replaces windows-hermes-resolution.test.ts,
importing the pure functions directly and asserting real return values
with fake/injected dependencies (fake venvs, fake probes) -- no readFileSync,
no regex-on-source.
windows-child-process.test.ts regexed main.ts and bootstrap-runner.ts
source text to check that spawn/execFileSync call sites wrapped their
options with hiddenWindowsChildOptions(), and that backend teardown
chose the right kill strategy.
Extract both into dependency-free sibling modules:
- windows-child-options.ts: hiddenWindowsChildOptions(options,
isWindows)
now takes isWindows as an injectable param (defaults to the real
platform check). main.ts and bootstrap-runner.ts both import the same
implementation instead of each defining their own copy.
- backend-child.ts: stopBackendChild(child, deps) with
forceKillProcessTree
and isWindows injected, so the SIGTERM-vs-tree-kill branching is
directly
testable with a fake child + a spy.
windows-child-options.test.ts replaces windows-child-process.test.ts,
calling the real functions with fake spawn/execFileSync-shaped objects
and asserting on the actual returned options / kill call.
Same fix as the base-env bootstrap tests: init_session's post-failure
non-login probe was overwriting captured["script"] with `true`. Capture
the first (bootstrap) _run_bash call via setdefault.
init_session now fires a follow-up non-login `bash -c true` probe when the
login bootstrap fails, so the two bootstrap-script assertions must capture
the first call only (setdefault), not the probe that overwrote it.
Commit 62a76bd3d (feat: make smart approvals the default, #62661)
changed approvals.mode default from "manual" to "smart". The
TestBlockingApprovalE2E tests did not patch the approval mode, so
check_all_command_guards routed through _smart_approve() first —
calling call_llm() which tried all auxiliary providers, failed (no
API keys in test env), and returned "escalate" before falling through
to the gateway blocking path. The LLM failure cascade took longer
than the test's 2.5s wait window (50 × 0.05s), so the notify
callback had not fired yet when assert len(notified) == 1 ran.
Force {"mode": "manual"} via patch in setup_method/teardown_method,
matching the pattern already used by test_blocking_approval_uses_
canonical_timeout in the same class.
#63621 fixed path quoting, but Ainz's Git for Windows still dies on
`bash -l` itself (`Directory \drivers\etc`). Hermes then fell back to
bash -l *per command*, so every write_file/terminal call failed the same way.
After a failed login snapshot, probe non-login bash -c; if it works, skip
-l for the session. Also skip a stale HERMES_GIT_BASH_PATH that fails a
noprofile probe in favor of %LOCALAPPDATA%\hermes\git portable bash.
Live deltas from session A were attaching to session B after New Session
when events arrived without session_id — fallback used the newly focused
activeSessionId (#47709).
Pin unscoped stream events to the session that received message.start
(#48281). Also reset RAF-pending view staging on new/resume/create so a
stale background flush cannot repaint over the switched chat (#47743).
Co-authored-by: Ray <rayjun0412@gmail.com>
Co-authored-by: zapabob <1920071390@campus.ouj.ac.jp>
When the base is an origin/… ref, fetch just that branch so the
local tracking ref is fresh before `git worktree add -b new origin/main`.
Fetch failures (offline / no remote) are silently ignored — git uses
whatever local ref exists, or raises a clear error if it's missing.
The sidebar "New worktree" button branched off whatever HEAD you were
on — now a filterable Popover+Command combobox lets you pick any local
or remote-tracking branch as the base, defaulting to origin/HEAD.
Backend listBaseBranches() queries refs/heads + refs/remotes via
for-each-ref, flags origin/HEAD (falling back to the local default for
no-remote repos). Mirrored on the Python REST API side
(base_branch_list + /api/git/base-branches route).
Splits the single broad `except Exception` in the compression-lock
acquire path into two handlers: AttributeError/TypeError (version skew —
the lock method is missing, or predates the `ttl_seconds=` kwarg) still
fails OPEN as before, since that's known-safe to proceed without a lock.
Any other exception now fails CLOSED (skips compression this cycle)
instead of treating every failure as "no lock subsystem present" and
letting a second compressor run concurrently and fork the session.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reserve API requests before their first await, include every drain-owned work type in runtime status, and pause local cron dispatch while a gateway drain is active.
Closes#63529
Root cause: GatewayRunner._drain_active_agents only waited on
_running_agents + cron in-flight counts. Desktop/API sessions are
tracked solely inside APIServerAdapter (_inflight_agent_runs +
_active_run_agents), so stop/restart logged active_at_start=0 and
systemd SIGKILL'd mid-tool work.
Fix: APIServerAdapter.active_agent_work_count() plus
GatewayRunner._active_api_run_count() folded into the drain wait,
status updates, timeout result, and shutdown logs — same pattern as
_active_cron_job_count for #60432.
Verification: pytest tests/gateway/test_api_server_active_work_drain.py
tests/gateway/test_cron_active_work_drain.py -q → 19 passed
Normalize Anthropic setup-token metadata for every PooledCredential construction path, persist corrected manual entries, heal legacy rows on load without copying global fallback credentials into profiles, and map the contributor email for release attribution.
Manually-added Anthropic setup-tokens defaulted to api_key and were sent
via x-api-key, which Anthropic rejects -> 429. Infer OAuth from the
sk-ant-oat prefix in from_dict so all ingest paths agree with
_is_oauth_token(). Fixes#63737.
Add fallback only updates local editor state; complete pairs are filtered
before onChange. The post-#7b5ba205 resync effect then saw the unchanged
persisted chain and wiped the draft — button looked dead.
Ignore value updates that match the last chain we emitted; still resync
on real external changes (profile/config reload).
Co-authored-by: HexLab98 <liruixinch@outlook.com>
Reject metadata that would make session queries fail, bound import work, and detach cyclic lineage links. Guard lineage traversal against pre-existing corrupt cycles.
_custom_provider_model_matches() only compared the session model
against the entry's single 'model' field. A custom provider declaring
a multi-model catalog (providers.<name>.models mapping / models list)
whose default model differed from the session model silently failed to
match — dropping the entry's extra_body entirely. Real impact: an
OpenAI custom provider pinning service_tier=flex via extra_body ran
every request at STANDARD tier (~2.3x billing) with zero signal.
- Model matching now accepts the session model when it appears in the
entry's models catalog (dict keys or list), case-insensitive;
single-model 'model' field behavior unchanged; entries with neither
still match everything.
- Usage report ('hermes -z --usage-file') now carries service_tier
(the tier requested via request_overrides.extra_body) so batch
pipelines can audit the billed tier per run.
Validation: 8 new tests; live E2E via real 'hermes -p sweeper -z'
with httpx-level wire capture — service_tier=flex present in the
outgoing /v1/responses body and in the usage report.
_default_spawn sets HERMES_KANBAN_GOAL_MODE=1 but launched 'chat -q' without
-Q; _run_kanban_goal_loop_q only executes in the quiet single-query branch,
so goal-mode never ran for dispatcher-spawned workers — they got one turn,
printed text, exited rc=0, and tripped the protocol-violation circuit
breaker (2026-06-09, cards t_d9cbe312 et al). Root-cause report + upstream
issue draft in kanban workspace t_720c5c60.
#63113 rewrote native drive paths in ShellFileOperations, but init_session
/_wrap_command still embedded C:/... hermes-snap paths from get_temp_dir.
MSYS arg-converts those during bash -l and surfaces Directory \drivers\etc
— including for relative write_file targets, since the wrapper is the fault.
Add _bash_safe_path, override BaseEnvironment._quote_shell_path on
LocalEnvironment (no base→local import), and normalize mixed /c/Users\...
paths in file ops.
Co-authored-by: xxxigm <tuancanhnguyen706@gmail.com>
The #54527 context pin (7acaff5ef) snapshots the selected stored session
and route token at submit entry and aborts when either changes mid-flight.
But a NEW chat's create pipeline legitimately moves both: on success,
createBackendSessionForSend re-homes selection and navigates to the chat
it just minted. Judged against the pre-create draft baseline that read as
a user switch, so every first send of a new chat aborted before
prompt.submit — message dropped, no DB row persisted (row creation is
lazy, server-side in prompt.submit), and the window stranded on a route
whose REST reads 404 "Session not found" forever.
Fix: after a successful create, verify no one re-homed during create's
post-commit await via the active-session ref (a non-null return
guarantees create set it; every switch path retargets it synchronously),
then re-pin the drift baseline to the created chat. A mid-create switch
still aborts through create's own null return, or through the active-ref
check for the post-commit window. Re-pinning also restores the correct
stored-id association for the optimistic-message state updates, which the
pinned pre-create null had degraded.
Tests: red-first regression for the new-chat send, an abort case for a
switch landing in create's post-commit window, and the sleep/wake
new-chat stub made faithful to the real create (it sets the active ref
before returning — the inert stub is what let this ship green).
The web UI CONFIG_SCHEMA showed ['ask', 'yolo', 'deny'] for the
approvals.mode select field. These don't match any real config values
and 'smart' mode was entirely unreachable from the dashboard.
Correct the options to ['manual', 'smart', 'off'] which match the
values defined and documented in hermes_cli/config.py.
Adds a regression test to TestBuildSchemaFromConfig to pin the correct
option names and guard against future drift.
Fixes#31925
Asserts each {provider, model} entry renders as its own row (the bug
produced "[object Object]"), that removing a row emits the remaining
entries, that adding a blank row never persists a partial pair, and the
empty-state hint.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Settings → Model rendered `fallback_providers` (a list of `{provider,
model}` objects) through the generic `list` config field, which does
`value.join(', ')` and stringified each entry to `[object Object],
[object Object]`.
Add a dedicated provider+model row editor (add/remove), sourced from the
same `getGlobalModelOptions()` the composer picker uses, that reads and
writes the `{provider, model}` chain. Half-filled rows are kept in local
state so the config autosave never persists a partial entry, and an
out-of-catalog model stays selectable so existing custom entries render.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Preserve the root cause and precedence direction from #43538 while applying the merge before truncation and covering all declared model shapes.
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
list_authenticated_providers() emits picker rows for every slug in
PROVIDER_TO_MODELS_DEV that has any credential env-var set. Several of
those slugs (notably 'mistral') have no PROVIDER_REGISTRY entry, so
resolve_provider() rejects them as 'Unknown provider' once the user
selects a model — leaving the picker showing rows that cannot actually
be selected.
Add a resolve-gate in section 1: if PROVIDER_REGISTRY.get(hermes_id)
is None, skip the slug. The picker now only lists providers that can
actually be switched to at runtime.
This automatically resolves the duplicate-Mistral dedup symptom too:
once the broken-from-models.dev row is filtered, the conflict between
PROVIDER_TO_MODELS_DEV['mistral'] and a custom_providers 'Mistral' row
is moot.
Composes with #50289 (which promotes mistral to first-class via the
provider-plugin path): when that lands, PROVIDER_REGISTRY gains a
'mistral' entry and the gate becomes a no-op for it. No conflict.
Tests (regression suite):
- tests/hermes_cli/test_model_switch_filter_unresolved.py (new, 4 tests):
Picker excludes 'mistral' when MISTRAL_API_KEY is set; 'deepseek' and
'xai' (PROVIDER_REGISTRY-backed) still appear; 'mistral' stays
excluded when no key is set. Confirmed by reverting the fix and
seeing the test fail with 'mistral leaked into /model picker'.
Cross-checked against the existing 51 test_model_switch_* and
test_custom_provider_* cases — 55/55 PASS, no regressions.
MoA was internally inconsistent: preset-level ops (set default / add /
delete) persisted on click, but reference-model and aggregator slot edits
sat behind a manual Save button. Debounce-persist slot/aggregator edits
like the rest of settings and drop the redundant button, so MoA is
uniformly autosave.
An aggregator whose pooled credentials are all exhausted/dead still counted as
an authenticated provider during no-provider /model resolution. It then won the
model-name match, was set as the sticky session provider, and poisoned every
later switch with "empty API key" errors while still routing through the dead
aggregator.
list_authenticated_providers now requires a pool to have at least one available
entry (has_available, not has_credentials / bare key presence) at all three
credential-pool gates. Simple token-style entries that don't parse into
exhaustion-tracked entries keep the prior behaviour, so providers whose creds
live only in the auth-store credential_pool still appear.
Fixes#45759
ShellFileOperations builds bash commands (wc/head/sed/cat/tee ...) with the
target path as an argument. On a Windows/Git-Bash host a native `C:\...` path
has its backslashes eaten by bash (and mangled by the msys runtime even when
single-quoted) — the "Directory \drivers\etc does not exist; exiting — update
your msys package" class of failures. Rewrite a native drive path to forward
slashes in `_escape_shell_arg`, reusing the env layer's `_windows_to_msys_path`.
Both `C:/...` and `/c/...` fix the backslash bug (the MSYS coreutils resolve
either via the POSIX API). We emit `/c/...` purely for consistency: it's the
same form `_windows_to_msys_path` already produces for the terminal `cd`
(LocalEnvironment._quote_cwd_for_cd), so shell file ops and `cd` share one
helper and one path form.
Scoped from #55481, which also patched BaseEnvironment._quote_cwd_for_cd — but
LocalEnvironment already overrides that through `_windows_to_msys_path`, so on a
real Windows host the base branch never ran (the cwd is already `/c/...`).
Co-authored-by: konsisumer <der@konsi.org>
Add shared translators in hermes_constants (Windows drive → /mnt, `\\wsl(.localhost|$)\`
UNC → POSIX, gated on is_wsl) and apply them at the gateway session-cwd boundary
so a Windows-host UI can hand the WSL backend a path it can actually chdir into.
De-dups the ACP adapter's private `_win_path_to_wsl` onto the shared helper and
extends it to the UNC spelling.
Co-authored-by: Rage Lopez <VrtxOmega@pm.me>
When the desktop UI runs on Windows and the gateway runs in WSL, a WSL/POSIX
cwd isn't openable/readable from the Windows host. Add wsl-path-bridge.ts to
translate the Windows-side direction only:
- native folder dialog defaultPath: `/home/...` → `\\wsl.localhost\<distro>\...`
- fs read path: WSL cwd → its UNC / `C:\` drive form
Distro detection reads `wsl.exe -l -q` with `WSL_UTF8=1` and strips stray NUL
bytes, since older wsl.exe emits UTF-16LE (microsoft/WSL#4607) — the original
utf8 read returned a garbled distro name. UNC uses `\\wsl.localhost\` with a
`\\wsl$\` fallback for older Windows. The reverse (any path → POSIX) is handled
once gateway-side, so the picker result needs no desktop translation.
Co-authored-by: Rage Lopez <VrtxOmega@pm.me>
Capture durable Desktop engineering principles from recent sessions —
state by authority, workspace-switch shapes, resolver ladders, optimistic
UI — and point root AGENTS.md at the scoped guide with current filenames.
Answered clarifies were collapsing into a generic tool row, hiding the
choice. Settle into a Q&A panel instead, and route freeform input through
the shared Textarea chrome.
Resuming a session cd's back into its recorded working directory, so it resumes
in the repo it belonged to. `--no-restore-cwd` opts out; skipped under
--worktree (that path owns its dir); best-effort — a missing dir warns and stays
put rather than failing the resume.
Co-authored-by: Cary Palmer <palmer@dugoutfantasy.com>
`hermes sessions list --workspace <needle>` filters to one workspace (git repo
root or project dir, matched by path substring or basename) and adds a
Workspace column. The column only appears once at least one listed session
carries a workspace, so all-unbound listings render exactly as before.
Co-authored-by: Cary Palmer <palmer@dugoutfantasy.com>
A session's coarse workspace identity: its git repo root when known, else its
cwd (branch excluded, so switching branches doesn't fragment history). Pure
helper over fields sessions already record — no new columns, no git shelling.
Co-authored-by: Cary Palmer <palmer@dugoutfantasy.com>
Align the workspace status-bar dropdown with the rest of the status bar: drop
the per-item icons (they mixed lucide size-4 with a Codicon 1rem glyph and were
the only status-bar menu carrying item icons), leaving text-only items on the
shared DropdownMenuItem primitive with default typography. The status-bar
trigger keeps its FolderOpen glyph, consistent with sibling items.
Also map true@supersynergy.de → Supersynergy in AUTHOR_MAP.
Squashed salvage of #45744 (@harjothkhara), rebased onto current main and
resolved against #58241 (which swapped the new-session cwd fallback to the
project-aware resolveNewSessionCwd).
An explicitly clicked sidebar workspace stays authoritative until session.create:
a one-shot $newChatWorkspaceTarget (null → detached, string → that folder) plus a
generation counter so a stale async `config.get project` normalization can't
overwrite a newer draft target. The start-workspace-session action is extracted
out of desktop-controller.tsx into a testable workspace-session-target module.
Integrated with #58241: the no-explicit-target branch now falls through to the
project-aware resolveNewSessionCwd() instead of the old workspaceCwdForNewSession.
Co-authored-by: harjoth <harjoth.khara@gmail.com>
Addresses @teknium1's review of #61950:
- The desktop live overlay (workspace-groups.ts) matched cwd membership
case-sensitively, so a fresh mixed-case/separator Windows session missed
its explicit/auto project until the next backend tree refresh. Mirror the
backend identity (isWindowsPath/comparisonSegments/pathKey) in isPathUnder,
liveSessionProjectId, and overlayRepoLanes lane matching. Comparison-only —
emitted ids/labels keep their spelling. POSIX stays case-sensitive.
- Backend _is_windows_path missed root-relative `\wsl.localhost\...` (single
leading backslash), leaving that historical spelling case-sensitive. Classify
any backslash-rooted path as Windows.
Tests: WSL-spelling collapse + explicit-project precedence (project_tree),
Windows/WSL live-overlay membership + POSIX case-sensitivity (workspace-groups).
Sign out of the dedicated OAuth partition before opening the login window so a
stale gateway/identity-provider cookie can't silently bounce an expired session
straight back into failure. Relabel the action "Sign out & sign in" and spell
out the sign-out step in the hint.
Co-authored-by: Tony Antunez <57689194+smtony@users.noreply.github.com>
Add isRemoteReauthError so an auth-shaped boot error counts as a remote-reauth
failure even when the session indicator still reads connected (a stale refresh
cookie / failed ws-ticket mint). Wire the boot error into the overlay's reauth
check so those sessions route to Sign in instead of the local-only recovery
buttons.
Co-authored-by: Tony Antunez <57689194+smtony@users.noreply.github.com>
A remote/VPS backend that failed to boot trapped the user on the recovery
screen — Retry/Repair/Use-local only target the local backend, so the only fix
was hand-editing connection.json. Add an in-place "Gateway settings" view (the
real GatewaySettings panel embedded via `embedded`, lazy-loaded) reached from
the recovery card, and shape the recovery actions by failure kind: Sign in for a
lapsed remote session, Gateway settings for any other remote failure (Retry
drops to secondary; Repair is dropped — it can't revive a remote), Retry for a
local backend. Use-local is scoped to remote failures.
Add an `embedded` flag to GatewaySettings (and a `bare` variant to
SettingsContent) that drops the page title/intro, Diagnostics row,
"Save for next restart", and the page gutters — so the same panel can be reused
inside a tighter surface without a second connection form to maintain. No change
to the standalone Settings → Gateway page (defaults off).
Factor the "remote/cloud with a URL" check out of isRemoteReauthFailure into a
shared isRemoteConfig helper so the boot-failure overlay can tell any remote
failure apart from a local one.
Remove the DEV-gated "Dev · soft switch" ListRow and its previewGatewaySwitch
helper. It was a temporary review affordance for exercising the soft-switch
reconnect; dead-stripped from production, but it doesn't belong in the tree.
wipeSessionListsForGatewaySwitch (the real path) and $gatewaySwitching stay.
A block-level label child (e.g. `flex`) collapses TooltipContent's inline
`box-decoration-clone` wrapper, so Radix measures a zero-size chip and parks
an empty black rectangle in the panel corner instead of by the trigger
(#62022). The terminal rail's hotkey labels and the preview row's two-line
label both hit this.
Harden the shared wrapper (`[&>*]:!inline-flex`) so any call site's direct
child renders inline-flex, add a reusable `TipHintLabel` for the common
text+hotkey label, and keep the preview row's label explicitly inline-flex.
Salvages #62139 (shared-component hardening + TipHintLabel) and #62073
(inline-flex call-site fixes + rail/preview coverage).
Co-authored-by: alelpoan <alelpoan@proton.me>
Co-authored-by: zapabob <1920071390@campus.ouj.ac.jp>
A reopened tab restarted the shell in its original launch dir, so the fresh
prompt showed the wrong folder after a prior `cd` (the issue's "separate
thing" note). Track the shell's working directory and restart the PTY there.
Two independent signals feed a persisted per-tab restoreCwd:
- a main-side PTY cwd probe (shell-agnostic; /proc on Linux, lsof on macOS;
Windows has no cheap per-process query so it falls back to the launch dir)
- cwd-reporting OSC sequences parsed in the renderer (OSC 7 file URIs, OSC 9;9
ConEmu/Windows-Terminal paths) for shells configured to emit them
On relaunch the fresh shell boots in restoreCwd, falling back to the launch
cwd (then home) when it no longer exists.
cleanReviveSnapshot only dropped the trailing prompt when a blank separator
sat above it (starship add_newline), so shells that print the prompt with no
preceding blank line — default PowerShell (PS C:\..>), bash user@host:~$ —
kept the idle prompt in the saved buffer and showed a duplicate under the
fresh boot prompt on every relaunch of an *active* session.
An interactive shell always reprints its prompt after a command, so the tail
of an idle buffer is the prompt, never history. Drop the short block after a
blank separator when present, otherwise drop the trailing single-line prompt.
Command output is preserved; the fresh shell reprints the live prompt on boot.
