Commit Graph

3782 Commits

Author SHA1 Message Date
YeonGyu-Kim 9b8aca45f9 fix(release): set version when publishing oh-my-openagent
The publish step was updating name and optionalDependencies but not
version, causing npm to try publishing the base package.json version
(3.11.0) instead of the release version (3.12.0).

Error was: 'You cannot publish over the previously published versions: 3.11.0'
2026-03-18 02:15:15 +09:00
YeonGyu-Kim f1f20f5a79 Merge pull request #2650 from code-yeongyu/fix/openagent-platform-publish
fix(release): add oh-my-openagent dual-publish to platform and main workflows
2026-03-18 01:55:31 +09:00
YeonGyu-Kim de40caf76d fix(release): add oh-my-openagent dual-publish to platform and main workflows
- publish-platform.yml: Build job now checks BOTH oh-my-opencode and
  oh-my-openagent before skipping. Build only skips when both are published.
  Added 'Publish oh-my-openagent-{platform}' step that renames package.json
  and publishes under the openagent name.

- publish.yml: Added 'Publish oh-my-openagent' step after opencode publish.
  Rewrites package name and optionalDependencies to oh-my-openagent variants,
  then publishes. Restores package.json after.

Previously, oh-my-openagent platform packages were never published because
the build skip check only looked at oh-my-opencode (which was already published),
causing the entire build to be skipped.
2026-03-18 01:45:02 +09:00
github-actions[bot] d80833896c @HaD0Yun has signed the CLA in code-yeongyu/oh-my-openagent#2640 2026-03-17 08:27:56 +00:00
YeonGyu-Kim d50c38f037 refactor(tests): rename benchmarks/ to tests/hashline/, remove FriendliAI dependency
- Move benchmarks/ → tests/hashline/
- Replace @friendliai/ai-provider with @ai-sdk/openai-compatible
- Remove all 'benchmark' naming (package name, scripts, env vars, session IDs)
- Fix import paths for new directory depth (../src → ../../src)
- Fix pre-existing syntax error in headless.ts (unclosed case block)
- Inject HASHLINE_EDIT_DESCRIPTION into test system prompt
- Scripts renamed: bench:* → test:*
2026-03-17 16:47:13 +09:00
YeonGyu-Kim f2d5f4ca92 improve(hashline-edit): rewrite tool description with examples and fix lines schema
- Add XML-structured description (<must>, <operations>, <examples>, <auto>)
- Add 5 concrete examples including BAD pattern showing duplication
- Add explicit anti-duplication warning for range replace
- Move snapshot rule to top-level <must> section
- Clarify batch semantics (multiple ops, not one big replace)
- Fix lines schema: add string[] to union (was string|null, now string[]|string|null)
- Matches runtime RawHashlineEdit type and description text
2026-03-17 16:47:13 +09:00
YeonGyu-Kim b788586caf relax task timeouts: stale timeout 3min→20min, session wait 30s→1min 2026-03-17 16:47:13 +09:00
YeonGyu-Kim 90351e442e update look_at tool description to discourage visual precision use cases 2026-03-17 16:47:13 +09:00
YeonGyu-Kim 4ad88b2576 feat(task-toast): show model name before category in toast notification
Display resolved model ID (e.g., gpt-5.3-codex: deep) instead of
agent/category format when modelInfo is available. Falls back to
old format when no model info exists.
2026-03-17 16:47:13 +09:00
YeonGyu-Kim 2ce69710e3 docs: sync agent-model-matching guide with actual fallback chains
- Metis: add missing GPT-5.4 high as 2nd fallback
- Hephaestus: add GPT-5.4 (Copilot) fallback, was incorrectly listed as Codex-only
- Oracle: add opencode-go/glm-5 as last fallback
- Momus: add opencode-go/glm-5 fallback, note xhigh variant
- Atlas: add GPT-5.4 medium as 3rd fallback
- Sisyphus: add Kimi K2.5 (moonshot providers) in chain
- Sisyphus-Junior: add missing agent to Utility Runners section
- GPT Family table: merge duplicate GPT-5.4 rows
- Categories: add missing opencode-go intermediate fallbacks for
  visual-engineering, ultrabrain, quick, unspecified-low/high, writing
2026-03-17 16:47:13 +09:00
YeonGyu-Kim 0b4d092cf6 Merge pull request #2639 from code-yeongyu/feature/2635-smart-circuit-breaker
feat(background-agent): add smart circuit breaker for repeated tool calls
2026-03-17 16:43:08 +09:00
YeonGyu-Kim 53285617d3 Merge pull request #2636 from code-yeongyu/fix/pre-publish-blockers
fix: resolve 12 pre-publish blockers (security, correctness, migration)
2026-03-17 16:36:04 +09:00
YeonGyu-Kim ae3befbfbe fix(background-agent): apply smart circuit breaker to manager events
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-17 16:31:55 +09:00
YeonGyu-Kim dc1a05ac3e feat(background-agent): add loop detector helpers
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-17 16:31:55 +09:00
YeonGyu-Kim e271b4a1b0 feat(config): add background task circuit breaker settings
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-17 16:31:55 +09:00
YeonGyu-Kim fee938d63a fix(cli): cherry-pick glm-4.7-free → gpt-5-nano fallback fix from dev 2026-03-17 16:30:12 +09:00
YeonGyu-Kim 4d74d888e4 Merge pull request #2637 from code-yeongyu/fix/ulw-verification-session-tracking
fix(ulw-loop): add fallback for Oracle verification session tracking
2026-03-17 16:25:28 +09:00
YeonGyu-Kim 4bc7b1d27c fix(ulw-loop): add fallback for Oracle verification session tracking
The verification_session_id was never reliably set because the
prompt-based attempt_id matching in tool-execute-after depends on
metadata.prompt surviving the delegate-task execution chain. When
this fails silently, the loop never detects Oracle's VERIFIED
emission.

