Commit Graph
99 Commits
Author SHA1 Message Date
Rohit P 93877871a3 docs: improve Desktop App and SDK getting started guides 2026-11-12 14:28:50 -08:00
Rohit P ea495cd092 docs: simplify Harness SDK onboarding and add architecture visual 2026-11-12 13:21:14 -08:00
Rohit P 8b27b39681 feat(skills): confirm replacement and retain installation backups 2026-11-12 12:00:59 -08:00
Rohit P 43f7e63c80 docs: clarify SDK tools, approvals and builder skill usage 2026-11-12 11:44:55 -08:00
Rohit P 685b6d12d4 feat(sdk): add reviewer and compaction guidance 2026-11-12 07:15:46 -08:00
Rohit P 9ac4f83267 feat(sdk): support image, PDF and text attachments 2026-11-11 08:21:22 -08:00
Rohit P 88c3535166 Add optional SDK observability and evaluation exports 2026-11-10 23:57:36 -08:00
Rohit Prasad 8171fb70e2 Merge pull request #871 from andrewyng/feat/standalone-sdk-subagents
Add standalone sub-agent support to the SDK
2026-11-10 20:17:42 -08:00
Rohit P 2869e84df8 feat: add standalone SDK sub-agents with durable coordination 2026-11-10 19:27:58 -08:00
Rohit P 66e9506d14 feat: prepare private Azure registry and expiry-owned management access 2026-11-10 18:48:23 -08:00
Rohit P 9fbaccff5c fix: support Azure Dasv7 nodes and verify selected compute quota 2026-11-10 18:48:23 -08:00
Rohit P ae8b44f998 test(sdk): consume typed text deltas in tool-free qualification 2026-11-07 21:41:22 -08:00
Rohit P 0f488afa62 fix(sdk): qualify provider flows and graceful budget summaries 2026-11-07 21:14:44 -08:00
Rohit P cfed61057c fix(sdk): regenerate policy-blocked signed tool batches safely 2026-11-07 20:55:49 -08:00
Rohit P 1dcaeaa4b9 feat(sdk): expose safe attempt streams and provider diagnostics 2026-11-07 20:54:33 -08:00
Rohit P 8cda95eab8 feat(sdk): add turn context, history import and explicit session tools 2026-11-07 20:53:19 -08:00
Rohit P 6c40f67ad6 feat(sdk): preserve Gemini signatures across streamed tool conversations 2026-11-07 20:51:16 -08:00
Rohit P 444d209191 fix(runtime): reject reused tool call IDs before dispatch 2026-11-07 20:50:26 -08:00
Rohit P 6b90a32245 feat(sdk): enable configurable Anthropic prompt caching 2026-11-07 20:42:02 -08:00
Rohit P 6c6b98b70f fix(sdk): report streaming usage and preserve tool activity context 2026-11-07 20:35:01 -08:00
Rohit P a213efe22e Support user-wide skill installation and simplify install commands 2026-11-06 17:38:28 -08:00
Rohit Prasad 1bdb1be02f Prepare OpenWorker SDK and app-building skills for npm (#847)
Rename the SDK to `@openworkerai/harness-sdk` and update its matching runtime packages. Add `@openworkerai/build-with-sdk-skills` so developers can install Desktop and Web app guidance for Codex or Claude Code without cloning this repository.

Update the examples and documentation. Fix Windows release archives and dependency setup on clean runners, and qualify native packages in release mode.

Local package and skill installation, the streamed Desktop example, and native release tests passed on macOS ARM64. npm publication is handled separately.
2026-11-06 14:28:38 -08:00
Rohit PrasadandDevika Verma d53e058eda Introduce OpenWorker Harness SDK (in beta), agent service cluster and relevant developer documentation (#844)
Allow developers to easily build AI apps without worrying about the harness part.
Bundles the Rust agent runtime as a SDK (Rust and TypeScript) for building desktop and web applications. Applications can manage a local harness or connect to an authenticated harness service on k8s with separately scaled workers and sandbox execution.

The implementation is primarily contained in harness/, with deployment tooling in deploy/, Markdown guides in docs/harness/guides/, and the static documentation site in docs-site/. It does not replace the existing Python harness or migrate OpenWorker Desktop.

Co-authored-by: Devika Verma <devikaverma11@gmail.com>
2026-11-06 09:45:20 -08:00
Devika Verma eeb3c04d91 fix(gui): the turn summary counts changes that worked, and pairs results by call id (OPE-238)
Review of the first version against 366 recorded runs found four defects and one
semantic gap, all fixed here.

- Two same-named calls in one batch swapped results, exit codes, origins and audit
  links in the live view: the finished event was matched to the LAST pending item by
  name. `tool_proposed` now carries the tool call id and the GUI matches on it.
- A command's exit status was read from the 300-character result preview; a long
  command pushed it out, and a timed-out command showed a green dot. The exit code,
  time-out and background flags now ride on `tool_finished` and on the persisted
  display sidecar.
- After a reload every non-denied call replayed as "ok", so a failed write showed as
  done. The status is persisted with the result and replayed.
- A notice inside a turn (compaction, continuation, a saved memory) split the summary
  in two and showed the first half while the turn was still running. One block per
  turn now, emitted after the answer.

