sapient/oh-my-openagent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,867 Commits 54 Branches 176 Tags
ed9b4a632960425a685a146e8caf02b382e670e5
Commit Graph

3867 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
YeonGyu-Kim
ed9b4a6329 Merge pull request #2780 from code-yeongyu/fix/issues-2741-2648-2779 
fix: resolve subagent model override, empty plan completion, deep task refusal (#2741, #2648, #2779)
 2026-03-24 10:28:24 +09:00
YeonGyu-Kim
a00a22ac4c fix: remove copy-paste artifacts in hephaestus gpt-5-3-codex prompt 
Same issue as gpt.ts and gpt-5-4.ts: duplicated CORRECT block with pipe
characters and duplicated Hard Constraints/Task Scope Clarification sections.
 2026-03-24 10:14:53 +09:00
YeonGyu-Kim
8879581fc1 fix: remove copy-paste artifacts in hephaestus GPT prompts 
- Remove leading pipe characters (|) from duplicated CORRECT block
- Remove duplicated ## Hard Constraints and ### Task Scope Clarification sections
- Properly place Task Scope Clarification section between CORRECT list and Hard Constraints

Addresses review comments by cubic-dev-ai[bot] on PR #2780
 2026-03-24 09:57:30 +09:00
YeonGyu-Kim
230ce835e5 fix: resolve 3 bugs - subagent model override, empty plan completion, deep task refusal 
- #2741: Pass inheritedModel as fallback in subagent-resolver when user hasn't
  configured an override, ensuring custom provider models take priority
- #2648: Fix getPlanProgress to treat plans with 0 checkboxes as incomplete
  instead of complete (total > 0 && completed === total)
- #2779: Relax Hephaestus single-task guard to accept multi-step sub-tasks
  from Atlas delegation, only rejecting genuinely independent tasks

Fixes #2741, fixes #2648, fixes #2779
 2026-03-24 09:45:11 +09:00
YeonGyu-Kim
10e56badb3 Merge pull request #2776 from code-yeongyu/fix/background-agent-timeout-defaults 
fix: stabilize background-agent stale timeout tests (Date.now race condition)
 2026-03-24 03:29:35 +09:00
YeonGyu-Kim
cddf78434c Merge pull request #2770 from code-yeongyu/fix/ci-test-timeout 
fix: add fetch mock to install test to prevent CI timeout
 2026-03-24 03:29:23 +09:00
YeonGyu-Kim
0078b736b9 fix: stabilize stale timeout tests with fixed Date.now() 
Tests 'should use default timeout when config not provided' (manager.test.ts)
and 'should use DEFAULT_MESSAGE_STALENESS_TIMEOUT_MS when not configured'
(task-poller.test.ts) failed in CI because Date.now() drifted between
test setup (when creating timestamps like Date.now() - 46*60*1000) and
actual execution inside checkAndInterruptStaleTasks().

On slower CI machines, this drift pushed borderline values across
the threshold, causing tasks that should be stale to remain 'running'.

Fix: Mock Date.now with spyOn to return a fixed time, ensuring
consistent timeout calculations regardless of execution speed.
 2026-03-23 22:17:03 +09:00
MoerAI
6d7f69625b fix: update stale timeout test fixtures for new 45/60 min defaults 2026-03-23 21:00:59 +09:00
MoerAI
fda17dd161 fix(background-agent): increase default stale timeouts and improve cancellation messages (fixes #2684) 2026-03-23 20:49:43 +09:00
YeonGyu-Kim
6e9128e060 fix: add fetch mock to install test to prevent CI timeout 
The first test case 'non-TUI mode: should show warning but continue when
OpenCode binary not found' was missing a globalThis.fetch mock, causing it
to make a real HTTP request to npm registry via fetchNpmDistTags().
The npm fetch timeout (5s) collided with the test timeout (5s), causing
flaky CI failures.