Add a fallback: when exact attempt_id matching fails but oracle
agent + verification_pending state match, still set the session ID.
Add diagnostic logging to trace verification flow failures.
Add integration test covering the full verification chain.
2026-03-17 16:21:40 +09:00
YeonGyu-Kim 78dac0642e Merge pull request #2590 from MoerAI/fix/subagent-circuit-breaker
fix(background-agent): add circuit breaker to prevent subagent infinite loops (fixes #2571)
2026-03-17 16:09:29 +09:00
YeonGyu-Kim 92bc72a90b fix(bun-install): use workspaceDir option instead of hardcoded cache-dir 2026-03-17 16:05:51 +09:00
YeonGyu-Kim a7301ba8a9 fix(delegate-task): guard skipped sentinel in subagent-resolver 2026-03-17 15:57:23 +09:00
YeonGyu-Kim e9887dd82f fix(doctor): align auto-update and doctor config paths 2026-03-17 15:56:02 +09:00
YeonGyu-Kim c0082d8a09 Merge pull request #2634 from code-yeongyu/fix/run-in-background-required
fix(delegate-task): remove auto-default for run_in_background, require explicit parameter
2026-03-17 15:55:17 +09:00
YeonGyu-Kim fbc3b4e230 Merge pull request #2612 from MoerAI/fix/dead-fallback-model
fix(cli): replace dead glm-4.7-free with gpt-5-nano as ultimate fallback (fixes #2101)
2026-03-17 15:53:29 +09:00
YeonGyu-Kim 1f7fdb43ba Merge pull request #2539 from cpkt9762/fix/category-variant-no-requirement
fix(delegate-task): build categoryModel with variant for categories without fallback chain
2026-03-17 15:53:11 +09:00
YeonGyu-Kim 566031f4fa fix(delegate-task): remove auto-default for run_in_background, require explicit parameter
Remove the auto-defaulting logic from PR #2420 that silently set
run_in_background=false when category/subagent_type/session_id was present.

The tool description falsely claimed 'Default: false' which misled agents
into omitting the parameter. Now the description says REQUIRED and the
validation always throws when the parameter is missing, with a clear
error message guiding the agent to retry with the correct value.

Reverts the behavioral change from #2420 while keeping the issue's
root cause (misleading description) fixed.
2026-03-17 15:49:47 +09:00
YeonGyu-Kim 0cf386ec52 fix(skill-tool): invalidate cached skill description on execute 2026-03-17 15:49:26 +09:00
YeonGyu-Kim d493f9ec3a fix(cli-run): move resolveRunModel inside try block 2026-03-17 15:49:26 +09:00
YeonGyu-Kim 2c7ded2433 fix(background-agent): defer task cleanup while siblings running 2026-03-17 15:17:34 +09:00
YeonGyu-Kim 82c7807a4f fix(event): clear retry dedupe key on non-retry status 2026-03-17 15:17:34 +09:00
YeonGyu-Kim df7e1ae16d fix(todo-continuation): remove activity-based stagnation bypass 2026-03-17 15:17:34 +09:00
YeonGyu-Kim 0471078006 fix(tmux): escape serverUrl in pane shell commands 2026-03-17 15:16:54 +09:00
YeonGyu-Kim 1070b9170f docs: remove temporary injury notice from README 2026-03-17 10:41:56 +09:00
acamq bb312711cf Merge pull request #2618 from RaviTharuma/fix/extract-status-code-nested-errors
fix(runtime-fallback): extract status code from nested AI SDK errors
2026-03-16 16:28:31 -06:00
github-actions[bot] c31facf41e @gxlife has signed the CLA in code-yeongyu/oh-my-openagent#2625 2026-03-16 15:17:21 +00:00
Ravi Tharuma de66f1f397 fix(runtime-fallback): prefer numeric status codes over non-numeric in extraction chain
The nullish-coalescing chain could stop at a non-numeric value (e.g.
status: "error"), preventing deeper nested numeric statusCode values
from being reached. Switch to Array.find() with a type guard to always
select the first numeric value.