The header reads "N changes auto-approved" and the count means "things that changed
state and that nobody approved": the engine stamps each cardless call's effect
("change" or "read", from its risk class and tier) and the summary counts failed
attempts and read-only actions apart. Several edits of one file collapse into one row;
background commands are labelled; after 25 rows the list offers the rest.

`turn_summary` gains `failed` and `reads`, and per-action effect, tier and shell
outcome; docs/headless.md describes the fields.
2026-10-29 14:08:30 +05:30
Devika Verma c3c813349b feat(gui): show the changes auto-approve made without asking, at the end of a turn (OPE-238)
A user who was away had no simple view of what ran with no approval card. After a
turn in which auto-approve let actions through (a gate tier or a reviewer "allow"),
the transcript now ends the turn with a collapsed "N changes made without asking"
block: file changes with diffs, commands with their exit status, other actions,
each with who let it through and a link to its audit rows.

- engine: one TURN_SUMMARY event just before the event that ends the turn, listing
  tool call id, tool, origin, status and the reviewer's reason (no arguments).
  Wraps run / retry / resume; closing the wrapper closes the turn as before.
- audit: /v1/audit takes call_id; Activity opens filtered to one call, clearable.
- gui: tool items carry their call id, live and on reload; the block is built from
  the persisted approval origins, so a reloaded session shows the same summary.
- docs/headless.md: the event in events.jsonl.
2026-10-29 14:08:30 +05:30
Devika Verma f44f760dbc feat(permissions): secret-looking data leaving the machine always needs a person (OPE-236)
Whether a model declines to upload a .env file is model behaviour, not policy,
and OpenWorker lets users pick any model. A new floor, placed with the other
human-only floors (ahead of every allowlist, the allowed-sites wall and the
reviewer): an action that sends data off the machine (egress or external risk:
web tools, connector writes, MCP tools; or a shell command running a network
client) AND names a secret-looking file (.env*, *.pem, id_rsa*, credentials*,
*token*, ...) or carries a secret-looking value (private-key headers, sk-,
AKIA, ghp_, xox?- shapes, api_key = <long value>) is human-only in every
asking mode and in bypass-approvals; dangerous-bypass clears it and records
the floor. Templates and public keys (.env.example, *.sample, *.pub) are not
secrets. A backstop on top of the sandbox network allowlist: shell egress
can't be recognised completely.

Corpora: gate-104 (browser upload of an SSH key) moves from reviewer_eligible
to human_only (secure stays hard_deny); four secret-egress gate rows are
appended (gate-133..136). Seven frozen legacy reviewer rows the floor now
intercepts (danger-003/010, inject-001/002/008/014/016) stay as they are; the
hygiene test lists them explicitly and checks they're caught by this floor.
Docs: the floor joins the safety-check list; the Windows sandbox page notes
what "Allow everything" leaves to the approval flow.
2026-10-29 11:24:12 +05:30
Rohit C Prasad 4578be6457 Merge remote-tracking branch 'origin/main' into feat/llamacpp-guided-setup 2026-10-26 12:28:24 -07:00
Rohit C Prasad 5ff7db1752 Merge remote-tracking branch 'origin/main' into feat/azure-openai-card
# Conflicts:
#	README.md
#	surfaces/gui/src/components/ManageTabs.tsx
2026-10-26 12:01:37 -07:00
Rohit C Prasad be78567c83 Screenshots of the custom provider box and the local server rows
Light and dark, for the PR and the docs.
2026-10-26 11:25:33 -07:00
Rohit C Prasad c7dacc92dc Screenshots of the llama.cpp setup
Light and dark: the three steps, the model picker, the running card.
2026-10-26 11:24:36 -07:00
Rohit C Prasad 8e8455f5a7 Screenshots of the Azure OpenAI provider
Light and dark, for the PR and the docs.
2026-10-26 11:17:17 -07:00
Rohit C Prasad db6e0af7eb Add Jan, Docker Model Runner and mlx-lm as local server providers
Same shape as llama.cpp/vLLM/LM Studio: address + optional key, models from the server.
Docker's /engines path is added when the user types the root; mlx-lm's help covers the port shared with llama.cpp.
Local-server checks now read LOCAL_SERVERS instead of a hand-kept tuple.
2026-10-26 11:10:29 -07:00
Rohit C Prasad c07f8096a3 Screenshots of the LM Studio provider
Light and dark, for the PR and the docs.
2026-10-25 20:55:44 -07:00
Rohit C Prasad 45d58dc9a5 Add LM Studio as a local server provider
Joins llama.cpp and vLLM: address + optional key, window from its own listing.
Based on #434 by zalex666: name, model and help text.
2026-10-25 20:55:44 -07:00
Rohit C Prasad aa9a6f9bba Screenshots of the Customization tab
Light and dark, for the PR and the docs.
2026-10-25 19:38:29 -07:00
Rohit C Prasad 535467a4d2 Point the web_search_provider notes at Settings > Customization 2026-10-25 19:06:58 -07:00
Rohit C Prasad d55ca63097 Register You.com with the site wall and make key handling uniform
Both You.com hosts join PROVIDER_HOSTS (keyed vs keyless) and the Sites catalogue; the YDC_API_KEY fallback moves to key resolution.
Every provider declares key_mode none/optional/required beside display_name and key_url.
2026-10-25 16:28:18 -07:00
Rohit C Prasad c59c288fe3 Register Firecrawl with the site wall
Firecrawl's host joins PROVIDER_HOSTS and the Access ▸ Sites catalogue.
The class gets display_name and key_url and raises on HTTP errors like the others.
2026-10-25 16:25:35 -07:00
Rohit C Prasad cb49df3644 Register Exa with the site wall
Exa's host joins PROVIDER_HOSTS and the Access ▸ Sites catalogue.
The class gets display_name and key_url and raises on HTTP errors like the others.
2026-10-25 16:24:17 -07:00
Rohit C Prasad 2a19c61345 Register Serper with the site wall and name every provider
Serper's host joins PROVIDER_HOSTS and the Access ▸ Sites catalogue.
Every provider carries display_name and key_url; keyed ones raise on HTTP errors.
2026-10-25 16:22:10 -07:00
Rohit C Prasad 70cd9c731a docs: add cloud_machines_base to config example
Matches the default in coworker/config.py.
2026-10-25 15:13:50 -07:00
ayobamiseun d76f29ee16 docs: document web_search_provider and cloud_* keys in config example
config.example.toml covered 7 of the 13 supported keys; a user reading it
could not discover how to switch web-search providers or point a dev/BYO
deployment at its own cloud instance. Adds web_search_provider (with the
three supported backends) and the cloud_* family (commented out — the
defaults are the production values, and an empty cloud_relay_ws_url
meaningfully disables the relay). Also notes the Windows global config
location and that allowed_commands/auto_allow are global-only until
workspace trust.