An idle terminal tab (no command ever typed) grew one extra copy of the
shell's boot prompt on every close/reopen: persistSnapshot re-serialized a
buffer that was just the replayed old prompt plus the fresh shell's new
prompt, and cleanReviveSnapshot's blank-line trim can't strip prompts on
shells like default PowerShell that print no separator line.
Track real user input (keystrokes/paste, drag-and-drop paths, injected
commands) and, when a session had none, skip re-serializing. If the buffer
we loaded carried no real scrollback (empty or only a repeated prompt),
clear it so the next launch shows a single fresh prompt and any existing
accumulation heals; otherwise leave the prior snapshot untouched so real
history from an earlier active session survives an idle reopen.
Salvages #61584 (activity tracking) and #61577 (clearing content-free idle
buffers) into one path: it also heals already-polluted buffers, counts
drag-and-drop and injected input as activity, and never discards genuine
short command history (only empty/all-identical buffers are cleared).
Co-authored-by: alelpoan <alelpoan@proton.me>
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
GatewayRunner._prepare_inbound_message_text's "@" context-reference
block read self._model / self._base_url to resolve the model for
get_model_context_length_async. GatewayRunner never sets either
attribute (copy-pasted from HermesCLI in da44c196b, which does carry
self.model/self.base_url). Every message containing "@" raised
AttributeError inside the try block, silently swallowed by the
surrounding except Exception at debug level, so
preprocess_context_references_async never ran and @file:/@folder:/@diff/
etc. references passed through to the model unexpanded.
Fix: resolve model/provider/base_url via
self._resolve_session_agent_runtime(source=, session_key=,
user_config=), the same session-aware resolution the hygiene
compression block already uses a few hundred lines later in this file.
Also raise the swallow log from debug to warning (with exc_info at
debug) so a future regression here is visible instead of silent.
Third correction, and the load-bearing one. The previous commit put the
"did compaction clear the threshold?" verdict inside should_compress(). But
conversation_loop calls should_compress() TWICE per turn with two different
measures (turn_context.py / conversation_loop.py:1033 and :4789):
* pre-API : request_pressure_tokens -- a rough estimate that can dip BELOW
the threshold
* post-API: real prompt tokens -- which stay above it
So the rough reading reset the strike every turn and the loop never stopped.
Reproduced: 8 compactions in 8 turns under the real two-call pattern, even
with the previous fix applied. (My earlier repro only called should_compress()
once per turn, which is why it looked contained.)
Move the verdict to update_from_response(), the one place that sees the
provider's real prompt_tokens for the just-compacted conversation, guarded by
the existing awaiting_real_usage_after_compression flag so it fires exactly
once per compaction. Real-vs-real: it cannot be fooled by a rough sub-threshold
reading, and (from the previous commit's lesson) never subtracts an estimate
from a real count. should_compress() goes back to a plain threshold test plus
the pre-existing cooldown and anti-thrash guards.
New test test_rough_preflight_reading_does_not_reopen_the_loop drives the real
two-call-per-turn pattern and fails on the prior should_compress()-based commit.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Follow-up to the previous commit, whose futility check was unsound:
incompressible_floor = max(0, display_tokens - pre_estimate)
`display_tokens` is the provider's real prompt count; `pre_estimate` is
`estimate_messages_tokens_rough(messages)`. Subtracting an estimate from a real
count folds the tokenizer skew into "floor" and misreads it as incompressible
overhead. With a 1.6x skew on a 200K window (threshold 150K, true floor 30K):
rough_msgs=253,804 real_prompt=436,086
computed floor = 182,282 <-- mostly skew; exceeds the threshold
after compaction: 401 -> 77 msgs, real prompt = 106,361 (CLEARS 150,000)
verdict: ineffective_count = 1 <-- false positive
Two such passes would permanently disable compaction on a healthy session --
worse than the loop this PR set out to fix.
Move the check into should_compress(), where both sides of the comparison are
the caller's own token count:
* prompt under the threshold -> not thrashing; reset the counter
* a compaction just ran and we are STILL over -> one strike
Real-vs-real, so tokenizer skew can never be mistaken for a floor, and nothing
subtracts an estimate from a real count. compress() now only ever increments the
counter; the reset lives with the one measure the trigger uses.
Adds `test_no_false_positive_under_tokenizer_skew` (the case above) and
`test_counter_resets_once_the_prompt_fits_again` (one failed pass must not
disable compaction forever). Against upstream, 5 of the 7 cases fail; the 2 that
pass are the regression guards, which is the intended shape.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
`should_compress()` documents anti-thrashing protection ("if the last two
compressions each saved less than 10%, skip compression to avoid infinite
loops"). In practice `_ineffective_compression_count` reset on every pass,
so the guard was dead code and a mis-sized context window presented as a
hung CLI instead of a warning.
Two defects:
1. Mixed measurement bases. Effectiveness was
`(current_tokens - estimate(compressed)) / current_tokens`, where
`current_tokens` is the provider's FULL prompt (system prompt + tool
schemas + messages) but `estimate(compressed)` covers messages only.
Every compaction therefore reported ~96% savings and reset the counter.
Savings is now scored messages-vs-messages.
2. Message shrinkage is the wrong yardstick. `should_compress()` trips on
the full prompt, but compaction can only shrink messages -- the system
prompt and tool schemas are an incompressible floor. When that floor
alone meets the threshold, each pass shrinks messages by a healthy
margin, legitimately resets the counter, and still leaves the prompt
over the line; the next turn compacts again, forever. Observed in the
wild: 45+ consecutive compactions, one auxiliary-LLM call each, zero
progress. Effectiveness is now scored against the goal -- did the
projected prompt get under the threshold? -- and a futile pass warns
with the numbers that prove it.
Also record an ineffective pass on the "only N messages (need > M)" early
return, which previously returned the transcript unchanged without moving
any anti-thrash state -- the same class of bug the neighbouring
"no compressable window" branch was already fixed for.
Tests: 4 of the 5 new cases fail on main and pass here; the fifth pins
that effective compaction still resets the counter (121 -> 15 messages,
88.9% savings).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Fold in the TUI direction from #61192 and cover the remaining new-live-session picker path with one shared session-argument normalizer.
Co-authored-by: DatTheMaster <hermesagent424@gmail.com>
Desktop active-session picker calls already pass a session_id, but the gateway's model switch persistence is controlled by parsed model flags. Add --session so the shared parser keeps live-session selections, including MoA virtual provider presets, out of profile config.yaml.
Constraint: config.set model values are parsed by hermes_cli.model_switch before persistence is decided.
Rejected: backend special-case for desktop session_id | it would duplicate existing --session semantics and widen the gateway surface.
Confidence: high
Scope-risk: narrow
Directive: Keep desktop model picker active-session switches explicit with --session; do not rely on session_id alone for persistence.
Tested: npm run test:ui -- src/app/session/hooks/use-model-controls.test.tsx src/app/shell/model-menu-panel.test.tsx
Tested: npm run typecheck
Tested: git diff --check
Not-tested: full pytest suite; change is desktop TypeScript/UI routing only.
Preserve deletability, route identity, stored costs, aggregate reconciliation,
and zero-usage Codex route accounting on top of the salvaged per-model usage
work.
The `sessions` table records only the initial (model, billing_provider)
for a session, so when a user switches models mid-session (via `/model`
or programmatically) every token — including the switched model's — is
attributed to the first model. Insights/billing reports then hide the
cost of the new model entirely (e.g. a session that started on deepseek
and switched to opus shows $0 for opus).
Add a `session_model_usage` table keyed (session_id, model,
billing_provider) that accumulates each per-API-call delta under the
model active at the time of the call. `update_token_counts()` is the
single chokepoint every per-call delta flows through (CLI, gateway,
cron, delegated, codex), so recording there captures accurate
attribution on every platform. Only the incremental path records — the
gateway's `absolute=True` summary overwrite is skipped to avoid
double-counting cumulative totals that can't be split per model. When a
call omits the model, it falls back to the session's recorded model,
matching the existing COALESCE-from-session summary behaviour.
Insights `_compute_model_breakdown` now aggregates tokens and cost from
`session_model_usage`, so a switched session splits correctly across
models, with a defensive fallback to the per-session aggregate for any
session lacking usage rows. A v17 migration backfills one usage row per
existing token-bearing session from its aggregate totals (idempotent via
INSERT OR IGNORE), validated lossless against a 1.3 GB production DB.
Tests: per-model recording, mid-session split, model fallback, absolute
no-double-count, v17 backfill, and an insights-level switch breakdown.
Fixes#51607.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Bundle Fireworks AI as a first-class BYOK provider across the CLI, web/TUI,
and desktop onboarding.
- New model-provider plugin with attribution headers (HTTP-Referer / X-Title)
so Fireworks can attribute Hermes traffic; PAYG-safe default aux + fallback
models (accounts/fireworks/models/...), IDs tracking fw-ai/fireconnect.
- Registered in CANONICAL_PROVIDERS so it appears in the CLI/web/TUI pickers.
- Alias wiring (fireworks-ai, fw) into both CLI resolvers.
- First-class wiring: OPTIONAL_ENV_VARS, HERMES_OVERLAYS (FIREWORKS_BASE_URL
override), doctor env hints. Live catalog + model_metadata are auto-derived.
- doctor: treat Fireworks' native slash-form IDs (accounts/fireworks/...) as
valid, not aggregator vendor prefixes, so it no longer tells Fireworks users
to switch to openrouter or drop the prefix.
- picker: plugin providers with no static curated list now lead with their
profile fallback_models, so the default is an agentic chat model instead of
whatever the live catalog returns first (Fireworks listed an image model,
flux-*, ahead of its chat models).
- Desktop onboarding: Fireworks as a RECOMMENDED hero card with the official
Fireworks logomark and a brand-purple badge, routing to the BYOK key form;
i18n in en/ja/zh/zh-hant.
- Tests: profile contract, first-class wiring (both resolvers, overlay, config,
doctor incl. the slash-form regression, aux headers, credentials), discovery
spot-check, and a live smoke test driven through the Hermes runtime.
Fire Pass (fpk_) support is coming soon; the future wiring is kept as a
commented-out scaffold in the plugin.
`hermes -t web chat` silently dropped the toolset filter (and the same
hold true for `-m`, `--provider`, `--tui`, `--dev` placed before
`chat`). Reported in #28780 for `-t/--toolsets`; the others are sibling
failures with the same root cause.
Root cause: the chat subparser re-declared these flags with `default=None`
(or `default=False` for store_true) on top of the matching top-level
parser flags. When argparse dispatches into the subparser it shares the
namespace via `dest`, so the subparser's default overwrites whatever the
top-level parser parsed before the subcommand. `-s/--skills`, `-r/-c/-w`,
`--yolo`, and `--pass-session-id` already use `default=argparse.SUPPRESS`
for exactly this reason — the chat-subparser action becomes a no-op
unless the user explicitly passes the flag after `chat`, and the parent
value survives.
Reproduction (origin/main, before fix):
>>> parser.parse_known_args(["-t", "web", "chat"]).toolsets
None
>>> parser.parse_known_args(["chat", "-t", "web"]).toolsets
'web'
After fix:
>>> parser.parse_known_args(["-t", "web", "chat"]).toolsets
'web'
>>> parser.parse_known_args(["chat", "-t", "web"]).toolsets
'web'
Sibling flags fixed in the same commit because they share the exact same
argparse pattern bug — verified via a new contract test that scans every
chat-subparser action whose `dest` is also on the top-level parser and
asserts `default is argparse.SUPPRESS`. The test fails on origin/main
listing all five offenders and passes after this fix.
Test additions in tests/hermes_cli/test_argparse_flag_propagation.py:
- TestChatSubparserInheritedValueFlags exercising real `_parser` build
(not the hand-rolled replica) so it catches future drift.
- Parametrized before-chat / after-chat cases for `-t`, `--toolsets`,
`-m`, `--model`, `--provider`.
- Negative case: passing none of the flags leaves attrs at the top-level
parser's `None` default (SUPPRESS does not remove existing attrs).
- Combined case: all three value flags before `chat` simultaneously.
- store_true cases for `--tui` / `--dev`.
- Contract test asserting every shared-`dest` flag on chat uses SUPPRESS.
Fixes#28780.
Review feedback: a same-host redirect to a different port can land on a
different service, which must not inherit the provider API key. Compare
(scheme, hostname, effective port) — with 80/443 defaults — instead of
hostname alone, and add a two-server regression test for the
same-host/different-port case.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
fetch_models() sends Authorization: Bearer <api_key> plus any
default_headers (x-api-key etc.) via urllib.request.urlopen, and
urllib's redirect handler forwards every header when following a
3xx — including to a different host. A catalog endpoint (or a
compromised/misconfigured proxy in front of it) answering with a
redirect to another origin therefore received the provider API key.
Install an HTTPRedirectHandler that drops authorization, x-api-key,
api-key, x-goog-api-key and cookie when the redirect target hostname
differs from the original request, mirroring the pattern already used
in skills/creative/comfyui/scripts/_common.py. Same-host redirects
keep credentials so legitimate path-level redirects still work.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
_CodexCompletionsAdapter (agent/auxiliary_client.py) is a second,
independent producer of Codex Responses input — used by auxiliary
calls (context compression, flush_memories, MoA aggregation,
session_search) that route through CodexAuxiliaryClient instead of
the main agent's ResponsesApiTransport.build_kwargs. It calls
_chat_messages_to_responses_input() directly without is_github_responses,
so the previous commit's fix didn't cover it: an auxiliary call made
against a Copilot-backed session could still replay a connection-scoped
codex_message_items id and hit the same HTTP 401.
Detect the Copilot host from the adapter's own client.base_url (same
check the adapter already does further down for prompt_cache_key
opt-out) and pass is_github_responses through, closing the gap.
Still #32716.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Copilot (api.githubcopilot.com/responses) binds replayed assistant
codex_message_items ids to a specific backend "connection". Credential-
pool rotation, a gateway restart, or routine load-balancer churn between
turns all invalidate that binding, and Copilot rejects the stale id with
HTTP 401 "input item ID does not belong to this connection" — even for
short ids well under the #27038 64-char length cap, since this is a
connection-scope problem, not a length problem. Once a session captures
one of these ids it is persisted and replayed forever, permanently
bricking the session.
Thread an is_github_responses flag from build_kwargs/convert_messages
into _chat_messages_to_responses_input and drop the id unconditionally
on that path, mirroring how reasoning items already strip id on replay.
phase/status/content are still replayed so cache-relevant signal isn't
lost — only the connection-scoped id is unsafe to reuse.
Written to apply independently of the #27038 length-cap fix so the two
PRs don't block each other; they touch adjacent conditions in the same
block and merge cleanly in either order.
Fixes#32716
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Keep empty-tail recovery scoped to the current stream segment and bound fallback flood retries. Preserve Telegram's server retry hint without blocking final delivery through a long cooldown.
Cron jobs in the gateway process wedged before HTTP on later non-streaming
API calls because interruptible_api_call spawned a daemon worker inside
nested cron thread pools. Route cron platform turns through direct_api_call
on the conversation thread instead.
Snapshot the selected stored session and route token for the full async submit
pipeline so a mid-flight session switch cannot resume the wrong chat or
misroute the user's text. Includes regression tests.
Fixes#54527 — a message typed into one TUI session could be silently
misrouted into (or overwritten by) another concurrently-open session.
Root cause: activeQueueSessionKeyRef is written on every render, but the
debounced draft-persist timer, the pagehide flush, and dispatchSubmit's
reject-restore path all read it lazily at async-resolve time instead of
capturing the scope that was active when the operation started. A session
switch landing between capture and resolve relabels one session's text
under the other session's key. A large paste widens the window (slower
synchronous render), which matches the original report.
Fix: introduce draftScopeRef, written only by the draft-swap effect (so it
always reflects the session whose text is actually loaded in the editor)
and read it instead of the render-time ref at both async write sites.
dispatchSubmit's restore() now uses the submittedScope already captured at
dispatch instead of re-reading the live ref.
Also adds isPendingDraftPersistCurrent as defense-in-depth: before the
debounce timer commits a write, it verifies its captured {scope, text}
pair is still the one on file. This is a no-op under the fix above (a
session swap or a newer keystroke already clears/replaces the pending
entry via clearTimeout), but turns any future regression that reintroduces
a stale/live-ref read at this call site into a dropped write instead of a
silent cross-session misroute.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Codex assigns assistant message items server-side ids that can run
400+ chars (base64 encrypted blobs), but the Responses API caps
input[].id at 64 chars and rejects the whole request with a
non-retryable HTTP 400. Once a session captures one of these long
ids, every subsequent turn replays it and 400s forever, since the
history persists it in codex_message_items.
Add a 64-char length guard at both replay sites — the history-to-
input converter and the final preflight gate — so oversized ids are
dropped while short ids (msg_...) are kept for prefix-cache hits.
Mirrors the existing pattern for reasoning items, which already
strip their id before replay because store=False means the API
can't resolve ids server-side anyway.
Fixes#27038
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
scripts/desktop-sandbox.sh runs a Hermes desktop instance in an isolated
sandbox — separate HERMES_HOME, separate Electron userData, and a
distinct
app name (HERMES_DESKTOP_APP_NAME) so it doesn't compete with the main
desktop instance's single-instance lock.
Two modes:
- Ephemeral (default): temp dir, cleaned up on exit
- --persistent: stored under .hermes-sandbox/ in the worktree git root,
survives restarts for repeat testing
In the Nix devShell the script is available as 'sandbox'.
Also makes APP_NAME overridable via HERMES_DESKTOP_APP_NAME in main.ts —
app.setName() runs before requestSingleInstanceLock(), so the overridden
name changes the lock key. collectRelaunchEnv already preserves
HERMES_DESKTOP_* vars through self-update relaunches; test updated to
cover the new env var.
we built .ts into .js for a minute there and dumped em in src, and those
old .js files are getting resolved over top of the ts updated ones so
desktop clients don't update.
just --clean the old files so there's never a conflict :3
The SLASH_TRIGGER_RE regex used (?:^|[\s]) as its left anchor, so typing
a / anywhere in the message (e.g. "hello /") opened the slash command
popover — even though slash commands only execute at the beginning of a
message. Anchor the regex strictly at position 0 (^) so the popover only
appears when / is the first character, matching the actual execution
semantics. The @-mention trigger is left untouched since those work
anywhere in the text.
removing tsc -b from the build script (previous commit) also removed
the only step that type-checked the electron/ directory — the CI
typecheck job runs tsc -p . --noEmit, which uses tsconfig.json whose
include is only ["src", "../shared/src"], so electron/ was silently
uncovered. extend the typecheck script to also run against
tsconfig.electron.json so electron/ stays type-checked in CI.
finalize passed conversation_history=history aliasing the snapshot so flush
skipped every message and wrote nothing. now flush _session_messages via
marker dedup like gateway shutdown. add real db e2e tests.
force_close_tcp_sockets stayed shutdown-only after #29507 to avoid
cross-thread FD recycle. That left CLOSED sockets unreclaimed when
httpx.close() skipped already-shutdown sockets under long-lived
gateways (~1 CLOSED fd / 6 min via proxy).
Add release_fds= for the owning-thread dispose path only; abort still
defaults to shutdown-only.
get_due_jobs()'s one-shot stale-entry recovery (#38758) treated an
expired run_claim (#59229) as proof the claiming tick died, but a run
stalled on network I/O — or a laptop asleep mid-run — legitimately
outlives the TTL while very much alive. The recovery then deleted the
job record mid-flight: list showed the job gone, and when the run
finished mark_job_run() found nothing to update, so last_run_at /
last_status / last_delivery_error were never recorded.
Two guards, per the liveness signals available:
- Same process (the common single-gateway case): before removing a
dispatch-limit-reached one-shot, consult the scheduler's running set
via a lazy import; if the job is still running here it is slow, not
stale — keep the entry.
- Cross process: run_job's monitor loop now refreshes run_claim.at
every 60s while the run is alive (including under
HERMES_CRON_TIMEOUT=0, which previously blocked without polling), so
an expired claim really does mean the owner died and the TTL stays a
dead-owner detector.
Fixes#62002
When web_search results are passed directly to web_extract, the URLs
field contains dict objects (e.g., {"url": "...", "title": "..."})
rather than plain URL strings. Two code paths assumed URLs were always
strings and crashed:
- agent/display.py get_cute_tool_message for web_extract: tried to call
url.replace() on a dict, causing AttributeError
- tools/web_tools.py web_extract_tool loop: tried regex search on a dict,
causing TypeError
Both now extract the URL string from dict objects (url or href field) or
fall back to empty string, preserving the cosmetic display and allowing
the tool to process the URLs correctly.
Fixes#61693
Curator review forks now pass credential_pool and request_overrides from resolve_runtime_provider into AIAgent so pool-backed custom providers can rotate credentials on 401 like main chat.
Add a glyph-agnostic ParticleField (float-up + organic sway/bank + springy
pop-in), skinned as pink pixel hearts. Hearts play on the pet when one is out
(in-window or popped out) and celebrate alongside; otherwise they rise from the
composer. A generic $petReaction bus mirrors the burst to the pop-out overlay
window so it reacts even while the app is minimized.
Consume the core `reaction` event to fire hearts on affectionate messages. DEV
Shift+H previews a burst.
Replace the client-side GOOD_VIBES_RE detection with the backend `reaction`
event: on it, flash the status-bar heart and the pet's celebrate pose. Detection
now lives once in the core, so the TUI, CLI, and desktop stay in sync.
tui_gateway forwards reaction_callback as a `reaction` event (shared by the TUI
and the desktop app). The interactive CLI wires reaction_callback to flash the
pet's celebrate ("jump") pose — the CLI's analogue of hearts.
Add a token-free, curated affection matcher (agent/reactions.py) — the single
source of truth for detecting user "vibes" (ily / <3 / good bot / heart emoji).
No model call, no tokens. Generalized to return a reaction *kind* so future
reactions can ride the same signal.
Wire an opt-in AIAgent.reaction_callback that fires from build_turn_context on
the incoming user message. It never touches the conversation (cache-safe) and
never fatal — a purely cosmetic side-beat each host can consume.