Added the same fetch mock pattern already used by the other two test cases.
Test runtime dropped from 5000ms+ to ~2ms.
 2026-03-23 20:03:45 +09:00
YeonGyu-Kim
331f7ec52b Merge pull request #2768 from code-yeongyu/fix/issue-2117 
fix: emit formatter events from hashline-edit tool (fixes #2117)
 2026-03-23 18:49:10 +09:00
YeonGyu-Kim
4ba2da7ebb fix: add tests and fix typing for formatter trigger (#2768) 2026-03-23 18:46:44 +09:00
YeonGyu-Kim
f95d3b1ef5 fix: emit formatter events from hashline-edit tool (fixes #2117) 2026-03-23 18:40:27 +09:00
YeonGyu-Kim
d5d7c7dd26 Merge pull request #2767 from code-yeongyu/fix/issue-2742 
fix: respect disabled_tools config in agent prompts (fixes #2742)
 2026-03-23 18:39:51 +09:00
YeonGyu-Kim
6a56c0e241 Merge pull request #2766 from code-yeongyu/fix/issue-390 
fix: trigger compaction before continue after session error recovery (fixes #390)
 2026-03-23 18:39:50 +09:00
YeonGyu-Kim
94c234c88c Merge pull request #2765 from code-yeongyu/fix/issue-2024 
fix: skip keyword injection for non-OMO agents (fixes #2024)
 2026-03-23 18:39:48 +09:00
YeonGyu-Kim
2ab976c511 Merge pull request #2764 from code-yeongyu/fix/issue-2624 
fix: add oh-my-openagent.jsonc config file detection (fixes #2624)
 2026-03-23 18:39:46 +09:00
YeonGyu-Kim
dc66088483 Merge pull request #2763 from code-yeongyu/fix/issue-2037 
fix: respect OPENCODE_DISABLE_CLAUDE_CODE env vars (fixes #2037)
 2026-03-23 18:39:45 +09:00
YeonGyu-Kim
67b5f46a7c Merge pull request #2762 from code-yeongyu/fix/issue-2150 
fix: clarify Prometheus file permission error message (fixes #2150)
 2026-03-23 18:39:43 +09:00
YeonGyu-Kim
0e483d27ac Merge pull request #2761 from code-yeongyu/fix/issue-2729 
fix: validate serverUrl port before tmux pane spawn (fixes #2729)
 2026-03-23 18:39:41 +09:00
YeonGyu-Kim
f5eaa648e9 fix: respect disabled_tools config in agent prompts (fixes #2742) 
- Check disabled_tools for 'question' in tool-config-handler permission logic
- Strip Question tool code examples from Prometheus prompts when disabled
- Pass disabled_tools through prometheus agent config builder pipeline
- Add tests for disabled_tools question permission handling
 2026-03-23 18:13:38 +09:00
YeonGyu-Kim
4c4760a4ee fix: trigger compaction before continue after session error recovery (fixes #390) 2026-03-23 18:12:51 +09:00
YeonGyu-Kim
7f20dd6ff5 fix: add oh-my-openagent.jsonc config file detection (fixes #2624) 2026-03-23 18:11:01 +09:00
YeonGyu-Kim
de371be236 fix: skip keyword injection for non-OMO agents (fixes #2024) 2026-03-23 18:10:44 +09:00
YeonGyu-Kim
f3c2138ef4 fix: respect OPENCODE_DISABLE_CLAUDE_CODE env vars (fixes #2037) 2026-03-23 18:10:08 +09:00
YeonGyu-Kim
0810e37240 fix: validate serverUrl port before tmux pane spawn (fixes #2729) 2026-03-23 18:09:31 +09:00
YeonGyu-Kim
a64e364fa6 fix: clarify Prometheus file permission error message (fixes #2150) 2026-03-23 18:07:59 +09:00
github-actions[bot]
d886ac701f @hunghoang3011 has signed the CLA in code-yeongyu/oh-my-openagent#2758 2026-03-23 04:28:31 +00:00
github-actions[bot]
30dc50d880 @0xYiliu has signed the CLA in code-yeongyu/oh-my-openagent#2738 2026-03-21 23:05:07 +00:00
github-actions[bot]
b17e633464 @ndaemy has signed the CLA in code-yeongyu/oh-my-openagent#2734 2026-03-21 10:18:31 +00:00
YeonGyu-Kim
eec268ee42 fix: use find() instead of calls[0] in wakeGateway test to handle background fetch calls 2026-03-21 18:01:39 +09:00
github-actions[bot]
363661c0d6 @whackur has signed the CLA in code-yeongyu/oh-my-openagent#2733 2026-03-21 05:27:27 +00:00
github-actions[bot]
261bbdf4dc @nguyentamdat has signed the CLA in code-yeongyu/oh-my-openagent#2718 2026-03-20 07:34:31 +00:00
YeonGyu-Kim
8aec4c5cb3 feat(hooks/todo-continuation-enforcer): enhance continuation message with skeptical verification guidance 2026-03-20 16:13:02 +09:00
YeonGyu-Kim
16cbc847ac fix(cli/run): set OPENCODE_CLIENT to 'run' to exclude question tool from registry 2026-03-20 16:12:58 +09:00
YeonGyu-Kim
436ce71dc8 docs(skills/github-triage): fix Phase 1 JSON parsing and large repo handling 2026-03-20 16:12:54 +09:00
github-actions[bot]
d2a49428b9 @tonymfer has signed the CLA in code-yeongyu/oh-my-openagent#2701 2026-03-19 17:14:04 +00:00
github-actions[bot]
c3b23bf603 @trafgals has signed the CLA in code-yeongyu/oh-my-openagent#2690 2026-03-19 04:22:43 +00:00
YeonGyu-Kim
50094de73e docs: fix remaining AGENTS hook composition text 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-03-19 12:02:52 +09:00
YeonGyu-Kim
3aa2748c04 docs: sync hook counts after continuation hook removal 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-03-19 12:02:52 +09:00
YeonGyu-Kim
ccaf759b6b fix(hooks): remove gpt permission continuation hook 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-03-19 12:02:52 +09:00
YeonGyu-Kim
521a1f76a9 fix(atlas): stop only after 10 consecutive prompt failures 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-03-19 12:02:52 +09:00
github-actions[bot]
490f0f2090 @walioo has signed the CLA in code-yeongyu/oh-my-openagent#2688 2026-03-19 02:35:04 +00:00
YeonGyu-Kim
caf595e727 fix(build-binaries): prevent test imports from triggering binary builds 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-03-19 10:47:33 +09:00
YeonGyu-Kim
1f64a45113 Merge pull request #2620 from code-yeongyu/feat/openclaw-bidirectional 
feat: port OpenClaw bidirectional integration from omx
 2026-03-19 10:47:07 +09:00
YeonGyu-Kim
9b2dc2189c fix(ralph-loop): detect promise tags in tool_result parts for ulw verification 
Oracle's <promise>VERIFIED</promise> arrives as a tool_result part from the
task() tool call, not as a text part. Both detectCompletionInSessionMessages
and collectAssistantText only scanned type=text parts, missing the
verification signal entirely. This caused ulw loops to fail verification
even when Oracle successfully emitted VERIFIED.