Adds 11 tests for extractStatusCode covering: top-level, nested
(data/error/cause), non-numeric skip, fallback to regex, and
precedence.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 13:51:23 +01:00
YeonGyu-Kim 427fa6d7a2 Merge pull request #2619 from code-yeongyu/revert/openclaw-one-way
revert: remove one-way OpenClaw integration
2026-03-16 21:09:30 +09:00
YeonGyu-Kim 239da8b02a Revert "Merge pull request #2607 from code-yeongyu/feat/openclaw-integration"
This reverts commit 8213534e87, reversing
changes made to 84fb1113f1.
2026-03-16 21:09:08 +09:00
YeonGyu-Kim 17244e2c84 Revert "Merge pull request #2609 from code-yeongyu/fix/rename-omx-to-omo-env"
This reverts commit 4759dfb654, reversing
changes made to 8213534e87.
2026-03-16 21:09:08 +09:00
Ravi Tharuma 24a0f7b032 fix(runtime-fallback): extract status code from nested AI SDK errors
AI SDK wraps HTTP status codes inside error.error.statusCode (e.g., AI_APICallError). The current extractStatusCode only checks the top level, missing these nested codes.

This caused runtime-fallback to skip retryable errors like 400, 500, 504 because it couldn't find the status code.

Fixes #2617
2026-03-16 13:04:14 +01:00
MoerAI fc48df1d53 fix(cli): replace dead glm-4.7-free with gpt-5-nano as ultimate fallback
The opencode/glm-4.7-free model was removed from the OpenCode platform,
causing the ULTIMATE_FALLBACK in the CLI installer to point to a dead
model. Users installing OMO without any major provider configured would
get a non-functional model assignment.

Replaced with opencode/gpt-5-nano which is confirmed available per
user reports and existing fallback chains in model-requirements.ts.

Fixes #2101
2026-03-16 19:21:10 +09:00
YeonGyu-Kim 4759dfb654 Merge pull request #2609 from code-yeongyu/fix/rename-omx-to-omo-env
fix: rename OMX_OPENCLAW env vars to OMO_OPENCLAW
2026-03-16 18:47:50 +09:00
YeonGyu-Kim 2c8813e95d fix: rename OMX_OPENCLAW env vars to OMO_OPENCLAW
Renames all environment variable gates from the old oh-my-codex (OMX) prefix
to the correct oh-my-openagent (OMO) prefix:

- OMX_OPENCLAW -> OMO_OPENCLAW
- OMX_OPENCLAW_COMMAND -> OMO_OPENCLAW_COMMAND
- OMX_OPENCLAW_DEBUG -> OMO_OPENCLAW_DEBUG
- OMX_OPENCLAW_COMMAND_TIMEOUT_MS -> OMO_OPENCLAW_COMMAND_TIMEOUT_MS

Adds TDD tests verifying:
- OMO_OPENCLAW=1 is required for activation
- Old OMX_OPENCLAW env var is not accepted
2026-03-16 18:45:34 +09:00
YeonGyu-Kim 8213534e87 Merge pull request #2607 from code-yeongyu/feat/openclaw-integration
feat: implement OpenClaw integration
2026-03-16 17:48:11 +09:00
YeonGyu-Kim 450685f5ea fix: extract session ID from properties.info.id for session.created/deleted events 2026-03-16 17:38:47 +09:00
YeonGyu-Kim 03b346ba51 feat: implement OpenClaw integration
Ports the OMX OpenClaw module into oh-my-openagent as a first-class integration.
This integration allows forwarding internal events (session lifecycle, tool execution) to external gateways (HTTP or command-based).

- Added `src/openclaw` directory with implementation:
  - `dispatcher.ts`: Handles HTTP/Command dispatching with interpolation
  - `types.ts`: TypeScript definitions
  - `client.ts`: Main entry point `wakeOpenClaw`
  - `index.ts`: Public API
- Added `src/config/schema/openclaw.ts` for Zod schema validation
- Updated `src/config/schema/oh-my-opencode-config.ts` to include `openclaw` config
- Added `src/hooks/openclaw-sender/index.ts` to listen for events
- Registered the hook in `src/plugin/hooks/create-session-hooks.ts`
- Added unit tests in `src/openclaw/__tests__`

Events handled:
- `session-start` (via `session.created`)
- `session-end` (via `session.deleted`)
- `session-idle` (via `session.idle`)
- `ask-user-question` (via `tool.execute.before` for `ask_user_question`)
- `stop` (via `tool.execute.before` for `stop-continuation` command)
2026-03-16 17:21:56 +09:00
YeonGyu-Kim 84fb1113f1 chore: add pre-publish blocker tracking document
Add FIX-BLOCKS.md to track critical and high-priority issues

identified in pre-publish reviews.

🤖 GENERATED WITH ASSISTANCE OF OhMyOpenCode
2026-03-16 14:15:36 +09:00
YeonGyu-Kim 90decd1fd4 chore(schema): regenerate schema after hook enum forward-compat change
🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-openagent)
2026-03-16 14:15:36 +09:00
YeonGyu-Kim 47d1ad7bb9 fix(plugin): persist ultrawork variant on same-model override and normalize Claude model IDs
🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-openagent)
2026-03-16 14:15:36 +09:00
YeonGyu-Kim 32a296bf1e fix(auto-slash-command): use event-ID dedup, align precedence, enforce skill agent gate
🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-openagent)
2026-03-16 14:15:36 +09:00