Radix's hoverable-content grace area can leave tips stuck over Electron drag regions; disable it and make tip content pointer-events-none so open state tracks the trigger only.
Switching connection mode (local / cloud agent / remote) no longer
full-window-reloads into the cold-boot CONNECTING screen. The primary
backend is torn down in place (no renderer reload); the shell + Settings
stay up while session lists are wiped so sidebar skeletons retrigger, then
the socket re-dials and config/sessions refresh. Cold-boot CONNECTING
latches off after the first successful boot; the intentional teardown
suppresses the backend-exit toast. Dev affordance: a "Preview soft switch"
button under Gateway diagnostics (Electron has no ?query= entry).
Gateway settings UI brought in line with the rest of Settings:
- Mode cards use the shared selectableCardClass on an equal-height
auto-rows-fr grid, stacking 1→3 (never an orphaned 2+1); titles wrap
instead of truncating.
- Remote gateway's auth detail moves into a ? tooltip in the title; drop
the redundant "connects to the one you choose" from the cloud card.
- textStrong buttons force px-0 so the underline sits flush with the label.
- Tooltip chip uses box-decoration-break: clone so the background hugs each
wrapped line (bg only on the text), capped at max-w-64.
Fully i18n'd (en + zh; ja/zh-hant inherit via defineLocale).
Old packaged Desktop apps re-entering bootstrap against an existing
~/.hermes/hermes-agent were still passing the baked-in --commit pin, which
detached the managed checkout back to the app stamp (e.g. 0.15.1) after
hermes update had already moved it forward.
Skip the packaged commit pin when activeRoot already has git metadata;
keep branch args and fresh-install commit pinning unchanged. Port of
#59902 onto the post-ts-ify bootstrap-runner.ts.
Co-authored-by: helix4u <4317663+helix4u@users.noreply.github.com>
Dashboard Chat is an xterm mirror of a TUI inside the gateway, so
server-side clipboard.paste never sees the browser clipboard. Upload
pasted/dropped images to the profile's images/ dir (same place
clipboard.paste / image.attach use), then drive /image over the PTY.
Uses a dedicated /api/chat/image-upload endpoint (magic-byte check,
25MB cap, profile scope) instead of relative managed-files uploads that
400 on local dashboards without a locked root. Ctrl/Cmd+Shift+V also
tries clipboard.read() for images before falling back to text, since
preventDefault on that chord suppresses the DOM paste event.
Salvages #57912 (client composition + /image PTY drive) and folds in
#48563's upload endpoint + drop path.
Co-authored-by: bird <6666242+bird@users.noreply.github.com>
Co-authored-by: tt-a1i <53142663+tt-a1i@users.noreply.github.com>
Windows drops webContents zoom on minimize/restore, so the UI snapped back
to 100% while Settings still read 125%. Zoom was only reasserted on the main
window's did-finish-load, never on show/restore and never for session windows.
Reassert the persisted level on show/restore + first load, wired once in
wireCommonWindowHandlers so the main window and secondary session windows
share it. The pet overlay opts out (zoom:false): it sizes its own OS window
to fit the sprite in unzoomed CSS px and has its own Alt+wheel scale, so
inheriting the global zoom would render the mascot larger than its window and
crop it (and it shares the renderer origin's zoom localStorage key).
Salvages #61245; keeps its pure-helper tests and adds a scope assertion.
Co-authored-by: HexLab98 <liruixinch@outlook.com>
The second lock block in get_or_create_session held self._lock during six
blocking operations on every inbound message: _is_session_ended_in_db
(SQLite SELECT), _should_reset (callback), _save (SQLite write + JSON write
+ os.fsync), and _recover_session_from_db (SQLite SELECT + UPDATE).
A code comment at line 1607 claimed 'SQLite calls are made outside the
lock' -- true only for _compression_tip_for_session_id, which was moved
out in a prior fix. The remaining I/O was never addressed.
Restructure into a four-phase lock/no-lock split that mirrors the pattern
already established at the bottom of the function:
Phase 1 (lock) -- read entry + session_id
Phase 1b (no lock) -- stale check + reset policy
Phase 2 (lock) -- apply decisions to _entries, capture snapshot + flags
Phase 3 (no lock) -- recovery DB query, _save from snapshot, end/create
_save_entries(snapshot) replaces _save() to avoid dict-mutation races when
called outside the lock. _query_recoverable_session splits the DB I/O out
of _recover_session_from_db so only the _entries assignment needs the lock.
Three early returns inside the lock block are eliminated in favour of a
unified save + return path.
The sync _session_has_compression_in_flight sat on the message hot path
and blocked the event loop twice: under session_store._lock during
_ensure_loaded_locked (JSON read) and via db.get_compression_lock_holder
(SQLite SELECT). Async-ify the method and offload both sources via
asyncio.to_thread; await the call site in _handle_active_session_busy_message.
Every inbound message calls get_or_create_session which synchronously
executes _is_session_ended_in_db → db.get_session → conn.execute on
the asyncio event loop. On a ~1.4GB state.db, this blocks the loop
for seconds to minutes, starving Discord heartbeats.
Upstream #55159 fixed the same pattern for self._session_db in
gateway/run.py but missed SessionStore._db in gateway/session.py.
This follows the exact same approach as #55159:
- session.py internals stay fully synchronous (zero changes)
- Threading.Lock contract is preserved
- All hot-path callers in run.py and slash_commands.py wrap calls
with await asyncio.to_thread(self.session_store.method, ...)
Affected: get_or_create_session, switch_session, update_session,
load_transcript, rewrite_transcript, rewind_session, reset_session,
set_model_override, _save — ~24 call sites across 2 files.
# Conflicts:
# gateway/slash_commands.py
Match the sibling pattern (pet-generate/generate-unavailable.tsx): inline the
portal URL literal in the ExternalLink href instead of a one-off named const.
Drop the portalBaseUrl→IPC→useState plumbing I added for the "create an agent"
link. HERMES_PORTAL_BASE_URL is a dev/staging-only override; threading it
through cloud.status() into React state just to build one link isn't worth it —
in prod it's always portal.nousresearch.com. Module-level constant instead.
Per review: the empty-state "create an agent" link went to the generic portal
agents list; point it at the Hermes Cloud create-instance flow
({portal}/cloud?setup=instance) instead. Derive the host from the portalBaseUrl
that cloud.status() already echoes so it honors HERMES_PORTAL_BASE_URL rather
than hardcoding a second copy of the portal host. Link text/copy → "Hermes
Cloud" (en + zh).
Git Bash hands file tools paths like /c/Users/... which Path() on native
Windows treats as relative \\c\\Users\\... under the process cwd. Reuse
local._msys_to_windows_path (extended for /cygdrive and /mnt drive forms)
in _resolve_path_for_task / _resolve_base_dir so read/write/search land on
the real drive. Container/WSL Linux paths are left untouched.
Salvages #50488 (drops unrelated desktop artifact commit); tests adapted
from #46995.
Co-authored-by: Jeff Watts <186512915+lEWFkRAD@users.noreply.github.com>
Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>
Tighten the salvaged Hermes Cloud code with no behavior change:
- main: one `trimCloudOrg` projection reused by the success-echo and the 409
org list (drop the duplicated map), and a `cloudLoginError()` factory for the
three needsCloudLogin throw sites.
- renderer: a `cloudLoginLapsed()` predicate for the duplicated
needsCloudLogin→signed-out check.
Cleanups on top of @ben's Hermes Cloud salvage:
- isConnectedAgent normalized both sides of the cloud-URL comparison (trim +
drop trailing slash + lowercase). The saved URL is host-lowercased by
normalizeRemoteBaseUrl but the discovered dashboardUrl is raw from NAS, so
a host-casing difference could silently break the connected-highlight.
- DesktopCloudStatus.signedIn doc said "AT-or-RT"; it actually reflects the
Nous portal Privy session (privy-token), not the gateway cookies.
Adds a third "Hermes Cloud" gateway mode to the desktop app: one portal
sign-in auto-discovers the agents on your account and connects to any of
them with no second interactive prompt.
- Electron: widen connection mode to 'local' | 'remote' | 'cloud', routed
through a centralized modeIsRemoteLike() so every resolution site treats
cloud exactly like remote; portal discovery (GET /api/agents over the
OAuth partition), Privy-cookie liveness, multi-org picker (NAS 409), and a
silent per-agent /oauth cascade (load protected root, not /login).
- Persist a cloudOrg on the cloud block; unselect cloud on mode switch.
- Renderer: Hermes Cloud ModeCard + agent picker (signed-out/loading/empty/
list), org picker, Change-org, connected-highlight + Connected pill.
- i18n (en + zh full; ja/zh-hant inherit via defineLocale), Cloud icon.
- IPC: hermes☁️{status,login,logout,discover,agent-sign-in}.
Salvage of #55402 onto current main: the original branch predates the
desktop electron .cjs -> .ts migration (39d09453f), so the electron half
was re-authored against the .ts files. Authorship preserved.
cloud-auto-discovery Phases 3 + 4.
Only restore held verification text when the loop genuinely ends through budget exhaustion. Preserve later interrupts and failures, keep generated-summary fragment explanations, and add regression coverage for both contracts.
Treat intent-ack continuation text as non-final so last-turn exhaustion requests a real summary instead of surfacing a premature promise. Keep iteration-limit fallback text free of the abnormal-fragment explainer.
Name the continuation fallback for its actual verification-only provenance so unrelated continuation paths cannot accidentally inherit its cron-delivery semantics.
Track held-back verification responses explicitly so budget exhaustion returns the composed report without a second model call. Keep unrelated error and recovery exit reasons intact, preserve Kanban timeout accounting, and cover the real run_conversation paths.
Clear stale final_response before verify-on-stop/pre_verify loop
continues, and normalize iteration-limit exit reasons in turn_finalizer
when a composed answer survives with unknown/budget_exhausted.
Fixes#61631
Sibling sites of the salvaged #55997 fix, all reading user-editable
config values through .get(key, '').method(): MoA slot provider/model
labels, gateway quick-command alias targets (2 sites), gateway.proxy_url,
and gateway.relay_url. Regression tests for the contributor's two sites
plus the MoA labels.
dict.get(key, default) returns None (not the default) when the key
EXISTS with value None. The default only applies when the key is ABSENT.
Chained method calls (.strip(), .upper(), .count()) crash with
AttributeError on NoneType.
Fix two confirmed hits:
- auxiliary_client.py: custom provider base_url/api_key (config null)
- anthropic_adapter.py: text block content (API null response)
Pattern: .get(key, "").method() → (.get(key) or "").method()
Without this UA tag the Feishu server does not push group @mention events
over the WebSocket transport. The "channel" tag tells the server to use
the Channel protocol which enables group-message routing in addition to P2P
direct messages.
Root cause: FeishuWSClient was created without any UA signaling tag, so the
server defaulted to the basic DM-only push mode. Group @mention events were
silently dropped before reaching Hermes.
Fixes https://github.com/NousResearch/hermes-agent/issues/50656
Also adds a regression test verifying the UA tag is present in the
FeishuWSClient constructor call.
Sibling of the salvaged #53196 read-path fix: setdefault() does not
replace a present-but-null key, so saving platform tools with
known_plugin_toolsets: null in config.yaml crashed on indexing None.
When config.yaml has known_plugin_toolsets set to null (or any value
mapped to None by the YAML loader), config.get returns None (dict.get
only falls back to the default when the key is absent, not when its
value is None). The subsequent set(known_map.get(platform, [])) then
crashes with TypeError: NoneType object is not iterable and the gateway
fails to start, even though no plugin toolsets are configured.
Add or-empty-dict and or-empty-list guards so a null/None value is
treated as empty instead of crashing the platform-tools resolver.
`_load_web_config()` is typed `-> dict` but returned `load_config().get("web",
{})`, which is `None` when the config has a present-but-null `web:` section
(YAML `web:` with no body). Every caller then does
`_load_web_config().get(...)` and raises `AttributeError: 'NoneType' object
has no attribute 'get'` — this hits `_get_backend`, `check_web_api_key`, and
the extract-char-limit reader.
Separately, `check_web_api_key()` read the backend as
`.get("backend", "").lower()`; a null `web.backend` value yields `None` (the
`""` default only applies when the key is absent), so `None.lower()` raised.
`check_web_api_key` is the `check_fn` gate for `web_search`/`web_extract`, so
this surfaced as an exception during tool-availability checking.
- Make `_load_web_config()` honor its `-> dict` contract (`... or {}`), fixing
the null-`web:`-section crash at every call site.
- Guard the backend value in `check_web_api_key` with `or ""`, mirroring the
existing guard in `_get_backend`.
Adds regression tests for both the null-backend-value and null-web-section
cases.
* test: deflake CI and dev-machine flaky tests in bulk
Fixes ten distinct flake sources found by mining recent CI failures and
running the full suite on a dev machine with real user state:
CI-observed races:
- tests/conftest.py live-system guard: allow signal 0 (pure liveness
probe) through _guarded_kill/_guarded_killpg. psutil.pid_exists()
probes a just-killed grandchild reparented to init; the subtree check
fails for it and the guard RuntimeError'd
test_entire_tree_is_sigkilled_not_just_parent intermittently on
unrelated PRs.
Hermeticity flakes (fail on dev machines with real state, pass on CI):
- agent/coding_context.py: _marker_root() now skips the shared temp
root (tempfile.gettempdir()) like it skips $HOME — a stray
/tmp/package.json flipped every tmp_path test into the coding
posture (9 failures in test_coding_context.py).
- test_agent_guardrails.py: pin MAX_CONCURRENT_CHILDREN=3 via autouse
monkeypatch instead of freezing the user's real config value at
import time (import-time vs call-time config mismatch).
- test_web_tools_config.py: TestCheckWebApiKey now neutralizes the
ddgs package probe and registry providers — the optional ddgs
package in a dev venv lit up the fallback backend.
- test_credential_pool.py: block claude_code/hermes-oauth credential
autodiscovery in the two pool-merge tests that assert exact id
lists (a real ~/.claude/.credentials.json seeded an extra entry).
- test_modal_sandbox_fixes.py: clear _permanent_approved /
_session_approved — the user's real command_allowlist silently
approved the guard-escalation commands under test.
- test_setup_irc.py: stub prompt_checklist to select only the IRC row;
the non-TTY cancel fallback re-ran the real configured platforms'
interactive setup_fn, which hit input() under captured stdin.
- test_doctor.py: TestGitHubTokenCheck now patches the module-level
HERMES_HOME constant (the file's established pattern) instead of
only setenv — doctor was running PRAGMA integrity_check against the
real multi-GB state.db and blowing the 300s per-file budget.
Latent atexit-duplication (same _enter_buffered_busy class as #34217):
- test_undo_command.py: drop importlib.reload(tui_gateway.server) in
fixture teardown; reload re-registers the module's atexit hooks.
- test_session_platform_resolution.py: drop per-test reload of
tui_gateway.server; every resolver reads env at call time.
* test: sentinel model value in ignore-user-config fallback assertion
With HERMES_IGNORE_USER_CONFIG=1, load_cli_config() falls back to the
repo-root cli-config.yaml (untracked, gitignored). On a dev machine that
file can legitimately set the same popular model the test hardcoded
(anthropic/claude-sonnet-4.6), flipping the != assertion locally while
CI (no cli-config.yaml) stayed green. Use an impossible sentinel model
name instead.
Sibling sites of the salvaged #47334 fix: xai/openai/elevenlabs/gemini/
mistral/piper/neutts subsection reads in transcription_tools.py and
tts_tool.py used .get(key, {}) which passes a present-but-null value
through as None. All provider-subsection reads now use .get(key) or {}.
Providers without a DEFAULT_CONFIG entry (e.g. stt.xai) were still
receiving None even after the load_config() deep-merge fix, since the
merge can only fill sections that have defaults.
When stt.local, tts.edge, or other config subsections are explicitly set
to null in config.yaml (which happens by default on a fresh --voice
setup), stt_config.get('local', {}) returns None instead of {} because
YAML null preserves the key. The chained .get('model') then crashes
with 'NoneType' object has no attribute 'get'.
Apply the defensive (x or {}) pattern to every place a config subsection
is read via .get('xxx', {}). Covers local, edge, openai, mistral, and
elevenlabs subsections in both transcription_tools.py and tts_tool.py.
Closes#47318
skills: null crashed with AttributeError, and a bare scalar
disabled: my-skill was split into a set of characters. Both now
normalize the same way agent.skill_utils._normalize_string_set does:
null -> empty set, scalar -> single-item set. Non-dict skills
sections are ignored.
Closes#13026.
_load_context_cache() returned None when context_length_cache.yaml
contained 'context_lengths:' (no value) — YAML parses this as
{'context_lengths': None} and dict.get(key, default) only returns
the default when the key is absent, not when the value is None.
This caused AttributeError in every downstream caller (issue #47135).
Fix: use 'or {}' instead of default= so both absent key and
None value return an empty dict.
Fixes#47135
Addresses Copilot review on #61348: the HTML-escaped role, while safe from
injection (quotes are escaped), still contains whitespace when a crafted role
is supplied, which splits the class attribute into several unintended CSS
classes. Keep the escaped role for the display badge, and reduce the raw role
to a single safe CSS token (alnum/-/_) for the class name. Real roles
(user/assistant/system/tool) are unchanged, so the existing .message-<role>
rules still match.
The gateway reconnect watcher forwards is_reconnect=True to every
adapter.connect() call on every retry. Adapters whose signature omits
the kwarg raise TypeError at every reconnect attempt and stay silently
disconnected — the exact bug that shipped for QQAdapter and only
surfaced after messages stopped flowing on the QQ channel for hours.
This test statically parses every adapter.py under gateway/platforms/
and plugins/platforms/ (via AST, so third-party SDKs like slack_sdk,
matrix-nio, aiohttp, telegram, etc. are NOT required in the test env)
and asserts every *Adapter class with an async connect() accepts
is_reconnect — either as a keyword-only argument or absorbed by
**kwargs.
Also fixes plugins/platforms/wecom/callback_adapter.py:WecomCallbackAdapter,
which the new test caught as a second offender. Same class of bug: bare
'async def connect(self)' signature would die on the first reconnect.
Companion to #59429 (which fixed the original QQAdapter offender).
The base adapter's signature was updated to include
, which the reconnect watcher passes as
during reconnection. All other platform adapters were
updated, but QQAdapter was missed, causing:
TypeError: QQAdapter.connect() got an unexpected keyword argument 'is_reconnect'
This leads to an infinite retry loop since every reconnect attempt fails
immediately with the same TypeError.
Fix: add to QQAdapter.connect()'s signature.
QQBot has no server-side update queue, so the flag is accepted only for
interface conformance.
Test: new test_connect_accepts_is_reconnect_param verifies both
adapter.connect() and adapter.connect(is_reconnect=True) succeed without
raising.
The streaming fallback path read yaml_cfg.get("gateway", {}).get("streaming") when top-level streaming was absent or malformed. If a user accidentally set gateway to a scalar value, config loading crashed with AttributeError instead of ignoring the malformed block and using defaults.
Read the gateway block once, verify it is a mapping before accessing nested streaming, and keep the existing gateway.platforms fallback using the same checked value.
Adds a regression test for config.yaml containing gateway: disabled.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
GatewayConfig.from_dict(), PlatformConfig.from_dict(), SessionResetPolicy.from_dict(), and StreamingConfig.from_dict() assumed their input sections were mappings. A malformed scalar from legacy gateway.json or an internal caller could crash config loading with AttributeError before env overrides/defaults had a chance to recover.
Coerce non-mapping sections to empty dicts, skip malformed platform entries, and keep valid sibling platform configs loading normally.
Tests cover scalar platform blocks, scalar nested reset/streaming sections, and malformed PlatformConfig home_channel/extra values.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Sibling site of the load_cli_config fix (#58277): _deep_merge treated a
YAML-null section (terminal: with no value) as an override, replacing
the entire DEFAULT_CONFIG dict for that section with None. Every
downstream consumer expecting a mapping was a latent crash, and default
sub-keys were silently lost. A None override of a dict default is now
ignored, matching the CLI loader's behavior. Scalar-null overrides are
unchanged.
Three tests for the #61099 salvage: OpenRouter attribution headers
present after switching to openrouter.ai, Kimi User-Agent sentinel
present after switching to api.kimi.com, and stale headers cleared
when switching to a provider with no URL-specific headers.
2/3 fail on unpatched main (DID NOT ATTACH), confirming the bug.
switch_model() rebuilds _client_kwargs from scratch (api_key + base_url)
but does not call _apply_client_headers_for_base_url(), so provider-
specific headers like OpenRouter HTTP-Referer and X-Title are lost.
Subsequent requests show "Unknown" in OpenRouter dashboard logs.
Call _apply_client_headers_for_base_url() after rebuilding _client_kwargs
and before creating the new client.
Fixes#61099
Follow-ups for salvaged PR #43819: the registry key was
str(Path(db_path).expanduser()) — a symlinked or relative path to the
same DB file got its own connection, silently reintroducing the exact
multi-writer contention the registry prevents. Key on Path.resolve()
(OSError-tolerant fallback). Adds a symlink regression test and the
AUTHOR_MAP entry for adambiggs.
Every MemoryStore instance opened its own SQLite connection guarded by
its own RLock. Several providers coexist in one process (the main agent
plus every delegate_task subagent), so instances pointing at the same
memory_store.db raced as independent WAL writers. Combined with writes
that were not rolled back on error, one connection could leave an open
write transaction that pinned the write lock and made every other
connection's writes fail with "database is locked" for the full busy
timeout.
Instances for the same database now share ONE process-wide connection
and ONE re-entrant lock, so access is fully serialized and
cross-connection contention is impossible. The shared connection is
refcounted: closing one instance never tears it out from under a live
sibling, and the last close releases it. The connection runs in
autocommit (isolation_level=None) so a write that raises mid-method can
never leave a dangling transaction holding the write lock; the existing
explicit commit() calls become harmless no-ops.