Include tool_result parts in promise detection alongside text parts.
Exclude tool_use parts to avoid false positives from instructional text.
 2026-03-18 19:09:59 +09:00
YeonGyu-Kim
f6c24e42af fix(ralph-loop): detect promise tags in tool_result parts for ulw verification 
Oracle's <promise>VERIFIED</promise> arrives as a tool_result part from the
task() tool call, not as a text part. Both detectCompletionInSessionMessages
and collectAssistantText only scanned type=text parts, missing the
verification signal entirely. This caused ulw loops to fail verification
even when Oracle successfully emitted VERIFIED.

Include tool_result parts in promise detection alongside text parts.
Exclude tool_use parts to avoid false positives from instructional text.
 2026-03-18 19:03:30 +09:00
YeonGyu-Kim
22fd976eb9 feat(categories): change quick category default model from claude-haiku-4-5 to gpt-5.4-mini 
GPT-5.4-mini provides stronger reasoning at comparable speed and cost.
Haiku remains as the next fallback priority in the chain.

Changes:
- DEFAULT_CATEGORIES quick model: anthropic/claude-haiku-4-5 → openai/gpt-5.4-mini
- Fallback chain: gpt-5.4-mini → haiku → gemini-3-flash → minimax-m2.5 → gpt-5-nano
- OpenAI-only catalog: quick uses gpt-5.4-mini directly
- Think-mode: add gpt-5-4-mini and gpt-5-4-nano high variants
- Update all documentation references
 2026-03-18 19:03:30 +09:00
YeonGyu-Kim
826284f3d9 Merge pull request #2676 from code-yeongyu/fix/atlas-task-session-review-followup 
fix(atlas): address review findings for task session reuse
 2026-03-18 18:50:45 +09:00
YeonGyu-Kim
3c7e6a3940 fix(atlas): address review findings for task session reuse 2026-03-18 18:44:42 +09:00