Commit Graph
118 Commits
Author SHA1 Message Date
Rohit P cc347f14f1 Add runtime integrations and session policies 2026-11-18 18:22:51 -08:00
Rohit P 8f7138349a feat: add InspectionBuddy edge sample with local setup 2026-11-16 14:58:54 -08:00
Rohit Prasad ecb445490f Merge pull request #898 from andrewyng/docs/desktop-getting-started
Add Desktop App docs
2026-11-13 16:34:18 -08:00
Rohit Prasad f68159ee2d Merge pull request #896 from andrewyng/docs/sdk-launch-guides
Update SDK docs and quickstart examples
2026-11-13 16:33:52 -08:00
Rohit P ad61ed95a9 Keep the cluster recording instructions in the guide 2026-11-13 16:07:35 -08:00
Rohit P b3799eed13 Fix guide example compilation and cancellation race 2026-11-13 15:16:44 -08:00
Rohit P f1daf75245 Merge verified SDK fixes into cluster qualification 2026-11-13 15:07:58 -08:00
Rohit P 38df9f7e4a Add Desktop App docs 2026-11-13 14:49:14 -08:00
Rohit P 6877196b11 Merge main and preserve combined SDK release behavior 2026-11-13 14:19:56 -08:00
Rohit Prasad 8c99b01e1d Merge pull request #893 from andrewyng/feat/owcluster-cli
Rename the cluster CLI to owcluster
2026-11-13 14:17:04 -08:00
Rohit Prasad bf754ba57d Merge pull request #890 from andrewyng/fix/sdk-activity-metadata
Show tool names and arguments in SDK activity
2026-11-13 14:15:26 -08:00
Rohit P 95d175a2c7 fix: preserve private installation access and recording schema setup 2026-11-13 12:38:44 -08:00
Rohit P abcbeadc84 Add CLI controls for management UI and trace storage 2026-11-13 12:38:44 -08:00
Rohit P 59a17fc9a5 feat: use owcluster with a compatible ows alias 2026-11-13 11:38:12 -08:00
Rohit P 164acdbb12 fix: expose approval decisions and safe denial context 2026-11-13 11:20:51 -08:00
Rohit P 5335949545 fix: expose tool activity names and arguments 2026-11-13 11:06:19 -08:00
Rohit P a6a8c9b886 Fix SDK errors for conflicting agent definitions 2026-11-13 10:57:58 -08:00
Rohit P 9f7a2e18a4 Keep release versions in compatibility documentation 2026-11-13 09:46:55 -08:00
Rohit P 5dd216d8b0 Refresh SDK guides and published-package examples 2026-11-13 07:49:51 -08:00
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