The provider's shutdown() now calls the refcount-guarded close() instead
of just dropping the reference: leaving finalization to GC kept the
connection (and its write lock) alive indefinitely on long-running
gateways, prolonging the exact contention this fix removes. The last
provider now releases the connection deterministically while siblings
stay live; regression tests fail without the wiring.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Flip the two tests that pinned the old buggy behavior (rewrite_transcript
called after in-place compaction) to assert the corrected invariant from
#61145: archive_and_compact() already persisted, so the handler must NOT
call rewrite_transcript — its replace_messages(active_only=False) would
DELETE the just-archived rows.
E2E-verified against a real SessionDB: 6 soft-archived rows are wiped by
replace_messages' default path, confirming the data-loss premise.
When gateway session-hygiene auto-compression fires with in-place
compaction, the flow was:
1. _compress_context() calls archive_and_compact() — soft-archives old
rows (active=0, compacted=1) and inserts compacted messages as the
new active set. This is the non-destructive, durable path.
2. The hygiene handler then called rewrite_transcript() — which calls
replace_messages(active_only=False) — DELETEing ALL rows including
the just-archived turns. Silent permanent data loss (#61145).
The interactive /compress handler had the same bug.
Fix: only call rewrite_transcript() when session rotation produced a new
session id (legacy path). When in-place compaction succeeded, skip the
rewrite — archive_and_compact() already handled persistence.
Closes#61145.
test_accepted_at_every_position spawned 11 separate
'python -m hermes_cli.main' subprocesses, each cold-importing the full
CLI module tree under a 15s TimeoutExpired deadline. On a loaded CI
worker the import alone can exceed that (slice 2/8 flaked exactly here
on PR #61726's run, TimeoutExpired at subprocess.py:1253), failing PRs
that never touched the CLI.
Replace with ONE driver subprocess that imports hermes_cli.main once
and parses all 11 argvs in-process (catching SystemExit per argv),
reporting JSON results. Same assertions per argv, identical semantics
(verified the --help-before-unknown-flag exit behavior matches the old
method), ~11x less import work, and the 180s timeout only trips on a
genuine hang.
Structural completion of the malformed-job freeze fixes (#61382 id-less,
#61525 non-dict schedule, #61581 bad next_run_at): wrap the per-job body
of _get_due_jobs_locked in try/except so any FUTURE malformed-field
variant degrades to skipping that one job for the tick instead of
aborting the scan before save_jobs() and freezing the whole profile's
scheduler.
Also: restore test_repeated_concurrent_runs_accumulate_completed_count
to TestMarkJobRunConcurrency (accidentally re-parented by the #61581
diff), add a containment regression test, and AUTHOR_MAP for hydracoco7.
E2E: one jobs.json carrying all five malformed shapes (drifted job_id,
missing id, null schedule, garbage next_run_at, non-string last_run_at)
plus a healthy sibling — single tick contains all five, sibling fires,
repairs persist, second tick stable. 670 cron tests green.
One bad next_run_at value in jobs.json aborts the due-jobs scan with
ValueError from fromisoformat, before any save_jobs, so siblings lose
progress (fast-forwards etc).
Early normalization in _get_due_jobs_locked + defensive parses in
compute_next_run / _recoverable_oneshot_run_at.
Added test_bad_next_run_at_does_not_crash_or_block_sibling_jobs.
A job record in jobs.json can have a non-dict 'schedule' value (null, string,
etc.) from direct edit or old writers.
In _get_due_jobs_locked:
schedule = job.get('schedule', {})
kind = schedule.get('kind')
This (and direct schedule['kind'] in compute_next_run etc.) raises and
aborts the entire due-jobs scan before save_jobs() or advancing next_run_at
for healthy jobs. Exactly the same failure mode as the id-less job P1.
Fix: normalize non-dict schedules to {} early (before any use), matching the
defense added for id-less records. Also added defensive guards in compute
functions.
Added regression test that a bad schedule does not crash and healthy sibling
is still returned.
Refs similar pattern in #61382.
A cron record authored by a direct jobs.json edit that bypassed
add_job() can lack an "id" key (older writers used "job_id"). Every
site in _get_due_jobs_locked indexes job["id"] eagerly — both the
logging helpers (job.get("name", job["id"]) evaluates the default
argument unconditionally) and the 'for rj in raw_jobs: if rj["id"] ==
job["id"]' persistence loops. A single malformed record therefore
raised KeyError mid-tick, aborting the entire scan before save_jobs()
ran. Result: healthy jobs' fast-forwarded next_run_at was computed in
memory then discarded on the exception unwind, freezing the whole
profile's scheduler in a per-minute loop (observed dormant for weeks).
Fix: normalize id-less records at the top of _get_due_jobs_locked before
anything keys off job["id"] — recover the id from a drifted "job_id"
key when present, else synthesize one via uuid4, and persist. This
repairs the whole bug class at the source rather than guarding each of
the ~12 downstream index sites.
Adds a regression test that fails with KeyError on the current code and
passes with the fix, asserting a healthy sibling job is still returned
when an id-less record shares the store.
The salvaged fix sets HERMES_YOLO_MODE in main()'s dispatch path before
_prepare_agent_startup(); this follow-up also sets it inside
_prepare_agent_startup() itself so every launcher that triggers plugin/tool
discovery (incl. the Termux fast-CLI path) gets the same ordering guarantee
before tools.approval freezes _YOLO_MODE_FROZEN (#60328).
The HTML session export interpolated the tool-call name into the page
without escaping, while every sibling field went through _escape_html. A
tool-call name is attacker-influenced, so a prompt-injected model can emit
a name containing HTML that executes when the export is opened in a browser.
Escape the tool-call name like the other fields.
switch_model() unconditionally set agent.provider but only set
agent.base_url when the resolved value was truthy. When a real
provider change resolved an empty base_url (e.g. minimax after
copilot), the agent ended up with provider="minimax" but
base_url still pointing at api.githubcopilot.com. That incoherent
pair then got snapshotted into agent._primary_runtime, so it kept
re-applying on every subsequent turn via restore_primary_runtime()
until the process restarted.
try_activate_fallback() and _swap_credential() were audited and
confirmed unaffected: both always derive base_url from an actually
constructed client, never from a possibly-empty resolver hint.
Fix: when base_url is empty AND the provider is genuinely changing,
raise ValueError instead of silently keeping the old provider's URL.
This routes through switch_model()'s existing snapshot/rollback
path, and callers (tui_gateway/server.py's _apply_model_switch)
already catch and surface a clean "switch failed, staying on X"
message. Re-selecting the SAME provider with an empty base_url
(credential-only refresh) still keeps the current URL, unchanged.
Fixes#47828
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Port from openai/codex#31188: a parse failure in a policy-bearing config
file must not silently replace the effective policy with an empty/default
one. Codex's load_exec_policy_with_warning replaced the whole exec policy
with Policy::empty() when a .rules file failed to parse, silently dropping
managed prompt/forbidden rules; the fix preserves the managed policy while
still warning.
Hermes had the same bug shape in load_config(): a YAML parse error made
_load_config_impl() fall through to DEFAULT_CONFIG, dropping every user
override — including approvals.deny rules, which are documented to block
commands even under --yolo. In a long-running gateway, a user mid-editing
config.yaml into broken YAML silently disarmed their own deny rules on the
next load.
Now, when the process has a last successfully loaded config for that path
(_LAST_EXPANDED_CONFIG_BY_PATH), a parse failure keeps serving it (cached
under the corrupt file's signature so the broken file isn't re-parsed) and
the warning says edits are being ignored until the YAML is fixed. Fresh
processes with no last-known-good keep the existing DEFAULT_CONFIG
fallback and warning.
E2E-verified: deny rule 'curl*evil.com*' still blocks after mid-process
corruption; fixed file reloads normally; fresh-process fallback unchanged.
The earlier fix gated _resolve_use_tui, but the EARLY launcher
(_wants_tui_early) decides TUI from display.interface before cmd_chat
runs — so a `display.interface: tui` default still booted the Ink UI for
headless spawns (kanban workers), whose no-TTY bail-out exits 0 →
"protocol violation". Gate the early resolver on a real TTY: headless
stdio never boots the TUI regardless of config; explicit --tui still does.
Dragging a task done→ready did nothing: the respawn guard saw a run that
completed within the success window and deferred forever, unable to tell a
deliberate operator re-run from a status flap. Now a re-queue event
(status change, promote, unblock, reclaim) AFTER the completion bypasses
the recent_success guard, so an explicit done→ready runs again.
A retried task (→ running) kept showing "crashed Nx": the in-flight run
has no outcome yet, so the trailing crash scan skipped it and kept
counting the prior streak, and the consecutive_failures counter lingers.
Exempt `running` from both repeated_failures and repeated_crashes so a
fresh attempt clears the banner until it itself resolves (re-fires if the
new run also fails).
An inherited HERMES_TUI=1 or a `display.interface: tui` config default sent
kanban workers into the Ink TUI, whose no-TTY bail-out exits 0 without doing
the task — every attempt ended in "protocol violation". Two layers:
- _default_spawn pins `--cli` (highest-precedence interface flag) and strips
HERMES_TUI from the child env (covers older builds on PATH).
- _resolve_use_tui gates ambient TUI prefs (env/config) behind a real TTY;
an explicit --tui still wins so the informative bail-out stays reachable.
A manual done (dashboard/desktop drag) runs complete_task but ends no
run, so a trailing crashed/crashed run history never gains the
'completed' outcome that breaks the repeated_crashes streak — the card
kept flagging "needs attention" forever after being finished.
repeated_failures had the same hole via a stale counter. Terminal
statuses are now exempt from both: done means done; the history stays
on the event log for audit. Regression test included.
Adding the 6 gpt-5.6 slugs to DEFAULT_CODEX_MODELS grew the curated codex
catalog to 11, above the test's max_models=10 cap. That truncated the
picker list to 10 while total_models reported 11, breaking the
total_models == len(models) assertion. The cap was an implicit
change-detector on catalog size; raise it to 100 so the list is never
truncated and the count-consistency invariant stays meaningful as new
gpt-5.x slugs land.
Close the remaining end-to-end gaps so the full gpt-5.6 family (sol/
terra/luna + their -pro high-effort modes, 6 slugs) works on every
surface a user can reach them through:
- agent/auxiliary_client.py: the Codex OAuth backend hard-caps context
at 272K for gpt-5.6 exactly as it does for 5.4/5.5, but the default
50% compaction trigger would summarize at ~136K and waste half the
usable window. Extend the existing _is_codex_gpt54_or_gpt55 chokepoint
(single enforced predicate feeding _compression_threshold_for_model)
to match gpt-5.6* on the openai-codex route so those sessions get the
same 0.85 auto-raise. Direct-API/OpenRouter routes (full 1.05M window)
are unaffected; the historical codex_gpt55_autoraise opt-out still
applies. The one-time notice banner is model-dynamic and already
renders the correct slug/cap.
- hermes_cli/config.py, agent/agent_init.py: refresh the autoraise
comments/notice to mention the 5.6 family.
- hermes_cli/codex_models.py: add the -pro variants to DEFAULT_CODEX_MODELS
+ forward-compat so ChatGPT-OAuth (openai-codex) Pro users see the full
family in /model, not just the base tiers.
Supersedes the earlier commit's note that 5.6 was intentionally kept out
of the codex catalog: the slugs are confirmed routable (OpenRouter live
+ codex backend), so they belong there like every other codex-capable
gpt-5.x slug.
E2E verified across all 6 slugs: direct-API ctx 1.05M, codex ctx 272K,
pricing reachable from openai + openai-api routes, codex compaction
override 0.85 (and None on direct-API + when opted out), present in
openai-api picker + codex catalog, /model gpt resolves to sol on both
native routes. Guard tests added for the compaction route matrix.
Rerun scripts/build_model_catalog.py so the manifest is source-generated
rather than hand-edited (the -pro rows from the cherry-picked #61587 were
already correct; only updated_at changes).
PR #61587 adds sol-pro/terra-pro/luna-pro to the aggregator lists.
Complete those on the native surfaces the same way this PR completes
the base tiers:
- hermes_cli/models.py: -pro variants in _PROVIDER_MODELS[openai-api].
- agent/usage_pricing.py: alias ("openai", "gpt-5.6-*-pro") onto the
base-tier PricingEntry rows — the -pro high-effort modes bill at the
SAME per-token rates (verified against OpenRouter live pricing
2026-07-09: identical prompt/completion prices for base and -pro);
they cost more per task by consuming more tokens, not a higher rate.
- Context lengths need no new entries: "gpt-5.6-sol" et al. are
substrings of their -pro variants and both lookup tables match
longest-key-first (verified: sol-pro -> 1.05M direct / 272K codex).
- model_switch sort: -pro variants parse as suffix "sol-pro" (rank 1),
so /model gpt still defaults to base sol — pinned by test.
- Not added to DEFAULT_CODEX_MODELS: only confirmed routable via API/
OpenRouter so far; codex live discovery will surface them if ChatGPT
exposes them, same policy as other unconfirmed codex slugs.
Tests: invariant tests extended (pro aliases share base entries, base
sol outranks sol-pro); 191 targeted tests pass.
Phase-2 review findings addressed:
- resolve_billing_route: normalize the "openai-api" picker slug to the
"openai" billing provider — without this the ("openai", <model>)
_OFFICIAL_DOCS_PRICING keys (incl. every pre-existing gpt-4o/gpt-4.1
entry, not just 5.6) were unreachable when the provider is openai-api.
- pricing_version: drop the "preview" tag (GA 2026-07-09 at same rates).
- model_metadata comment: dict order is cosmetic — lookups length-sort
keys at match time; the old comment implied a positional invariant.
- model_switch comment: note "sol" is a series codename, not a generic
quality word.
- tests/hermes_cli/test_gpt56_registration.py: behavior contracts (no
list snapshots) — sol > terra/luna > 5.5 sort invariant, pricing
reachability from both openai and openai-api routes, cache-write
1.25x / cache-read 0.10x input relation.
PR #61578 added the GPT-5.6 series (sol/terra/luna) to the two aggregator
surfaces (OPENROUTER_MODELS, _PROVIDER_MODELS[nous]). This completes the
registration on the remaining surfaces per the standard add-model checklist:
- agent/model_metadata.py: DEFAULT_CONTEXT_LENGTHS 1.05M (direct API, same
as gpt-5.5; more-specific keys precede gpt-5.5 for longest-substring
matching) + _CODEX_OAUTH_CONTEXT_FALLBACK 272K for all three slugs.
Without these the direct-API fallback matched generic "gpt-5" = 400K.
- hermes_cli/codex_models.py: DEFAULT_CODEX_MODELS + forward-compat
templates so ChatGPT-OAuth (openai-codex) pickers surface the series.
- hermes_cli/models.py: _PROVIDER_MODELS[openai-api] (native API picker).
- agent/usage_pricing.py: _OFFICIAL_DOCS_PRICING snapshot — sol 5/30,
terra 2.50/15, luna 1/6 per 1M in/out; cache read 0.10x input, cache
write 1.25x input (OpenAI billing change starting with the 5.6 series).
GA 2026-07-09 at preview rates. Sol Fast mode (Cerebras tier) excluded.
- hermes_cli/model_switch.py: rank "sol" as a flagship suffix so
/model gpt resolves to gpt-5.6-sol, not alphabetical-first luna.
Verified: registry E2E via real imports (both context tables, codex
forward-compat from a gpt-5.5 template, billing-route lookup for
openai/gpt-5.6-sol -> 5.00/M), alias resolution on openai-codex and
openai-api resolves to gpt-5.6-sol; 183 targeted tests pass
(model_metadata, usage_pricing, codex_models, model_catalog).
hermes send "MEDIA:/x.png This Caption" now arrives as one native captioned
bubble instead of a separate text message followed by an uncaptioned bubble.
Root cause: the standalone senders (hermes send / cron / send_message tool)
stripped the MEDIA: tag, sent the remaining text as its own message, and
called the media send with no caption -- even though hermes send's help
advertises the captioned form and the bridges/adapters already support a
caption. Signal already captioned correctly.
- tools/send_message_tool.py: new _media_caption_split() chokepoint decides
caption-vs-separate-body (single captionable non-voice file within the
platform's message-length cap). Wired into the Telegram, WhatsApp and
Discord dispatch paths.
- Telegram/WhatsApp/Discord: when the single captioned file is missing, the
caption text is delivered as a plain message so it is never silently lost.
- Telegram caption send gets a MarkdownV2->plain parse fallback.
- Tests: _media_caption_split unit tests + per-platform caption tests
(ride, multi-file fallback, voice exclusion, over-limit fallback,
missing-file text fallback); updated the 3 tests that asserted the old
text-then-media split.
Closes the gap reported against #58911 (the MEDIA_CAPTION directive PR);
credit to @ferreiraesilva for surfacing the caption behavior.
Review finding: callers mutate the returned dicts in place —
hermes_cli/web_server.py annotates s['enabled']/s['usage'] on the skills
list — so handing out the cached objects poisons the cache for every
subsequent caller (and is a cross-thread shared-mutable hazard in the
gateway). Return [dict(s) for s in cached] on both hit and miss paths;
warm-path cost is negligible (241x speedup retained on a 300-skill
fixture). Regression test mutates a returned list/dict and asserts the
next cached call is clean.
Review findings on the cherry-picked cache (follow-up to #58985):
- The cache key was the max mtime of only the TOP-LEVEL scan dirs.
Adding/removing a skill inside a category subdir bumps the category
dir's mtime, NOT the root's, so the cache served a stale list
indefinitely. Replace with a per-dir signature covering roots +
immediate children (one scandir per dir; mirrors
hermes_cli/profiles.py::_count_skills from d5eee133e).
- The disabled-set is config-driven and changes with no filesystem
mtime bump; fold it into the signature so /skills disable takes
effect without a restart.
- Platform is part of the signature (gateway processes serve multiple
platform scopes; scan results are platform-filtered).
- Add a 30s TTL to bound staleness from in-place SKILL.md edits (file
mtime is invisible to any directory signature).
- The original also keyed dirs off the module-level SKILLS_DIR constant;
the scan itself uses _skills_dir() (live profile HERMES_HOME) — use
the same resolution for the signature.
Mutation-verified: nested-add, disabled-set, and TTL tests fail against
the pre-fix cache and pass with it.
_find_all_skills() re-reads every SKILL.md on every call, which is
wasteful when nothing changed between turns. Cache results keyed by
the max mtime across all scanned skill directories — a skill write
touches the directory, bumping mtime past the cached value and
triggering an automatic re-scan.
skip_disabled True/False are cached separately.
This commit is unstacked from #58984; it carries only the skill
discovery cache change.
(cherry picked from commit cd65673a8fddfec8a0fa130197d49aaab1fefc77)
The salvaged PR added a standalone test_reasoning_timeouts.py that duplicated
the structure of the existing parametrized test_reasoning_stale_timeout_floor.py.
Fold the v4-flash/v4-pro/-free positive cases and deepseek-chat negative cases
into the canonical parametrized tables and remove the redundant file.
DeepSeek V4 models (deepseek-v4-flash, deepseek-v4-pro) emit
reasoning_content in a separate delta field before final content,
requiring the same 600s stale timeout floor as R1. Without this,
streams hang for 30–50s with APITimeoutError on providers like
opencode-go while direct calls succeed in ~3s.
Fixes#60338.
Phase-2 review finding: the validation branch expanduser()s the path but
web_server.py reads os.environ['HERMES_WEB_DIST'] raw at import — a
'~/dist' value would validate here and still 404 there. Write the
expanded path back before the web_server import. Adds a regression test
asserting the env var holds the expanded path after cmd_dashboard.
Review finding: PR #40632's branch had silently dropped gemma-3-27b
from the keep-extra_content test loop (part of its Gemma narrowing,
which this salvage reverts). Restore main's original coverage so a
future narrowing back to Gemini-only fails loudly.
Trim the salvaged commit to its two still-valid conversions:
- ChatCompletionsTransport.convert_messages (copy-on-write sanitize)
- QwenProfile.prepare_messages (copy-on-write normalize + cache_control)
Dropped from the original PR:
- agent/prompt_caching.py selective-copy: superseded by #57229 which
already rewrites apply_anthropic_cache_control on current main.
- Gemma extra_content narrowing (_model_consumes_thought_signature
'gemini or gemma' -> 'gemini' only) + its two tests: unrelated
behavior change reverting deliberate e8c3ac2f5; belongs in its own
PR with its own justification if pursued.
Conflict resolution: preserved main's newer timestamp-stripping
(#47868) inside the copy-on-write path.
Mock _preflight_user_systemd and _select_systemd_scope in
test_systemd_start_refreshes_outdated_unit and
test_systemd_restart_refreshes_outdated_unit. These tests target
unit-file refresh logic, not D-Bus reachability, so the preflight
check was causing spurious UserSystemdUnavailableError on macOS,
WSL, and Docker where systemd is unavailable.
(cherry picked from commit 34113300a1cbbecf7c9fa2201ddaf517acc521d3)
A custom HERMES_WEB_DIST without --skip-build skipped BOTH the web UI
build and any validation: cmd_dashboard fell through the build gate and
started the server against a dist that may not exist, serving 404s with
no obvious cause. This is the same failure mode issue #23817 fixed for
the --skip-build branch — the env-var branch was left unvalidated.
Add the missing else-branch: fail fast with actionable guidance when
HERMES_WEB_DIST has no index.html, proceed (still without building) when
it does.
Credit: @Caelier (#17845) originally proposed dist validation for the
dashboard startup path; the --skip-build half of that PR's scope has
since landed via the #23817 fix, this covers the remaining env-var path
on the rewritten cmd_dashboard surface.