Verified: the example parses with tomllib and every key (including the
commented cloud_* names) matches coworker.config._FIELDS.
2026-10-25 15:13:32 -07:00
Devika Verma a952d5463b run: --no-web-tools keeps web_search and web_fetch out of the tool list (OPE-226)
For sealed evaluation runs and air-gapped work. A network block only refuses the call: the model still sees both tools, can spend turns on them, and the record cannot say they were absent. The flag withholds them at registration (build_engine(web_tools=False)), and summary.json and the trajectory record web_tools: false. Without the flag nothing changes.

Tests: with the flag both calls get the engine's unknown-tool answer and the record says false; without it web_fetch is present, shown with a non-URL the tool rejects before any network I/O.
2026-10-20 17:35:20 +05:30
Devika Verma 514c0beb37 llama.cpp and vLLM as providers
Each is a provider of its own with an address and an optional key; the served model, its window and tool support are read from the server (vLLM is probed for tool calling).
Providers carry a kind (local, subscription, api_key) for the settings page; docs/local-servers.md.
2026-10-05 19:49:34 -07:00
Devika Verma 83131c0a6f Per-model settings and a recommended-settings table
model_config.json holds context size, longest reply, thinking, sampling, auto-compact and the default model; the app's API and the CLI read it.
recommended_models.json carries the makers' own values per model, with sources; docs/model-settings.md explains both.
2026-10-05 19:49:34 -07:00
Rohit C Prasad 857e4e7b29 The openworker program for the Mac
build_macos_cli.sh freezes the CLI, signs and notarizes it; the release attaches it for arm64 and x86_64.
install.sh downloads it on a Mac instead of the Python package.
2026-10-05 15:28:03 -07:00
Rohit C Prasad 9de6b83c7f run: retry a failed model call after 2 s, then back off
Waits are now 2, 5, 10, 30, 60, 120, 240, 300, 300 s; the first was 30 s.
One dropped connection no longer costs half a minute.
2026-10-05 11:20:53 -07:00
Rohit C Prasad 00ebf7979f Publish the CLI image to GitHub's container registry
A workflow builds it for Intel and ARM, checks it, and pushes ghcr.io/andrewyng/openworker.
Runs when a release is published, or by hand.
2026-10-05 10:10:05 -07:00
Rohit C Prasad 09dc46575a Inside OpenShell, ask about a blocked site and wait
With a person at the terminal the coworker asks, they allow the site from outside, and it tries again.
With auto-answer it reports the block in its answer, as before.
2026-10-05 06:23:01 -07:00
Rohit C Prasad a2b0225580 Inside OpenShell: the allow-a-site command the agent gives is the whole command
On OpenShell 0.1.2 a rule added without --binary lets no program through.
The doc says a --no-keep run cannot be changed after it ends.
2026-10-05 05:45:16 -07:00