Two async handlers still called the cron profile-walk helpers directly on
the FastAPI event loop after the 49fa04a23/346e5673d threadpool migration:
- POST /api/cron/fire called _find_cron_job_profile() inline — it walks
every profile and lists its jobs (file I/O per profile), stalling the
loop before the 202 is returned.
- POST /api/cron/blueprints/instantiate called _call_cron_for_profile()
inline for create_job.
Route both through the existing _run_cron_dashboard_io threadpool wrapper
like every other cron dashboard endpoint.
Credit: @riceharvest (#50948) originally identified the sync-I/O-in-async-
handlers bug class for the desktop boot endpoints; 49fa04a23, 346e5673d,
7d0ddbb2f, d5eee133e and 24d5bda1e have since fixed most of that PR's scope
via the managed threadpool + PID cache + alias-map surfaces. This covers
the two cron handlers those merges missed.
Review finding: the substring check ('kimi' or 'moonshot' in model)
under-matches bare release slugs like k2-thinking that the repo's
canonical _model_name_is_kimi_family matcher (anthropic_adapter.py)
already covers. Reuse it instead of a second ad-hoc matcher; add a
regression test for the bare-slug case.
Adapted from PR #26014's test file to the canonical seam
(tests/run_agent/test_anthropic_prompt_cache_policy.py _make_agent
helper) instead of a new top-level file with sys.path manipulation.
Covers: kimi-k2.6 + moonshot-v1 on OpenRouter (envelope layout),
kimi via Nous Portal, and the non-OpenRouter negative case.
Kimi/Moonshot models on OpenRouter honour the same envelope-layout
cache_control markers as Claude on OpenRouter, but the policy fell
through to (False, False) — serving ~1% cache hits on 64K-token prompts
and re-billing the full prompt every turn. Observed within-turn
progression with cache enabled: 1% -> 67% -> 84% -> 97%.
(cherry picked from commit 3b857a35e, agent/agent_runtime_helpers.py hunk only;
the original PR #26014 branch also carried unrelated .dev-workflow artifacts
which are intentionally not included)
Structured review (2a/2b/2c) findings, all fixed:
- MAJOR: detect_local_server_type memo was process-lifetime with no
invalidation, permanently pinning a URL's server type. Now a bounded
1h TTL ((type, monotonic) tuples) so a backend swap on the same port
is re-detected. Test covers ollama->lm-studio swap after expiry.
- MAJOR: legacy disk-row compat was one-way. get_cached_context_length
and _invalidate_cached_context_length now consult the same key-shape
set {canonical, literal, canonical+slash} in both directions, so an
old slashed row is found (and cleared) when the runtime passes the
normalized URL. Tests pin both migration directions.
- MINOR: _localhost_to_ipv4 did whole-string replacement, which could
corrupt a proxy URL embedding http://localhost in its query. Now a
scheme-anchored host-only regex; localhost.example.com and embedded
substrings pass through. Tests added.
- MINOR: _invalidate_cached_context_length now also drops the
in-memory TTL probe rows for the pair, so a resolution inside the
TTL window can't re-persist the value just declared stale.
- Test gaps closed: detect-type cache hit + TTL-expiry re-detection,
ollama-show TTL expiry re-probe, reverse legacy-row lookups.
- Attribution gate: added zhchl@hermes-agent.local -> 8294 (PR #50572
author) to AUTHOR_MAP; the strict CI grep needs bare non-plus emails
literal in release.py.
Gates: ruff clean; targeted suites 202 passed / 0 failed; full
tests/agent 5426 passed with 17 failures identical on clean
upstream/main (pre-existing env-dependent anthropic/bedrock/credpool
tests); mypy delta vs base: 0 new errors; live smoke 6/6 PASS.
#37595 fixed the Windows dual-stack IPv6 timeout only inside
detect_local_server_type. The same 2s-per-probe penalty existed at every
other helper that builds a probe URL from base_url. Extract the rewrite
into _localhost_to_ipv4() and apply it at:
- query_ollama_num_ctx
- query_ollama_supports_vision
- _query_ollama_api_show (server_url derivation)
- _query_local_context_length (server root + LM Studio native URL)
Tests cover the helper's URL forms, non-localhost passthrough, and that
the ollama probes actually POST to 127.0.0.1.
Follow-up hunks completing the probe-cache cluster:
1. _query_ollama_api_show now goes through the existing
_LOCAL_CTX_PROBE_CACHE (30s TTL, positive-only, namespaced key) —
it was the one remaining per-resolution POST not covered by the
#56431-era wrapper. Failures are never memoized so a server that
comes up mid-startup is re-probed. Idea credit: #42081 (@Morad37),
reworked to comply with the positive-only rule.
2. Persistent context-cache keys are normalized through
_context_cache_key (trailing-slash strip) so http://host/v1 and
http://host/v1/ share one entry; reads and invalidation honor
legacy un-normalized rows. Idea credit: #37905 (@stevenau21).
Tests: TTL hit collapses to one POST, failure-not-memoized
(mutation-verified: unconditional caching makes it fail), namespace
no-collision vs the sibling probe, slash-variant dedup, legacy-row
read, dual-shape invalidation.
_cli's show_banner() calls _resolve_active_context_length() at every
startup. For non-OpenRouter providers (e.g. minimax-cn, kimi-coding,
custom endpoints) the resolver falls through to step 6 (OpenRouter
live /models fetch), which blocks ~2-3s per CLI launch and adds up
to 7+ minutes when openrouter.ai is unreachable through a proxy that
403s CONNECT (#46620).
Two complementary changes:
1. model_tools.py: read model.context_length from config.yaml and pass
it as config_context_length to get_model_context_length. The
step-0 config override short-circuits the entire resolution chain
including the OpenRouter fetch. No network call is made when the
user has set the value explicitly.
2. agent/model_metadata.py: replace flat timeout=10 with (5, 10)
tuple at all five sites (fetch_model_metadata + four endpoint
probes). urllib3 can otherwise block for 10s per retry stage
through proxies that 403 CONNECT. The tuple bounds connect at 5s
while still allowing slow reads.
Complements the in-flight PR #46685 (which adds HERMES_DISABLE_MODEL_METADATA
env var + same timeout tuple change for fetch_model_metadata). This PR
extends the timeout fix to the other four endpoint probes and adds the
config-override path that addresses the slow-but-reachable scenario
where env-var disable is too heavy-handed.
Refs #46620, PR #46685.
(cherry picked from commit e7faa34199f553d2b1d30c4009856a983cc87707)
Remaining hunk of the PR-branch fixup commit: the LM Studio first-probe
assertion now expects the IPv4-resolved URL (the code half — applying
the rewrite to `normalized` before deriving lmstudio_url — was folded
into the previous cherry-pick's conflict resolution).
(cherry picked from commit 7d324b0e47444887fc615e1c428aa30c3dfcd2e8)
On Windows, `localhost` resolves to both ::1 (IPv6) and 127.0.0.1 (IPv4).
httpx tries IPv6 first, hanging 2 sec per probe when the server binds IPv4
only. detect_local_server_type() is called 3+ times during init, each with
a new httpx.Client, compounding to ~14s of dead time.
Replace localhost with 127.0.0.1 inside the function before connecting.
The function is only called for local endpoints (callers guard with
is_local_endpoint()), so IPv6 loopback adds no diagnostic value.
Measured: 19.9s → 4.0s on Windows with a local proxy on 127.0.0.1:8317.
(cherry picked from commit a075d3194bba2e0fa1aa13852862190839bfecef)
Every 5 minutes fetch_endpoint_model_metadata() re-runs the full server-type
waterfall (LM Studio -> Ollama -> llama.cpp -> vLLM), spraying 404s at
endpoints the server never exposes (e.g. /api/v1/models and /api/tags on a
vllm backend).
Add _endpoint_probe_path_cache (base_url -> server type) so the first
successful probe's result is reused for the lifetime of the process.
Subsequent refreshes skip straight to the known-good path.
Fixes#29971.
(cherry picked from commit f3d7a8960a93e33683298e51c91c1b22a876d4da)
Follow-up hardening on the salvaged NS-591 mobile-chat reconnect fix, from
review findings:
- Guard the page-resume reconnect against the async socket-open window:
a connectInFlightRef is set synchronously before the ticket-URL await so
a visibilitychange/focus fired during that gap (wsRef still null) can't
spawn a redundant second socket. Threaded through
shouldReconnectPtyOnPageResume as connectInFlight.
- Recover a socket wedged in WS_CONNECTING (half-open mobile socket after a
radio handoff — the NS-591 scenario) via a PTY_CONNECTING_TIMEOUT_MS
force-close so onclose routes into scheduleReconnect. Cleared on
open/close/effect-cleanup.
- Avoid collapsing legitimate single-letter reduplication ("a a") in the
mobile duplicate-final-word heuristic (>=2-char guard).
- Extract the 350ms replacement window and 1000ms resume throttle to named
exported consts; drop the dead WS_CONNECTING term from the resume
predicate's final expression.
Adds tests for the in-flight guard and the single-letter reduplication case.
Two review fixes on the mobile input normalization path:
- updatePtyInputLine appended the printable payload of escape sequences
(the '[D' of a left-arrow) to the tracked line, and after any cursor
movement the flat tracker no longer matched the visual line — the
DELETE-repeat replacement could then be computed against a stale
snapshot. Any chunk containing ESC now resets the tracker, disarming
replacement normalization until a cleanly-tracked line starts.
- Move the SGR mouse-report filter ahead of the blocked-input check so
scrolling a disconnected terminal doesn't print the reconnect notice.
Follow-up to HexLab98's fix. The sync-before-regenerate invariant was
enforced by convention across 6 callsites (~3 idempotent unit-file reads
per command). Consolidate it into the one function every compare/regenerate
path funnels through — systemd_unit_is_current — and drop the now-redundant
callsite pre-syncs in refresh_systemd_unit_if_needed / systemd_start /
systemd_restart / systemd_status.
Kept the systemd_install pre-sync: the --force path bypasses the
is_current gate and calls generate_systemd_unit() directly, so it needs
its own sync to avoid baking /root/.hermes under sudo.
Reworked the two callsite-ordering tests into a chokepoint-invariant guard
(test_is_current_syncs_before_reading_unit) + a delegation test proving
start/restart no longer pre-sync. Both fail if the chokepoint sync is
removed; the pre-existing behavior test still passes.
Under sudo, start/restart refreshed the unit from /root/.hermes before
adopting the unit's pinned home, so TimeoutStopSec and env drifted and
status stayed stuck on "service definition is outdated".
Follow-up to the salvaged str(tools) fix. The id()-keyed
_TOOLS_TOKENS_CACHE had no eviction, so a long-lived gateway/desktop
backend could accumulate an unbounded number of stale entries as it
builds transient tool lists. Cap it at 256 with oldest-first eviction
(insertion-ordered dict) and add a regression test asserting the cache
never exceeds the cap.
Estimate tool-schema size without repeatedly stringifying full tool lists, and cache the result per tool snapshot to reduce GIL-heavy work during preflight and compaction.
PR #61281 removed the client-side X-Hermes-Session-Token requirement from the
dashboard OAuth mutation calls so cookie-authenticated hosted/mobile sessions
can start provider logins. That change is safe only because the server still
gates those endpoints (gated_auth_middleware cookie check + _require_token).
The PR's api.test.ts suite mocks fetch and only asserts client behavior, so a
re-break of the gated-mode cookie gate would pass CI unnoticed.
Add gated-mode TestClient tests asserting POST /api/env/reveal and the OAuth
mutation endpoints (disconnect/start/submit/cancel) return 401 with no session
cookie. Mutation-verified: neutering both the middleware gate and _require_token
flips all five to 200.
The new oauth.copyCode/copyFailed keys existed only in en.ts, with
optional types and English literal fallbacks in OAuthLoginModal — so
non-English users got English strings on the device-code copy button.
Backfill translations in all 16 non-English locales, refresh the
updated oauth.description/notConnected copy (dashboard Login flow
mention) to match en.ts, make the two keys required in the
Translations interface, and drop the English fallbacks from the modal.
Verified with web tsc --noEmit (required keys enforce locale
completeness), vitest, and a web build.
Electron 40 ships Node 24.15, where tsx's ESM load hook returns null and
crashes with ERR_INVALID_RETURN_PROPERTY_VALUE. Bundle main+preload via
esbuild for `npm run dev` and always load the JS preload from dist/.
grok-4.5 is GA and is now the single curated Grok entry on the
aggregator lists. grok-4.3 is NOT retired upstream — it remains fully
usable by typing the model name (validated against the live catalogs);
this only removes it from the short curated picker snapshots. The
xAI-direct list is models.dev-cache-driven and unaffected.
The model often emits a follow-up batch of tool calls as its own
assistant message with no prose or reasoning. On screen those rows look
like one continuous run, but assistant-ui only groups tool calls within a
single message, so the auto-scrolling tool window never triggered on them
(e.g. two batches of two searches read as 2 + 2, never reaching the
threshold).
Coalesce each settled tool-only assistant message into the preceding
assistant message in the render pipeline so its calls join that message's
tool group. Render-only (never touches the $messages store) and
settle-only (pending messages are skipped) so a live turn is never
merged/un-merged mid-stream; merged results are cached by source identity
so a stable turn yields stable objects with no re-render churn.
- Return the boundary snapshot from
_launch_session_boundary_memory_flush as a local value instead of
staging it on self._session_boundary_snapshot. The instance-attr
handoff could leak (no memory manager configured) or mis-fire a
stale snapshot on a later /new if an exception hit between staging
and consumption. A local variable eliminates the class; the helper
also returns None when no memory manager is configured so
new_session takes the inline-switch path.
- Drop the now-dead session_id kwarg from commit_memory_session:
after the redesign no production caller passes it (gateway, TUI,
compression all use the default), and speculative params are
rejected per AGENTS.md. The explicit-old-session need is served by
cli.py's direct engine call + commit_session_boundary_async.
- Drop the dead providers snapshot in commit_session_boundary_async
(only the emptiness check used it).
- Tests updated accordingly (dead-kwarg test removed, snapshot
assertion now covered by return-value contract).
Phase-2 gates: 2a tests/cli 1048 passed + 6 memory files 137 passed;
2b programmatic live smoke 0.38ms non-blocking caller, end→switch→sync
ordering verified; 2c structured 4-angle review — no Criticals, these
warnings fixed.
Deep review of the cherry-picked #16454 found the ad-hoc flush thread
raced new_session()'s inline on_session_switch(reset=True): memory
providers key off internal _session_id state (MemoryManager.on_session_end
takes no session id), so a late off-thread extraction ran against
post-rotation bindings — misattributing the old transcript to the new
session id, double-ingesting the old turn buffer (supermemory), or
double-committing (openviking already async-finalizes in
on_session_switch).
Redesign: new MemoryManager.commit_session_boundary_async queues
on_session_end + on_session_switch as ONE task on the manager's existing
single-worker background executor (the same worker sync_all already
uses). This preserves the strict end→switch ordering providers depend on,
serializes against per-turn syncs FIFO, keeps /new non-blocking, and
degrades to inline (pre-#16454 behavior) when the executor is
unavailable. No ad-hoc threads; no per-provider changes needed.
The context-engine on_session_end half stays synchronous in
_launch_session_boundary_memory_flush (cheap, must land before
reset_session_state rebinds the engine).
Exit durability: _run_cleanup calls the manager's existing
flush_pending(timeout=10) barrier before shutdown, so '/new then quit'
doesn't drop the queued extraction (shutdown_all's own drain is ~5s and
cancels queued tasks). Bounded well inside the 30s exit watchdog.
Tests: ordering invariant with slow (LLM-like) extraction, FIFO
serialization vs sync_all, switch-fires-even-if-end-raises, no-provider
no-op, CLI snapshot handoff + inline-switch fallback, sync engine
boundary, cleanup flush_pending.
Fixes#3356
Build the skills snapshot manifest in one directory walk, avoid importing gateway session context during CLI prompt startup, and reuse direct platform-list matching for snapshot entries.
(cherry picked from commit 1a64c2ed04f739ce03de94ca33d20b34c8d0e3cb)
Follow-ups on the #60987 salvage (review pass):
- _refresh_fallback_model: keep last known-good chain on transient
config.yaml read/parse failure (user mid-edit, torn write) — only a
successful read that lacks the key clears the chain. Previously a
refresh error wiped a cached agent's working fallback for the turn.
- Move the cached-agent refresh+apply OUTSIDE the agent-cache lock:
config.yaml read is disk I/O and the idle-sweep watcher contends on
that lock (same reasoning as #52197). Per-session turn serialization
keeps the post-lock apply safe.
- _apply_fallback_chain_to_agent: clear _unavailable_fallback_keys when
chain content actually changes, so an entry re-configured mid-uptime
(e.g. credentials added) is retried instead of staying suppressed for
the cached agent's lifetime; no-op refreshes keep the memo.
- Tests: cwd-independent source pin (Path(__file__) anchor), pin the
reuse-path apply call, + regression tests for last-known-good, memo
clear-on-change, memo keep-on-unchanged (mutation-verified).
Pin reload + cached-agent apply helpers for #60955 so a mid-uptime
fallback chain change reaches messaging sessions without a restart.
(cherry picked from commit fafb34103509f890cce158bfdbfd4faee8982253)
Gateway froze the fallback chain at process start while cron reloads it
per job, so a chain configured after hermes gateway was running never
reached messaging sessions. Refresh from disk on agent create and when
reusing a cached agent.
Fixes#60955.
(cherry picked from commit b64e7155b29cc97b9f427fe2b91cba4f22c64900)
When an API error carries an httpx.Response whose body was consumed via
iter_bytes() during streaming error handling (e.g. GeminiAPIError from
agent/gemini_native_adapter.py), accessing .text raises
httpx.ResponseNotRead. The secondary exception replaced the real,
already-computed provider error (429 free-tier quota guidance) with the
generic 'Attempted to access streaming response content' message on
every turn.
Guard the .text access so it degrades to an empty snippet and falls
through to the str(error) fallback, which carries the full original
message. Mirrors the existing guards in
agent/error_classifier.py::_extract_error_body() and
agent/gemini_native_adapter.py::gemini_http_error().
Fixes#59769
Salvaged from PR #59868 (guard + regression test); the unrelated
desktop Ctrl-C fix bundled in that PR was intentionally dropped and is
triaged separately.
Rebase reconciliation with #60884: _count_status_active_sessions (from
#58238) now passes compact_rows=True (this branch's #47437 projection),
so the fake asserts both.
tui_gateway session.list/most_recent now pass compact_rows=True
(#47437 salvage); the keyword-only fake signatures in
test_tui_gateway_server.py rejected the new kwarg and CI slice 6/8
failed with TypeError. Other list_sessions_rich fakes use **kwargs and
are unaffected.
Review finding: get_messages(offset=N) with no limit dropped the OFFSET
entirely. SQLite requires a LIMIT clause for OFFSET, so emit LIMIT -1
(unbounded) when only offset is given. Regression test added.
- derive the compact_rows projection from SCHEMA_SQL (parse once, cache)
instead of a hardcoded column list: the original #47437 list was cut
against a June schema and silently dropped session_key/chat_id/chat_type/
thread_id/display_name/origin_json/expiry_finalized/git_branch/
git_repo_root/compression_failure_* — including desktop sidebar fields.
Schema-derived means declaratively reconciled new columns are included
automatically; only system_prompt is excluded.
- guard test pinning the schema<->projection contract (mutation-verified:
dropping a column from the projection fails it)
- wire compact_rows=(not full) into /api/sessions and /api/profiles/sessions
so the SQL projection pairs with the API-level field strip (?full=1 still
returns complete rows end-to-end)
- pass compact_rows at the remaining hot list callers: /api/status active
count, _session_latest_descendant fallback, /api/sessions/stats by-source
- thread compact_rows through the compression-tip projection
(_get_session_rich_row) so projected tips can't reintroduce the blob
- add pagination tests for get_messages (#60347 shipped none): paging order,
offset-past-end, active-flag interaction; add tip-projection compact test
- AUTHOR_MAP entries for mahdiwafy + CodeForgeNet (plain emails)
list_sessions_rich and _get_session_rich_row previously used SELECT s.*,
pulling the system_prompt TEXT blob on every row even for dashboard and
picker callers that never display it. On large databases this blob routinely
runs to tens of kilobytes per session, causing unnecessary B-tree I/O.
Add compact_rows=False param to both functions. When True, an explicit
column list omitting system_prompt is substituted for s.* in both the
simple and the recursive-CTE (order_by_last_active) query paths.
Default is False so all existing callers are unaffected.
Update dashboard and session-picker callers in web_server.py and
tui_gateway/server.py to pass compact_rows=True.
Add seven regression tests covering: omission of system_prompt, presence
of all metadata fields, both query paths, _get_session_rich_row, and
backward-compat default.
(cherry picked from commit c470cbd3042d95a62708cb5572118efd964f7699)
The session messages endpoint returned ALL messages in a single
response with no limit/offset. Sessions with 500+ messages produced
1.2-1.6 MB JSON payloads, causing GIL starvation and WebSocket
timeouts on the Desktop client (#60155).
Add optional limit/offset query params to both the API endpoint and
SessionDB.get_messages(). Limit clamped to 500 max per page. Response
now includes a pagination object with limit/offset/returned count.
Backward compatible: callers that omit limit get the old behavior
(all messages).
Closes#60155
(cherry picked from commit d58396b154efc2e66223528bec7dae23a5b40334)
get_status now probes via get_running_pid_cached() (#53511 salvage);
these tests were added on main after that PR was cut and still patched
web_server.get_running_pid, so their fakes were bypassed and CI slice
5/8 failed. Patch the name the handler actually calls.
Review finding: SessionDB(read_only=True) requires the DB file to exist
(its documented contract says callers guard on db_path.exists()); on a
fresh install every /api/status poll paid an OperationalError until the
first session was written. Short-circuit to 0 when state.db is absent.
Tests: fresh-install guard + existing read_only test adjusted.
The #39140 CTE used UNION ALL, which recurses forever if a corrupted
parent chain loops (a -> b -> a) — reproduced: query never returns. The
old Python walk was cycle-safe via a seen-set. UNION dedups the working
set and terminates. Regression test added and mutation-verified (UNION
ALL hangs the test, UNION passes).
Flip the handler from async def to sync def so FastAPI executes it in
its threadpool: the SessionDB open + list_sessions_rich query no longer
block the single uvicorn event loop.
Residual hunk from PR #53966 — that PR's get_profiles_sessions flip
already landed via #54523/1bb7b59c5, and its get_status offload is
superseded by #58238's read_only + timeout variant in this branch.
(cherry picked from commit 414c12a40db07b941b0c589674bc6aad3f090ff7)
_session_latest_descendant fetched EVERY sessions row and built the
parent->children tree in Python on each call. Replace with a recursive
CTE that loads only the target session's descendant branch.
Hand-applied from PR #39140 (the schema-init cache and Rust PTY bridge
parts of that PR are intentionally NOT salvaged here); main's function
signature gained a db parameter since the PR was cut.
(cherry picked from commit 8ed5e54f65c706d197d0ea554232d5071d0279df)
* feat(xai): add grok-4.5 (early access) to catalog, context lengths, and reasoning-effort allowlist
- hermes_cli/models.py: grok-4.5 in _XAI_CURATED_EXTRAS (callable but absent
from models.dev) and _XAI_STATIC_FALLBACK, so the /model picker and
validation surface it on both xai and xai-oauth.
- agent/model_metadata.py: context lengths grok-4.5 -> 500K (per model card)
and grok-build-latest -> 500K (alias); grok-4.5 added to
_GROK_EFFORT_CAPABLE_PREFIXES.
Verified live against api.x.ai /v1/responses (2026-07-08): effort
low/medium/high accepted (server default: high), "none" rejected,
function calling works, full agent turn with terminal tool succeeded.
* feat(xai): grok-4.5 GA — add aggregator catalog entries, refresh comments
grok-4.5 is now GA: models.dev lists it (500K context, effort
low/medium/high) and both OpenRouter and Nous serve x-ai/grok-4.5.
Add it to the OpenRouter fallback snapshot and the Nous static list,
and update the early-access comments.
* chore: regenerate model-catalog.json for x-ai/grok-4.5
Follow-up to #60944 (webhook payload filters and route scripts):
- reference/cli-commands.md (en+zh): document the new --script option on
'hermes webhook subscribe'
- zh-Hans user-guide webhooks.md: mirror the Payload Filters and Script
Filters/Transforms sections plus the filters/script route properties
(the salvage shipped English-only docs)
- hermes-agent skill webhooks reference: teach the agent the filters/
script surface so agent-driven subscriptions can use them
Sessions on sub-512K-context models were spending most of their wall-clock
re-summarizing: the 50% trigger left too little post-compaction headroom
(the incompressible floor — system prompt, tool schemas, protected tail,
rolling summary — ate most of the reclaimed space), so compaction re-fired
every 1-2 turns. Three compounding defects fixed:
- Threshold floor: models with context windows below 512K now trigger at
>=75% of the window (raise-only — a higher configured value or per-model
autoraise like Codex gpt-5.5's 85% always wins). Re-derived on
update_model() in both directions.
- No max_tokens on the summary call: the summary budget is prompt guidance
only ("Target ~N tokens"). The wire cap truncated summaries mid-section
on the Anthropic Messages / NVIDIA NIM paths (thinking models burn the
cap on reasoning first), yielding truncated or thinking-only summaries
and compaction loops. Summary token ceiling lowered 12K -> 10K to keep
the guidance within the intended 1K-10K envelope.
- Reasoning traces excluded end-to-end: inline <think>/<reasoning> blocks
are now stripped from assistant content before serialization to the
summarizer, and from the summarizer's own output before the summary is
stored (previously a thinking summarizer model's trace was persisted in
_previous_summary and re-fed into every iterative update, compounding
bloat). Native reasoning fields were already excluded.
Verified E2E with real imports against a temp HERMES_HOME: threshold table
across 64K-1M windows, override interactions (user 0.85 wins, spark 0.70
raised, gpt-5.5 0.85 kept), full compress() round-trip with a thinking
summarizer, and wire-kwargs capture proving no max_tokens is sent.
Two client-side halves of the #55578 session split:
1. Submit with a null activeSessionId but a SELECTED stored session now
resumes that stored session instead of falling straight through to
createBackendSessionForSend - which silently forked the user's
conversation into a brand-new session that then got orphan-reaped.
New-chat drafts (no stored selection) still create sessions as before.
2. prompt.submit recovery now also fires on gateway request timeouts,
not only 'session not found'. A starved backend loop (the async-
delegation poller spin) rejects the submit with 'request timed out'
even though the stored session is fine; previously that surfaced an
error, left the binding cleared, and set up the split on the next
send.
Fail-then-pass: 2 new tests fail with production code reverted.
- run_route_script shells out with subprocess.run (up to 30s timeout); wrap
the call in asyncio.to_thread so a slow script can't stall every other
webhook and gateway task on the loop.
- scripts/release.py: map grace@weeb.onl -> evelynburger for the salvaged
contributor commit.
Completes the session-binding class on the gateway surface (#55578),
matching the TUI rules:
1. Fail-closed pinning: switch_session() re-opens ended sessions, so
pinning a completion to a spawning session that has since ENDED
(user /new, closed rotation) would resurrect a conversation the user
explicitly ended and inject into it. The injection path now checks
the pinned row's ended_at first and drops the injection with a
WARNING when the spawning session is dead or unknown - the result
stays in the delegation records.
2. /new ends the old conversation's delegations: _handle_reset_command
calls interrupt_for_session() with the expiring durable session id
(matching the parent_session_id pin stamped at dispatch) plus the
routing key as fallback, so a reset can't leave dangling subagents
whose completions have no live owner.
interrupt_for_session() gains the parent_session_id selector because a
gateway chat's session_key (the platform conversation key) survives a
reset while the session id rotates - key-based matching alone could
never sever a gateway conversation's delegations.
Background delegate_task completions only carried session_key. When multiple
active sessions shared a routing peer, get_or_create_session could recover the
latest ended_at IS NULL row and inject the subagent result into the wrong
session.
Capture parent_agent.session_id at dispatch time, include it on async-delegation
completion events, and pin gateway routing via switch_session when the
synthetic completion message is handled.
Fixes#57498
In single-query (-q) mode, the assistant's final answer was printed and
then immediately erased by _print_exit_summary() — which unconditionally
called _clear_terminal_on_exit() (ESC[3J ESC[2J ESC[H]). The answer was
present in the session store but invisible in the terminal.
The clear is only needed for interactive TUI teardown (#38928) where
prompt_toolkit chrome must be cleaned up. Add a clear_screen parameter
to _print_exit_summary() (default True, preserving interactive behavior)
and pass False from the single-query call site so the answer stays
visible above the exit summary.
Regression tests cover:
- clear_screen=True (default) calls _clear_terminal_on_exit()
- clear_screen=False skips the clear
- Single-query -q path passes False end-to-end
- Interactive path still clears (preserving #38928)
Extends the salvaged session_key filter with the same fail-closed,
compression-chain-aware ownership gate the poller uses (#55578):
- drain_notifications() accepts an owns_event callback; when provided,
an async-delegation event is consumed ONLY on positive proof of
ownership, and a broken callback re-queues (never leaks). Bare key
equality remains for single-session callers (CLI); no filter remains
legacy behavior.
- The TUI post-turn drain passes _session_owns_notification_event, so
it can't adopt another session's (or an orphan's) delegation payload,
while a post-compression session still claims its own pre-compression
dispatches - the gap bare key equality left open.
The completion event already carries the dispatching session's session_key
(captured at dispatch time in delegate_tool.py:2798), but the delivery
router ignored it — results landed in whatever session was active at
completion time instead of the session that dispatched the subagent.
Changes:
- drain_notifications() in process_registry.py: optional session_key
filter. Non-matching async_delegation events are re-queued instead of
consumed, so they remain available for the correct session's drain.
- cli.py process_loop: passes active session_key to drain_notifications()
- tui_gateway/server.py post-turn drain: passes session_key from the
TUI session dict
- gateway/run.py _build_process_event_source: logs warning when routing
metadata is unresolvable (previously silent drop)
- Regression tests verifying session-scoped drain filtering
Fixes#58684
- OPENROUTER_MODELS: remove openrouter/owl-alpha (free) and
tencent/hy3-preview{,:free}; add tencent/hy3 and tencent/hy3:free
- _PROVIDER_MODELS[nous]: tencent/hy3-preview -> tencent/hy3
- run_agent.py reasoning-prefix list: tencent/hy3-preview -> tencent/hy3
(prefix match still covers -preview if pinned)
- model_metadata: register hy3 context length (262144) alongside hy3-preview
- regenerate website/static/api/model-catalog.json
- update tokenhub curated-list tests to the new IDs
The tencent-tokenhub direct provider still serves hy3-preview and is
intentionally unchanged.
Two invariants layered on the origin-routing commit (#55578):
1. Fail closed on orphaned async-delegation payloads. The poller's
belongs-elsewhere check handles events owned by another LIVE session,
but an event whose owner is gone previously fell through and was
adopted by whichever poller saw it - injecting one chat's delegation
output into another chat. Delegation completions are now injected
only into a session that PROVABLY owns them (origin UI id, or
session-key/lineage match via the compression chain); unowned
payloads are dropped from injection with a WARNING (the subagent's
output is already persisted in the delegation records, so nothing is
lost). The shutdown drain applies the same rule. Non-delegation
events keep the historical adopt-orphans behavior.
2. A session's in-flight async delegations end with the session.
_finalize_session now calls interrupt_for_session(): delegations
commissioned by the closing UI session are interrupted always;
key-matched delegations only when the TUI owns the session lifecycle,
so closing a viewer tab on a live gateway session never kills the
gateway's own background work.
Carry the live TUI session id with async delegation completion events and prefer the commissioning UI session when desktop pollers share the completion queue. Resolve compressed session keys to their continuation before treating events as orphaned, and capture the live parent agent session id for TUI/ACP dispatch.
The desktop app's chat panel reuses tui_gateway as its backend, so every chat session was stamped platform="tui". That made the agent read terminal-specific platform guidance while running in the graphical desktop chat surface.
Resolve the misclassification at its source: tui_gateway now picks platform="desktop" when HERMES_DESKTOP=1 and HERMES_DESKTOP_TERMINAL is unset, and keeps platform="tui" for the embedded terminal pane and standalone TUI. Add a PLATFORM_HINTS["desktop"] entry describing the actual chat surface (full GFM markdown, MEDIA: intercept, inline images). Move the embedded-pane clarifier to the platform-hint resolution site so it appends only to the tui hint under HERMES_DESKTOP_TERMINAL=1. Delete the now-dead desktop-hint block from build_environment_hints() that competed with the platform hint.
Standalone TUI sessions produce byte-identical prompts as before; the new desktop hint and clarifier are assembled once per session in the stable tier, so prompt caching is preserved.
The busy-session branch of _notification_poller_loop re-queued the
completion event and immediately re-polled it with no sleep, spinning
at full speed (100% CPU, ~1100 futex/s of GIL churn) for as long as
the session stayed running. This starved the dashboard asyncio loop:
/api/status went from 0.14s to 3-6s with 10s timeouts.
Sleep 0.25s outside history_lock before re-polling, mirroring the
0.1s back-off already used for foreign-session events.
Three fixes for the silent post-restart ticker stall:
1. _jobs_lock() bounds its cross-process flock: LOCK_NB polled against a
30s deadline instead of an unbounded LOCK_EX taken while holding the
process-wide RLock. On timeout it logs at ERROR and degrades to
in-process-only locking (the existing fallback path), so a sibling
process wedged while holding .jobs.lock can no longer freeze every
cron function - including the ticker's get_due_jobs() and thus the
heartbeat - forever with zero logging.
2. fire_claim/run_claim freshness checks are bounded on both sides
(0 <= age < ttl): a claim stamped in the future (clock/TZ skew across
a restart) was previously fresh forever, making the job permanently
unfireable and every manual run report 'already being fired'.
3. _execute_job_now distinguishes paused/disabled/missing jobs from a
genuinely held claim instead of mislabeling them all as 'already
being fired'.
Review findings (hermes-pr-review Phase 2, 3-angle):
- _save_auth_store() does real filesystem I/O (mkdir, O_EXCL create, fsync,
atomic replace) and can raise on disk-full/permissions/lock-timeout. The
persist ran bare in the success path, so a persist failure aborted
_resolve_zai_base_url() after detection had already succeeded. Wrap the
persist in try/except: log a warning and still return the detected URL
(worst case: next start re-probes).
- Readability: stage the payload in a local detected_endpoint instead of
writing through the stale pre-lock 'state' dict, which is no longer what
gets persisted.
_save_provider_state() sets auth_store['active_provider'] as a side effect.
The Z.AI endpoint probe runs from credential-pool env seeding for any user
with a Z.AI key in env — persisting the probe cache must not silently make
zai the active provider. Use _store_provider_state(set_active=False).
Follow-up to PR #41201 salvage.
For air-gapped / self-hosted-IdP deploys with NO Nous Portal, let the gateway
obtain its caller-identity bearer from a generic OAuth2 client_credentials grant
against the operator's own IdP (e.g. Microsoft Entra ID) instead of only
resolve_nous_access_token(). The connector's OIDC tenant resolver reads a claim
(default tid) off that token as the tenant.
- gateway/relay: new canonical _resolve_relay_identity_token() — client_credentials
when gateway.idp.token_url (or GATEWAY_RELAY_IDP_* env) is set, else Nous Portal
(unchanged default). Wired into self_provision_relay().
- hermes_cli/gateway_enroll: _resolve_identity_token() delegates to the canonical
resolver so the enroll CLI and the runtime self-provision path share ONE impl.
Config via gateway.idp.{token_url,client_id,client_secret,scope} in config.yaml
(env override GATEWAY_RELAY_IDP_*). No behaviour change when unset.
Tests: tests/gateway/relay/test_identity_token_resolver.py (6 — mode selection,
request shape, config/env precedence, fail-closed). Relay suite 162 pass.
Validated via the cross-repo gateway<->connector live E2E (provision, managed
self-provision, inbound round-trip, /link) against a connector running the OIDC
tenant resolver with zero NAS config.
The salvaged guard used a hand-maintained frozenset of 14 platform names —
several of which (line, wechat, facebook, imessage, googlechat) aren't
actual Hermes Platform values, while real ones (whatsapp_cloud, feishu,
wecom, dingtalk, qqbot, yuanbao, plugin platforms like irc) were missing.
Resolve the source through gateway.config.Platform instead (built-ins +
registered plugin platforms via _missing_), with an explicit exclusion set
for self-owned/local sources. Adds tests for the guard and both reap paths.
Guard _finalize_session's db.end_session() call against gateway-owned
sessions (telegram, bluebubbles, discord, etc.). The TUI is a viewer
for these sessions, not the lifecycle owner. Unconditionally ending
them in state.db creates a Groundhog Day routing loop: the gateway's
#54878 self-heal detects the stale entry, recovers to the parent
session, context compression splits back to the reaped child, and the
cycle repeats on every inbound message — causing complete conversational
context amnesia.
Fixes#60609
Keep #60631's get_running_job_ids() snapshot + _active_cron_job_count()
(import-guarded for minimal test doubles) as the single read path, and
retarget #60612's drain tests at it. Drops the redundant
cron_jobs_in_flight() helper so there is one surface, not two.
Follow-up to the previous commit on #60432. The status-write guard
(_consume_interrupted_flag, checked right before mark_job_run) closes
the false-success bookkeeping gap, but run_one_job delivers its result
BEFORE that check: delivery happens right after run_job() returns,
mark_job_run happens at the very end. A job whose tool subprocess was
killed mid-flight can still produce a plausible-looking final_response
from the truncated output, and that response would reach the user via
_deliver_result before the interrupted flag was ever consulted --
correct status in jobs.json, wrong message already sent.
Adds _is_interrupted(), a non-destructive peek at the same
_interrupted_job_ids set (_consume_interrupted_flag stays as the
consuming, authoritative check right before the status write -- this
needed a peek instead since the flag has to still be visible there).
Checked right after save_job_output, before the deliver_content
decision: if the run looked successful but was flagged interrupted,
force success=False with an explicit interruption message. This
routes delivery through the existing _summarize_cron_failure_for_delivery
path (the same one a real failure already uses) instead of the raw
final_response, so the user gets an honest "this run was interrupted"
instead of a truncated/misleading result.
Testing: 4 new tests in tests/cron/test_shutdown_interrupt.py --
_is_interrupted peek semantics (false/true/does-not-clear, as opposed
to the consuming _consume_interrupted_flag), and the delivery-gate
test itself, which mocks run_job to return a normal-looking success
with a "plausible final response" while the job is pre-marked
interrupted, and asserts _deliver_result receives the failure summary
("This run was interrupted.") instead, with the summarizer's error
argument confirmed to mention the interruption.
Fail-then-pass: reverted cron/scheduler.py only, the 4 new tests fail
(3 on the missing _is_interrupted attribute, 1 -- the delivery-gate
test -- on _summarize_cron_failure_for_delivery never being called,
i.e. the raw response would have gone out); restored, all 16 tests in
the file pass.
Regression: tests/cron/ (683 tests) + test_cron_active_work_drain.py +
test_gateway_shutdown.py + test_shutdown_cache_cleanup.py -- 11
pre-existing failures (Unix file-permission-bit and path-tilde
assertions that don't apply on this Windows dev box), matching the
same set already established as pre-existing in the prior commit's
regression check. Zero new failures.
Continues #60432
Cron jobs run through cron/scheduler.py's own ThreadPoolExecutor via a
standalone AIAgent (run_job/run_one_job), entirely outside
GatewayRunner._running_agents -- the dict _drain_active_agents() and
every other active-work check on that class reads. A gateway shutdown
(/update, /restart, and SIGUSR1 all funnel through the same stop())
could log active_at_start=0 and immediately kill tool subprocesses
while a cron job's terminal command was still running, with no wait
and no indication anything was interrupted.
Real-world impact (from the issue): a scheduled daily briefing cron
job was in flight during /update, its tool subprocess got killed
by the unconditional shutdown cleanup, and the job was never marked
failed -- it simply never completed or delivered, with no error
surfaced anywhere. A repro with a 30-minute `sleep` cron job in flight
during /update reproduced the same pattern: subprocess killed at
+0.22s of drain (active_at_start=0), the job's agent thread continued
in-process and produced a plausible-looking final response from the
truncated tool output, and the scheduler marked the run successful.
Root cause is layered, not a single line:
1. GatewayRunner._drain_active_agents() only waits on _running_agents.
Cron work was invisible to it, so drain returned instantly whenever
the only active work was a cron job.
2. Even with visibility, the shutdown's final tool-subprocess kill
(process_registry.kill_all()) is a global, unconditional sweep with
no per-job targeting -- a long-running cron job that outlives the
drain timeout still gets its subprocess killed.
3. cron/scheduler.py had no way to detect that a job's tool subprocess
was killed out from under it mid-run; the agent thread kept going
and its eventual (often degraded but plausible-looking) response
got reported as a normal successful completion.
Fix, three parts:
- cron/scheduler.py: expose get_running_job_ids() (thread-safe
snapshot of the existing _running_job_ids set, already used to
prevent double-dispatch) so the gateway can read cron's in-flight
state without reaching into private module internals.
- gateway/run.py: GatewayRunner._active_cron_job_count() reads that
snapshot. _drain_active_agents() now waits on
(_running_agents OR active cron jobs), so a cron-only workload gets
the same bounded wait chat sessions already get instead of an
instant active_at_start=0. Shutdown drain logging gains
cron_active_at_start/cron_active_now fields alongside the existing
ones (unchanged, for compat).
- cron/scheduler.py: mark_running_jobs_interrupted(reason), called by
gateway/run.py's _kill_tool_subprocesses() right after
process_registry.kill_all(), marks every job still in
_running_job_ids at that instant as failed/interrupted via the
existing mark_job_run() -- and records the job IDs in
_interrupted_job_ids BEFORE writing, so run_one_job()'s own
eventual completion for the same run (racing in its own thread)
checks that flag and skips its normal write instead of clobbering
the interrupted status with a false "ok" produced from the
now-truncated tool output. This does not attempt to correlate a
killed PID to a specific job ID (process_registry tracks PIDs, not
job IDs) -- any job still dispatched at the moment of a forced kill
is treated as interrupted, matching the existing coarser precedent
set by _interrupt_running_agents(), which interrupts every entry in
_running_agents on a drain timeout without per-agent correlation
either.
Deliberately out of scope (flagged in the issue as a separate,
lower-priority concern): startup-time reconciliation of cron runs that
started but never reached a terminal status.
Testing:
- tests/cron/test_shutdown_interrupt.py (12 tests): get_running_job_ids
snapshot semantics, mark_running_jobs_interrupted marking/no-op/
partial-failure behavior, and -- the core race guard -- run_one_job
skipping its own last_status write (both the success path and the
exception path) when the shutdown path already marked the run
interrupted, with a control test proving ordinary un-interrupted
completions are unaffected.
- tests/gateway/test_cron_active_work_drain.py (9 tests):
_active_cron_job_count reading cron state and failing closed (0) if
the cron module is unavailable; _drain_active_agents waiting for an
in-flight cron job the same way it waits for chat sessions, timing
out if the job outruns the window, and leaving existing chat-session
drain behavior unchanged; a full runner.stop() integration test
(drain-timeout path) proving mark_running_jobs_interrupted actually
fires with the right job ID when a tool subprocess is force-killed,
plus a no-op control when nothing cron-related is in flight.
- tests/gateway/test_shutdown_cache_cleanup.py: added
_active_cron_job_count() to that file's hand-rolled _FakeGateway test
double, which stop() now calls -- without it those 8 pre-existing
tests AttributeError (caught by fail-then-pass below, not a
production bug).
Fail-then-pass: reverted gateway/run.py + cron/scheduler.py, all 21
new tests fail (fixture/attribute errors -- the feature doesn't exist
yet); restored, all 21 pass.
Regression check: ran the full plausibly-affected surface --
tests/gateway/{test_gateway_shutdown,test_restart_drain,
test_restart_notification,test_restart_redelivery_dedup,
test_restart_resume_pending,test_restart_service_detection,
test_shutdown_cache_cleanup,test_stuck_loop,test_clean_shutdown_marker,
test_external_drain_control,test_session_state_cleanup,
test_update_command,test_update_streaming}.py plus tests/cron/ (944
tests) -- against a clean upstream/main checkout and against this
branch. Diffed the two FAILED lists: identical, 20 pre-existing
failures on both sides (Windows-locale/cp1252 file-encoding issues and
Unix-permission-bit assertions that don't apply on this Windows dev
box), zero new failures, zero fixed-by-accident. The 8
test_shutdown_cache_cleanup.py failures found mid-development were
from the _FakeGateway gap above, fixed in the same commit and
confirmed clean on the final rerun (diff against baseline: exit 0).
Fixes#60432
/update and other shutdown paths only waited on gateway session agents,
so active cron tool work was killed immediately in final-cleanup while
the scheduler could still mark the job successful (#60432).
safe_load() raises ComposerError on multi-document streams (k8s manifests)
and ConstructorError on application-defined tags (CloudFormation !Sub,
Ansible !vault) — both valid YAML syntax. Now that the linter's verdict is
a fail-closed write gate, those false positives would refuse legitimate
writes outright. Switch to yaml.parse() (scanner+parser only), which still
catches real syntax failures.
write_file() previously called _atomic_write() first and only ran the
JSON/YAML/TOML/Python syntax check afterward as an informational lint
delta -- a parse failure never set the top-level `error` key, so a
corrupt structured-data write still landed on disk (and file_tools.py's
files_modified gating, which keys off `error`, silently reported it as
a successful modification).
Move the in-process syntax check for JSON/YAML/TOML ahead of
_atomic_write() and refuse the write outright on a parse failure: no
temp file, no rename, nothing touches disk, and the result carries a
top-level `error` so callers correctly see it as unmodified.
Deliberately scoped to _FAIL_CLOSED_INPROC_EXTS (JSON/YAML/TOML), not
all of LINTERS_INPROC -- .py is excluded because this codebase's own
test fixtures (TestPatchReplacePostWriteVerification et al.) write
arbitrary non-Python text through *.py paths purely to exercise
write-mechanics; a hard block there broke 3 previously-passing tests
during development. Python keeps its pre-existing non-blocking
lint-delta report.
Adds tests/tools/test_write_file_syntax_gate.py: invalid JSON/YAML/YML/
TOML refused with nothing written (new file) and nothing modified
(existing file); valid JSON/YAML still written byte-for-byte; a
non-linted extension with garbage content is unaffected; invalid Python
is confirmed NOT hard-refused (still just reported).
* feat(install): warn pip/Homebrew installs are unsupported (CLI, TUI, desktop)
pip and Homebrew are now Unsupported install methods per
website/docs/getting-started/platform-support.md. Surface a
warn-don't-block deprecation notice everywhere the install method is
already shown, pointing at the platform-support docs and noting these
installs will not receive further updates. NixOS (Tier 2) is untouched.
- hermes_cli/config.py: shared is_unsupported_install_method() /
format_unsupported_install_warning() helpers so the wording and docs
link stay consistent across every surface.
- hermes_cli/banner.py: generalize the existing pip-only banner
warning to also cover Homebrew.
- hermes_cli/main.py: hermes update and hermes update --check print
the warning before proceeding (still update; warn, don't block).
- tui_gateway/server.py: session.info gains install_warning.
- ui-tui: SessionPanel renders install_warning alongside the existing
'N commits behind' notice.
- apps/desktop: SessionRuntimeInfo/GatewayEventPayload gain
install_warning; applyRuntimeInfo + the live session.info event fire
a snoozable warning toast via a new reportInstallMethodWarning(),
mirroring the existing backend-contract-skew toast pattern. i18n
strings added for en/zh/zh-hant/ja.
- Tests: updated pip banner assertions for the new wording, added a
Homebrew banner test, and two tui_gateway session_info tests
(install_warning present for pip, absent for git).
* fix(nix): make `hermes` in developement environment actually work
install modules as editable overlay with uv
* feat: print install method when running --version
* fix: correct detect install method when running from a subtree
The April 2026 pin to WhiskeySockets/Baileys#01047deb existed only to
pick up the abprops bad-request fix (Baileys PR #2473) before it was
released. That fix shipped in v7.0.0-rc11 (May 2026); our pinned commit
is now 48 commits behind rc13.
The git pin forced npm to clone the repo and compile Baileys from
TypeScript source on every fresh install (~3 min), which blew past the
dashboard pairing flow's timeout. Registry install takes ~3s.
Validation: all 9 bridge.js imports present in rc13, bridge.native.test.mjs
passes (13/13), live bridge boot renders pairing QR against real WA servers.
The chat PTY launch path landed on main after PR #50558 and still called
_session_latest_descendant() with the old one-arg signature. Open the
requested profile's state DB (matching the REST endpoint) so profile-scoped
resume resolves descendants in the right database.
The connector now depends on the single multiplexed gateway for per-profile
relay routing, so hosted deployments need to FORCE multiplexing on regardless
of the image's config.yaml. gateway.multiplex_profiles was config.yaml-only,
which a user could leave unset or flip off.
Add GATEWAY_MULTIPLEX_PROFILES as a standard operator override on top of the
existing config key — the same 'config.yaml is canonical, env is the operator
override' pattern the Telegram/Signal require_mention bridges use:
env (recognized token) > config.yaml (top-level or nested gateway.*) > False
- gateway/config.py: _env_multiplex_profiles_override() resolves the env var
tri-state — recognized truthy/falsy token → bool; unset/blank/unrecognized
→ None (fall through to config). Blank is deliberately None, not False, so a
provisioned-but-unpopulated Fly secret ('') can't shadow a config.yaml opt-in
(the empty-secret trap). Wired into GatewayConfig.from_dict so every consumer
(run.py, session.py via self.config) sees the resolved value.
- hermes_cli/gateway.py: the named-profile-start guard
(_guard_named_profile_under_multiplexer) reads config.yaml directly, so it
gets the SAME env precedence — otherwise env-forced multiplex would leave the
guard blind and someone could start a conflicting per-profile gateway that
double-binds a bot token. Env-forced-on trips the guard even with no
config.yaml key; env-forced-off disables it over a config opt-in.
Tests: full 3-tier precedence in test_config.py (incl. the discriminating
env-overrides-config cases + the empty/whitespace/unrecognized fall-through
trap + resolver tri-state), mutation-verified (flipping precedence fails
exactly the two env-wins tests); guard env cases in test_multiplex_lifecycle.py.
Force-on is safe on a single-profile instance: session keys stay byte-identical
(agent:main) and the _run_agent wrapper installs the per-turn secret scope, so
the fail-closed get_secret() path is satisfied.
Strict charset allowlist (alnum + - _, max 64) on the {name} path param of
the memory-provider config/setup endpoints. Prevents traversal-shaped names
from reaching find_provider_dir(), and setup now 404s when neither a
loadable provider nor a plugin manifest exists, so the command-running path
is only reachable for discoverable plugins. Adds regression tests.
The multiplex machinery already routes an inbound message to a profile via
SessionSource.profile (build_session_key namespacing + the per-turn
config/credential scope in SessionStore._resolve_profile_for_key). But the
relay path never populated it: _event_from_wire rebuilt the SessionSource
field-by-field and dropped any 'profile' the connector sent, so a
Team-Gateway (connector + relay) message could not be routed to a specific
profile the way the /p/<profile>/ HTTP prefix and per-credential polling
adapters already can.
Stamp source.profile from the wire payload in _event_from_wire. This is the
last missing link for NAS-driven per-profile routing over the relay in
multiplex mode; the connector populating the field ships separately
(gateway-gateway contract adds the optional wire field).
Back-compat: absent 'profile' → None → legacy agent:main namespace,
byte-identical to today for every single-profile gateway.
The profile+gateway topology added in #60537 sits entirely behind the
loopback/--insecure auth gate. But a hosted agent (Hermes Cloud) binds
non-loopback with OAuth, so should_require_auth is True, and NAS reads
/api/status over the network (fly-provider.ts getInstanceRuntimeStatus)
with no session token. On that gated path the whole topology block was
omitted, so the Portal could never render the profile list.
Split the topology readout by sensitivity:
- profile NAMES (profiles) + gateway_mode are low-sensitivity product
surface and now ride the always-public status body, surviving the auth
gate so NAS/the Portal can enumerate profiles.
- the per-gateway detail (gateways[], carrying host ports) is deployment
recon and stays gated alongside hermes_home / config_path / env_path /
gateway_pid / gateway_health_url.
The collector now runs unconditionally (still in the executor, off the
event loop). No new fields; only the gate placement changes.
Headless/hosted deploys run the dashboard server without COLORTERM in
the process environment, so chalk inside the PTY-spawned TUI child
downgraded every skin hex color to the xterm 256 palette — the default
skin's bronze banner border (#CD7F32) snapped to palette 173 (#D7875F,
salmon red) and the gold caduceus rendered red/yellow on fresh cloud
instances. Local launches never reproduced it because the operator's
interactive terminal leaks COLORTERM=truecolor into the server env.
xterm.js always renders 24-bit RGB, so the dashboard PTY child should
always advertise truecolor: backfill COLORTERM=truecolor in
_resolve_chat_argv via setdefault (an explicit operator value wins).
Verified with a clean-env PTY probe of the real TUI binary:
no COLORTERM -> 0 truecolor SGRs / 165 palette-256 (salmon 38;5;173);
with the backfill -> 166 truecolor SGRs, exact bronze 38;2;205;127;50.
Session-based channel discovery resurrected historical origins for
platforms with no connected adapter, exposing stale send_message
targets that can no longer deliver. Gate both the enum loop and the
plugin-registry loop on the live adapter set.
Surgical reapply of the channel-directory portion of PR #25959 (branch
was 6.5k commits stale; the text-batching delay changes bundled there
were dropped - separate concern, defaults have since been retuned on
main).
Co-authored-by: Marco-Olivier Lavoie <marcolivier@gmail.com>
Docs portion of PR #57067: 'bot connects but never replies' section
pointing at the gateway.log warning and the allowlist/policy knobs.
Co-authored-by: ooovenenoso <120500656+ooovenenoso@users.noreply.github.com>
Log a one-shot structured warning when Discord denies traffic because
no allowlist/policy is configured, and correct the setup wizard's
inverted warning text. The fail-closed default itself is unchanged.
Fixes#58682.
Restructures the five parallel export sections into a single 'Export
Sessions' section: a format table (jsonl/md/qmd/html/trace + --only
user-prompts), one shared-filters paragraph covering all formats, and
per-format subsections nested beneath. EN + zh-Hans.
When a user explicitly configures a platform with its native composite
(e.g. platform_toolsets.discord: [hermes-discord]), the discord and
discord_admin toolsets were silently stripped by _DEFAULT_OFF_TOOLSETS
even though the composite contains those tools. The strip could not tell
an explicit composite opt-in apart from the unconfigured default.
Track whether the platform was explicitly configured and, when it was,
exempt toolsets that are both default-off and platform-restricted to the
current platform from the strip. Only discord/discord_admin are affected
(the sole entries in both _DEFAULT_OFF_TOOLSETS and
_TOOLSET_PLATFORM_RESTRICTIONS). Unconfigured and empty-list platforms
keep the security default-off behaviour.
/api/status (loopback/insecure binds only) now includes:
- profiles: every profile on the host (default + named)
- gateway_mode: none | single | multiple | multiplex
- gateways: one entry per live gateway with the host ports its
port-binding platforms listen on, plus served_profiles when the
default gateway is multiplexing
Ports resolve from each profile's config.yaml (top-level platforms:
wins over gateway.platforms:, matching load_gateway_config precedence)
with adapter defaults as fallback. Topology enumeration runs in an
executor so the profile scan + process-table probes stay off the event
loop, and the whole block is gated behind the same loopback-only split
as hermes_home/gateway_pid so gated binds leak nothing new.
signal.SIGKILL / os.killpg don't exist on Windows. The watchdog is only
spawned on POSIX (wrap site gates on os.name), but guard via getattr with
a plain terminate/kill fallback so an accidental Windows import can't
AttributeError.
The salvaged test predates the parked-server self-probe
(_PARKED_RETRY_INTERVAL, landed on main after the PR branched): after the
final failed retry, run() parks in a real asyncio.wait that the patched
asyncio.sleep doesn't cover, stalling the test 300s. Signal shutdown once
the retry budget is exhausted so the park exits immediately.
Two fixes on top of the salvaged parent-death watchdog:
- Apply the watchdog wrap AFTER the OSV malware preflight so the check
inspects the real npx/uvx package instead of the python wrapper
(the wrap previously made the preflight a silent no-op for every
stdio server).
- The real server runs in its own process group under the watchdog, so
the graceful-shutdown killpg no longer reached it; the watchdog now
forwards SIGTERM/SIGINT to the child's group, keeping wedged servers
killable on clean shutdown.
A stdio MCP server (e.g. `npx -y mcp-remote <url>`) is spawned as a direct
child of the Hermes process. Existing teardown (MCPServerTask.shutdown() /
_kill_orphaned_mcp_children()) reaps it correctly on a clean exit, but a
kill -9 / crash / force-quit of the Hermes process skips that path entirely
-- the child (and its own descendants, e.g. mcp-remote's spawned node
process) is orphaned and keeps running. Repeated ungraceful restarts pile up
N orphaned processes racing to hold the same upstream SSE session, producing
errors like 'Invalid request parameters' on legitimate reconnects.
macOS/Linux have no portable equivalent of prctl(PR_SET_PDEATHSIG) at the
Python subprocess level, so this adds a thin supervisor
(tools/mcp_stdio_watchdog.py) that:
- execs the real command as its own child in its own process group
- passes stdin/stdout/stderr through untouched (MCP stdio protocol
talks directly over those streams)
- polls the original spawning PID with the same orphan-detection
algorithm already proven in tui_gateway/slash_worker.py (ppid
comparison + psutil creation-time guard against PID reuse)
- SIGTERM-then-SIGKILL's the child's process group the moment the
original parent is gone
Wired into _run_stdio via a new _wrap_command_with_watchdog() helper,
POSIX-only (matches the existing killpg-based cleanup's platform scope),
fails open (any error resolving pid/create-time falls back to the
unwrapped command) so this can never be the reason a working MCP server
stops starting.
Verified: reproduced the exact orphan scenario standalone (fake parent
process spawns watchdog + fake long-running MCP child, kill -9 the fake
parent, confirm the watchdog reaps the child within its poll window with
zero leaked processes). Updated test_mcp_tool_issue_948.py's resolved-path
assertion to check the watchdog-wrapped command instead of the raw
resolved binary. Full test_mcp_tool.py + test_mcp_stability.py +
test_mcp_tool_issue_948.py suite: 232 passed. Full -k mcp sweep across the
whole test tree: 1003 passed, 2 skipped, 0 failed.
Sibling sites of the same bug class as the salvaged stdio fix:
- SSE, streamable-HTTP (new + deprecated API) initialize() calls are now
bounded by the same connect_timeout, so an endpoint that accepts the
connection but never answers the handshake cannot park the run() task
forever.
- start() now cancels its ensure_future'd run() task when the caller's
connect timeout cancels start() itself — the orphaned-task leak was
the root mechanism behind #59349, and this closes the class for any
future pre-ready hang.
A stdio MCP server that never completes `initialize` (e.g. emits a
non-JSON-RPC frame and then blocks on stdin) leaks a child process plus its
stdio pipes/pidfd on every discovery-retry cycle — unbounded, until the
gateway hits EMFILE and every new open()/spawn fails (#59349).
Root cause (confirmed by instrumenting the live repro, and different from the
issue's own hypothesis): the spawned child IS captured in `new_pids`, so the
report's "new_pids empty at finally" guess is not it. The real cause is that
`session.initialize()` hangs forever on the garbage stream. `connect_timeout`
only bounds the caller's `.result()` wait on the foreground thread — it does
NOT cancel the `_run_stdio` coroutine on the background MCP loop. So the
coroutine is stuck at `await session.initialize()` permanently, its cleanup
`finally` never runs, the child is never reaped, and it stays invisible to the
orphan-reaper (whose `_orphan_stdio_pids` set never gets populated).
Fix: wrap `session.initialize()` in `asyncio.wait_for(..., connect_timeout)`
so a stalled handshake fails instead of hanging. The TimeoutError unwinds
through the SDK context managers (closing the child's stdin -> EOF -> exit)
and lets the existing `finally` reap any straggler. Cross-platform — no
signals/pgid/proc.
Scope: stdio only. The HTTP path has the same `await session.initialize()`
shape but spawns no subprocess (so it can't cause this leak) and already has
httpx transport timeouts.
Verified: the reporter's repro goes from unbounded growth to draining to zero;
added a hermetic regression test (fake transport whose `initialize()` hangs,
asserts the connect is bounded by connect_timeout) that fails on the pre-fix
code and passes on the fix; 566 existing MCP tests pass; ruff clean.
Repro confirmed on macOS (pipe FDs); the Linux-specific pidfd growth in the
report should be equivalent — the reporter offered to validate on Linux.
Closes#59349
Merge the two cherry-picked reap call sites into one unscoped sweep at
the top of _run_stdio (the unscoped sweep is a superset of the
per-server one), and run it via asyncio.to_thread so the 2s
SIGTERM->SIGKILL escalation cannot stall the shared MCP event loop.
When an MCP stdio subprocess fails to connect (token expiry, port
contention, timeout), the run() reconnect loop retries with backoff.
Each retry calls _run_stdio() which spawns a new process pair, but the
previous failed pair was only detected as orphaned (added to
_orphan_stdio_pids) — never actually killed. This caused rapid zombie
accumulation: 5 failed attempts × 2 procs each = 10 orphans competing
for the same port.
Add a _kill_orphaned_mcp_children() call at the top of _run_stdio(),
before the _snapshot_child_pids() baseline, so any orphans from prior
failed attempts are reaped before a new subprocess is spawned.
Fixes#57355
ChatPage sends ?attach=<localStorage token> so /chat reattaches to its
live PTY across refresh. onclose: 4410=process-exit (session ended),
4409=superseded (quiet), else transient -> auto-reconnect.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Keep-alive path when ?attach=<token> is present: PTY outlives the socket
via PTY_REGISTRY, reattaches on reconnect. No token = unchanged legacy
pump (_legacy_pump). detach (not close) on disconnect.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
_run_approval_gate's gateway branch only queued via submit_pending, so
plugin-escalated approvals never sent the interactive embed+buttons on
Discord/Telegram/Slack (#59413) - the user was never notified and the
action stayed silently blocked. Mirror check_dangerous_command's path:
when a session notify callback is registered, run the blocking
_await_gateway_decision round-trip (redacted payload, once/session/
always persistence, deny/timeout produce definitive BLOCKED outcomes);
fall back to submit_pending only when no callback exists.
Fixes#59413.
Follow-up on the #56966 salvage:
- is_provider_explicitly_configured(): an env-seeded credential-pool entry
only counts as explicit while its env var still resolves to a usable
secret. A stale auth.json entry left behind after the user deletes the
var no longer keeps the provider in the picker forever (#55790).
- TUI modelPicker + dashboard ModelPickerDialog/api.getModelOptions pass
include_unconfigured=true explicitly, preserving their full-universe
setup-affordance behavior now that the backend defaults to the
configured subset.
- desktop lib/model-options.ts routes explicit_only through the shared
requestModelOptions() helper (added on main after the PR branched).
- regression tests for ambient (gh_cli) pool sources, explicit manual/
device-code sources, and stale vs live env-seeded entries.
* feat(trace): upload sessions to HF Agent Trace Viewer
Salvage trace upload as a smaller CLI-first feature: deterministic Claude Code JSONL export, fail-closed redaction, lazy Hugging Face dependency, and no gateway slash-command wiring.
* chore(trace): drop external porting references from docstrings
Describe the trace-upload design in Hermes' own terms.
* feat(sessions): fold trace upload into 'sessions export --format trace'
Integrates the HF Agent Trace Viewer exporter (PR #36145) onto the
unified export surface instead of a separate 'hermes trace' subcommand:
- --format trace: Claude Code JSONL to stdout/file, or one
<id>.trace.jsonl per session for filtered bulk export; defaults to
the most recent session when no --session-id/filters given.
- --upload pushes to the user's private HF traces dataset (--public to
opt out of private); reads HF_TOKEN with guided setup when missing.
- traces are secret-redacted by default (force mode); --no-redact opts
out after review; redaction failure blocks export (fail closed).
- hermes_cli/trace.py + subcommands/trace.py removed; agent/trace_upload.py
is the single engine. Docs EN + zh-Hans; 4 new CLI tests.
The salvaged SelfHostedBackend made self-hosted servers reachable via
mem0.json / MEM0_HOST, but the setup wizard still offered only Platform
and OSS — exactly the gap users hit (Discord report: 'At memory setup
there's only 2 options'). Adds a third wizard mode:
- interactive picker: Platform / Self-hosted server / Open Source
- non-interactive: hermes memory setup mem0 --mode selfhosted
--host http://... [--api-key ...] [--dry-run]
- host -> mem0.json (behavioral), API key -> .env as MEM0_API_KEY
(secret), optional key for AUTH_DISABLED servers
- best-effort reachability check against the server, non-fatal
- README + memory-providers docs updated with the wizard path
`_save_anthropic_oauth_creds` wrote the Anthropic OAuth token file with
`os.replace(tmp, path)` followed by a post-hoc `chmod(0o600)`. Between the
rename and the chmod the token file existed at the default umask (0o644 on most
hosts) — a window in which another local user could read the access/refresh
tokens.
Write via `utils.atomic_json_write(..., mode=0o600)`, which creates the temp
with mode 0o600 *before* any content is written, fsyncs, atomically replaces,
preserves the existing file's owner, and cleans up its temp on failure. This
matches the `atomic_json_write(mode=0o600)` call already used elsewhere in this
module for the credential-pool write, and #56644's owner preservation.
Tests updated for the new mechanism, plus a check that the write goes through
`atomic_json_write(mode=0o600)` (mutation-verified).
Opt-in discord.approval_mentions (config.yaml, bridged to
DISCORD_APPROVAL_MENTIONS) prepends <@id> mentions for numeric
allowlist entries to exec-approval prompts, with a scoped
AllowedMentions override (users only). Default off - no surprise
pings. Reapplied onto the content-mirror layout from #60245: mentions
prepend to the visible content block and its truncation budget.
Original implementation from PR #39719; commits arrived bot-authored,
re-attributed to the contributor.
Salvage follow-up integrating PR #30481 (@simplast) and PR #57683
(@catbearlove1-lang) into the unified export surface:
- --format html: standalone self-contained HTML transcript (single
session or multi-session with sidebar), works with all shared filters
and --redact; requires a file output path.
- --only user-prompts: prompt-only export (jsonl records or md sections)
via the shared session_export renderer; the separate export-prompts
subcommand from the original PR is subsumed by this flag.
- AUTHOR_MAP entries for both contributors; docs EN + zh-Hans.
Implements a professional, standalone HTML export feature for Hermes sessions.
Key changes:
- Adds 'hermes sessions export <file>.html' support to the CLI.
- Implements a dark-mode-first, responsive HTML generator in 'hermes_cli/session_export_html.py'.
- Single session export features a focused, centered 90% width layout.
- Multi-session export adds a fixed sidebar with session switching and real-time search filtering.
- ZERO external dependencies; all styles and JS are embedded for offline portability.
Review follow-ups on the salvage:
- get_all() pruned from the ABC and all three backends: mem0_list (its
only caller) was removed by the recall-tuning commit, leaving new,
tested, unreachable code — including SelfHostedBackend's _MAX_TOP_K
over-fetch workaround. Tests for it dropped; fake-class stubs remain
harmlessly. (The #52921 true-total fix lives on in the PR history if
a lister ever returns.)
- The persisted rerank config key was write-only (setup prompted for it,
nothing read it). initialize() now parses it into _rerank_default and
mem0_search uses it when the model doesn't pass rerank explicitly;
per-call args still win. Guard test added.
- Platform-mode setup now warns when MEM0_HOST is set in the environment:
the json host-clear can't help there (_load_config seeds host from the
env var, docs tell users to put it in .env) — the user would silently
keep routing to the self-hosted server.
- SelfHostedBackend: connect-level retries (httpx.HTTPTransport(retries=2))
so a single transient blip doesn't count toward the provider breaker;
transport now injectable and the test helper uses the real __init__
instead of mirroring it via __new__.
- plugin.yaml description no longer leads with reranking (off by default,
platform-only); docs em-dash typo fixed.
Follow-up on the salvaged #55614. The PR added host-based routing to
_create_backend (precedence: oss > host > platform) but two sibling surfaces
didn't mirror it:
- system_prompt_block() checked host before oss, so an oss+host config ran
OSS but told the model it was self-hosted HTTP. Reordered to match routing.
- Platform setup (hermes memory setup mem0 --mode platform) left a stale host
in mem0.json; since host beats platform, the user kept routing to the
self-hosted server. save_config merges (no delete), so clear host to ""
rather than pop() so the merge actually overwrites it.
Adds regression tests for both (mutation-checked).
Salvage of #55614 by @kartik-mem0 (mem0 maintainer). Adds a SelfHostedBackend
that talks to a self-hosted Mem0 Docker server over httpx (X-API-Key auth,
/search + /memories routes), gated behind `host`. Also folds in the mem0
research-team recall tuning that rides with it: rerank defaults to false across
all modes, the mem0_list tool is removed (5->4 tools), search guidance is
de-shouted, and self-hosted get_all reports the true stored total (#52921).
Supersedes the self-hosted portion of #52487 (@liuhao1024, first-submitted).
Closes#52478Fixes#52921
Review findings on the salvaged shim: (a) OpenAI callers may pass stop as
a bare string but Converse's stopSequences requires a list — normalize;
(b) call_llm(stream=True) (MoA aggregator) can reach this client and the
shim silently returned a complete response — keep that behavior (the
streaming consumer's got-final-object path downgrades gracefully) but log
it, and log dropped tool_choice, instead of silently ignoring both.
+2 regression tests.
Follow-up to the salvage of #60217 by @xxxigm.
Auxiliary Bedrock resolution always used the Anthropic Bedrock SDK, which
only works for Claude foundation-model IDs. Non-Claude models such as
openai.gpt-oss-20b-1:0 now use a Bedrock Converse adapter, matching the
main agent's bedrock_converse transport.
Review findings on the salvaged #60332 breaker, fixed as follow-ups:
- restore_primary_runtime() now resets the streak (third provider-swap
path; without it a recovered primary was short-circuited before a
single attempt and could never be re-proven healthy except via /model).
- interruptible_api_call (non-streaming) now carries the same breaker
(guard at entry, bump on stale_call_kill, reset on success). Quiet-mode
/ subagent / headless sessions — the profile most like #58962's
unattended 494-failure session — take this path and had the identical
infinite stale-retry class.
- Partial-stream stub return now resets the streak (chunks were received,
provider demonstrably responsive).
- Consolidated the triple-duplicated counter arithmetic into shared
helpers (_stale_streak/_bump_stale_streak/_reset_stale_streak/
_check_stale_giveup) with one canonical comment block; error message
now says 'consecutive stale attempts' (the counter counts kills, not
turns — a single turn can produce several).
4 new tests (restore resets / no-op restore keeps latch / non-streaming
short-circuit / non-streaming success reset).
Follow-up for the salvaged #60332 circuit breaker. The breaker latches:
once the streak trips, interruptible_streaming_api_call raises before any
stream is attempted, so the on-success reset can never run again. The
error text tells the user to switch models and retry — but neither
switch_model() nor try_activate_fallback() cleared the streak, so a
freshly selected healthy provider kept short-circuiting forever (only
/new recovered), and the automatic fallback chain was wedged the same way.
Reset the streak at both swap sites (after a successful rebuild only;
rollback/exhaustion paths keep the latch). 4 tests.
A session wedged against an unresponsive OpenAI-compatible provider can hit the stale-stream detector on every turn and loop forever, burning the full 180s x retries each turn with no response. Issue #58962 reports 494 consecutive failures over 3+ days on a single session.
The streaming retry path already caps retries WITHIN a turn (HERMES_STREAM_RETRIES, default 2) but has no cross-turn cap. Once a session's conversation state makes every turn stale, it retries indefinitely across turns and never notifies the user.
Add a per-session consecutive-stale-stream counter on the agent:
- incremented on every stale-stream kill in the outer poll loop;
- reset to 0 only when a stream actually completes;
- when it reaches HERMES_STREAM_STALE_GIVEUP (default 5), the next turn aborts immediately with a clear, actionable RuntimeError instead of spending 180s x retries again.
This is distinct from the existing stale-stream work (local-provider hard ceiling #44938, backoff/parse-error #60031): those bound a single hung stream, while this bounds repeated cross-turn staleness and surfaces a user-visible error.
Adds tests/run_agent/test_stream_stale_circuit_breaker.py covering the short-circuit, the success-reset, and the increment.
Same 10062 degrade-gracefully pattern as _run_simple_slash: create the
thread anyway, skip the ephemeral followups that need a live
interaction token. Non-expiry defer errors still raise.
- export now shares _add_session_filter_args / build_prune_filters with
prune/archive: AGE grammar (5h/2d/1w/ISO) on --older-than plus the full
filter set (--model, --provider, --min-messages, --min-cost, --branch,
--chat-id, ...) for both JSONL and md/qmd bulk exports; --dry-run works
on JSONL too; removes the one-off list_export_candidates helper.
- new --redact flag runs exported message content and tool output through
force-mode secret redaction (agent.redact) for jsonl, md, and qmd.
- docs EN + zh-Hans updated; new tests for AGE grammar, extended filters,
filtered JSONL, and redaction.
Replaces the parallel export-md subcommand from the salvaged commit with
a --format jsonl|md|qmd flag on the existing export subcommand, so all
session export formats share one surface. Adds AUTHOR_MAP entry.
Salvage follow-up for PR #59542 by @web3blind.
@@ -491,18 +491,18 @@ The dashboard embeds the real `hermes --tui` — **not** a rewrite. See `hermes
### Electron Desktop Chat App (`apps/desktop/`)
A **separate** chat surface from both the classic CLI and the dashboard's embedded TUI. It is an Electron + React + nanostore renderer (`@assistant-ui/react`) that talks to a `tui_gateway` backend over JSON-RPC (`requestGateway(method, params)`). The WebSocket/JSON-RPC transport lives in the framework-agnostic `apps/shared` package (`@hermes/shared` — `JsonRpcGatewayClient` + WS URL helpers), which the web dashboard (`web/`) also consumes; **desktop has no build/runtime dependency on the dashboard frontend** — it spawns a headless `hermes serve` backend server (the same gateway `dashboard` serves, minus the browser UI entirely: `serve` sets `headless_backend=True`, so `cmd_dashboard` skips `_build_web_ui` AND exports `HERMES_SERVE_HEADLESS=1` so `mount_spa()` disables the SPA even if a stray `web_dist/` exists — only the JSON-RPC/WS/API surface is reachable). `dashboard` and `serve` share `cmd_dashboard`/`start_server` but are independent surfaces — neither launches the other. The one exception is a backward-compat *fallback*: `serve` is newer, so the desktop spawn (`electron/backend-command.cjs` + `backendSupportsServe()` in `main.cjs`) detects whether the resolved runtime registers `serve` and, only when it does not (an older managed install / PATH `hermes` the app hasn't updated yet), rewrites the argv to the legacy `dashboard --no-open`. Without that, a new app against an un-upgraded runtime would crash on an unknown subcommand and brick every mid-upgrade user. It does NOT embed `hermes --tui` — it has its own composer, transcript, and slash-command pipeline. Route desktop bugs to the `hermes-desktop-app-work` skill, not `hermes-dashboard-work`.
A **separate** chat surface from both the classic CLI and the dashboard's embedded TUI. It is an Electron + React + nanostore renderer (`@assistant-ui/react`) that talks to a `tui_gateway` backend over JSON-RPC (`requestGateway(method, params)`). The WebSocket/JSON-RPC transport lives in the framework-agnostic `apps/shared` package (`@hermes/shared` — `JsonRpcGatewayClient` + WS URL helpers), which the web dashboard (`web/`) also consumes; **desktop has no build/runtime dependency on the dashboard frontend** — it spawns a headless `hermes serve` backend server (the same gateway `dashboard` serves, minus the browser UI entirely: `serve` sets `headless_backend=True`, so `cmd_dashboard` skips `_build_web_ui` AND exports `HERMES_SERVE_HEADLESS=1` so `mount_spa()` disables the SPA even if a stray `web_dist/` exists — only the JSON-RPC/WS/API surface is reachable). `dashboard` and `serve` share `cmd_dashboard`/`start_server` but are independent surfaces — neither launches the other. The one exception is a backward-compat *fallback*: `serve` is newer, so the desktop spawn (`electron/backend-command.ts` + `backendSupportsServe()` in `electron/main.ts`) detects whether the resolved runtime registers `serve` and, only when it does not (an older managed install / PATH `hermes` the app hasn't updated yet), rewrites the argv to the legacy `dashboard --no-open`. Without that, a new app against an un-upgraded runtime would crash on an unknown subcommand and brick every mid-upgrade user. It does NOT embed `hermes --tui` — it has its own composer, transcript, and slash-command pipeline. For scoped Desktop architecture, state, resolver, transport, and testing rules, read `apps/desktop/AGENTS.md`.
**Slash commands in the desktop app are curated client-side, then dispatched to the backend.** The pipeline:
- **Backend already provides everything.** `tui_gateway/server.py``commands.catalog` (empty-query list) and `complete.slash` (typed-query completions) both include built-in commands, user `quick_commands`, AND skill-derived commands (`scan_skill_commands()` / `get_skill_commands()`). The desktop app does not need a new RPC to see skills.
- **The renderer curates via `apps/desktop/src/lib/desktop-slash-commands.ts`.** This is the load-bearing file. It holds `DESKTOP_COMMANDS` (the ~19 built-ins shown in the palette) plus block-lists for terminal-only / messaging-only / picker-owned / settings-owned / advanced commands that should NOT clutter the desktop popover.
- **The renderer curates via `apps/desktop/src/lib/desktop-slash-commands.ts`.** This is the load-bearing file. It holds `DESKTOP_COMMAND_SPECS` (the built-ins and their Desktop surfaces) plus `NO_DESKTOP_SURFACE` block-lists for terminal-only / messaging-only / picker-owned / settings-owned / advanced commands that should NOT clutter the desktop popover.
-`isDesktopSlashCommand(name)` — gates **execution**. Returns true for built-ins AND for any non-built-in (skill / quick command), so typed extension commands run.
-`isDesktopSlashSuggestion(name)` — gates **discovery/completion**. Used by BOTH completion paths in `app/chat/composer/hooks/use-slash-completions.ts` (empty-query catalog filter + typed-query `complete.slash` filter) and by `filterDesktopCommandsCatalog`.
-`isDesktopSlashExtensionCommand(name)` — true when the command is NOT a known Hermes built-in (i.e. a skill or user quick command). Both suggestion and catalog-filter paths allow extensions through so skill commands surface in the palette. (Added when fixing "skill commands missing from the desktop slash palette" — the curated allow-list was silently dropping every skill/quick command from completions even though they executed fine when typed.)
- **Dispatch** lives in `app/session/hooks/use-prompt-actions.ts` (`runSlash`): built-ins that the desktop owns (`/skin`, `/help`, `/new`, …) are handled locally or via `commands.catalog`; everything else goes to `slash.exec`, falling back to `command.dispatch` (which the gateway resolves into skill / alias / exec directives). A skill command resolves to `{type: "skill", message}` and is submitted as a normal prompt.
- **Dispatch** lives in `app/session/hooks/use-prompt-actions/slash.ts` (`runSlash`): built-ins that the desktop owns (`/skin`, `/help`, `/new`, …) are handled locally or via `commands.catalog`; everything else goes to `slash.exec`, falling back to `command.dispatch` (which the gateway resolves into skill / alias / exec directives). A skill command resolves to `{type: "skill", message}` and is submitted as a normal prompt.
**Rule:** the desktop slash palette's curation is about hiding noise (terminal-only / messaging-only built-ins), NOT about hiding user-activated extensions. Skill commands and `quick_commands` are extensions the backend surfaces — they belong in completions. If you tighten `desktop-slash-commands.ts`, keep `isDesktopSlashExtensionCommand` flowing into both the suggestion and catalog-filter paths. Tests: `apps/desktop/src/lib/desktop-slash-commands.test.ts` (run via the repo-root `vitest`, since `apps/desktop` resolves deps from the root workspace install).
**Rule:** the desktop slash palette's curation is about hiding noise (terminal-only / messaging-only built-ins), NOT about hiding user-activated extensions. Skill commands and `quick_commands` are extensions the backend surfaces — they belong in completions. If you tighten `desktop-slash-commands.ts`, keep `isDesktopSlashExtensionCommand` flowing into both the suggestion and catalog-filter paths. Tests: from`apps/desktop`, run `npx vitest run src/lib/desktop-slash-commands.test.ts` (workspace dependencies are installed at the repo root).
---
@@ -1354,3 +1354,58 @@ not the specific names.
Reviewers should reject new change-detector tests; authors should convert
them into invariants before re-requesting review.
### Never read source code in tests
A test that reads a source file's text is testing *the shape of the
source code*, not its behavior. This is a hard antipattern, banned outright.
Any test that reads a .py, .ts, .tsx, etc., file is suspect.
**Why it's actively harmful, not just weak:**
- It passes when the implementation is subtly broken (the regex matches a
call site that exists but is wired wrong) and fails when a correct
refactor changes formatting, variable names, or control flow with
identical runtime behavior. Both directions of failure are wrong.
- It can't be run against a built/bundled/minified artifact, so it silently
stops testing anything the moment code moves, gets renamed, or a
dependency reformats it.
- It actively blocks refactors: reviewers see "keeps a pattern intact" tests
fail during pure structural cleanup with no behavior change, and either
hand-wave the failure (dangerous) or waste time updating regexes that add
nothing (waste).
- It gives false confidence. a green suite full of source-regex tests
looks like coverage but has never once executed the code path it claims
@@ -67,6 +67,8 @@ npm run dev # Vite renderer + Electron, which boots the Python backend
Point the app at a specific source checkout, or sandbox it away from your real config:
```bash
# throwaway HERMES_HOME, separate Electron userData, distinct app name to avoid the single-instance lock
../scripts/dev-sandbox.sh npm run dev
HERMES_DESKTOP_HERMES_ROOT=/path/to/clone npm run dev
HERMES_HOME=/tmp/throwaway npm run dev
npm run dev:fake-boot # exercise the startup overlay with deterministic delays
@@ -85,7 +87,63 @@ Installers are built and uploaded to GitHub Releases manually. macOS/Windows sig
### How it works
The packaged app ships the Electron shell and a native React chat surface. On first launch it can install the Hermes Agent runtime into `HERMES_HOME` (`~/.hermes`, or `%LOCALAPPDATA%\hermes` on Windows) — the **same layout a CLI install uses**, so the two are interchangeable. Backend resolution first honours `HERMES_DESKTOP_HERMES_ROOT`, then a completed managed install, then a probed `hermes` on `PATH` (unless `HERMES_DESKTOP_IGNORE_EXISTING=1` is set), and finally an explicit `HERMES_DESKTOP_HERMES` command override for packagers/troubleshooting. The renderer (React, in `src/`) talks to a headless backend the app launches for you — a `hermes serve` process that serves the `tui_gateway` JSON-RPC/WebSocket API — through the framework-agnostic client in [`apps/shared`](../shared/) (the same client the web dashboard consumes), and reuses the agent runtime rather than embedding `hermes --tui`. The app is **self-contained**: it runs its own `hermes serve` backend and never opens or requires the web dashboard UI. (For backward compatibility, a runtime that predates the `serve` command automatically falls back to a headless `dashboard --no-open` — see `electron/backend-command.cjs` — so mid-upgrade installs never break.) The install, backend-resolution, and self-update logic all live in `electron/main.cjs`.
The packaged app ships the Electron shell and a native React chat surface. On
first launch it can install the Hermes Agent runtime into `HERMES_HOME`
(`~/.hermes`, or `%LOCALAPPDATA%\hermes` on Windows), using the same layout as a
CLI install.
The app has three boundaries:
- **Electron** resolves and validates a runnable backend, owns native
filesystem/git/window capabilities, and exposes a narrow preload bridge.
- **React** owns the Desktop routes, panes, interaction state, and
`@assistant-ui/react` transcript.
- **Hermes Agent** runs as a headless `hermes serve` process and exposes the
`tui_gateway` JSON-RPC/WebSocket API. The renderer connects through
[`apps/shared`](../shared/), which is also used by the browser dashboard.
Backend resolution is an ordered ladder:
1. `HERMES_DESKTOP_HERMES_ROOT`
2. the current source checkout during development
3. a completed managed install
4. `HERMES_DESKTOP_HERMES`, or `hermes` on `PATH`
5. a system Python that can import the Hermes runtime
6. the first-launch bootstrap installer
Candidates are probed before use; an existing shim or interpreter is not enough.
A runtime that predates `serve` falls back to headless
`dashboard --no-open`. This is compatibility for the backend command only and
does not launch or embed the dashboard UI.
The Electron orchestration entry point is `electron/main.ts`; pure resolution,
probe, hardening, and platform policies live in focused modules beside it. The
renderer is under `src/`, with shared atoms in `src/store` and transport/native
adapters in `src/lib`.
Before changing the app, read:
- [`AGENTS.md`](./AGENTS.md): architecture, state ownership, resolver/fallback,
transport, performance, and testing rules.
- [`DESIGN.md`](./DESIGN.md): visual system, information architecture, motion,
direct manipulation, and keyboard behavior.
### Connections, projects, and switching
Desktop supports a managed local backend, explicit remote gateways, and Hermes
Cloud connections. Remote and cloud modes use the same remote-capability path;
authentication and discovery differ, not the renderer feature model.
Projects are the workspace abstraction. A project may own multiple folders,
repositories, worktrees, and sessions; a bare new chat remains detached unless
the user enters a project or configures a default project directory. Use the
Projects UI rather than adding a second per-session folder-picker workflow.
Changing profiles or connection modes is a soft workspace switch, not another
cold boot. The shell and current management overlay remain mounted while
gateway-bound nanostores are wiped, query-backed data is invalidated, and the
new connection repopulates skeletons. This prevents rows or transcripts from
the previous gateway bleeding into the next one.
### Verification
@@ -95,9 +153,13 @@ Run before opening a PR (lint may surface pre-existing warnings but must exit cl
npm run fix
npm run typecheck
npm run lint
npm run test:desktop:all
npm run test:ui
npm run test:desktop:platforms
```
Run `npm run test:desktop:all` for install, boot, update, packaging, or other
release-path changes.
### Troubleshooting
Boot logs land in `HERMES_HOME/logs/desktop.log` (includes backend output and recent Python tracebacks) — check it first if the app reports a boot failure.
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Brooklyn Nicholson