Commit Graph

2356 Commits

Author SHA1 Message Date
YeonGyu-Kim
67efe2d7af test: verify provider setup runs for openai/copilot without gemini 2026-02-16 15:23:22 +09:00
YeonGyu-Kim
abfab1a78a enhance: calibrate Prometheus plan granularity to 5-8 parallel tasks per wave
Add Maximum Parallelism Principle as a top-level constraint and replace
small-scale plan template examples (6 tasks, 3 waves) with production-scale
examples (24 tasks, 4 waves, max 7 concurrent) to steer the model toward
generating fine-grained, dependency-minimized plans by default.
2026-02-16 15:14:25 +09:00
sisyphus-dev-ai
1509c897fc chore: changes by sisyphus-dev-ai 2026-02-16 05:09:17 +00:00
YeonGyu-Kim
dd91a7d990 Merge pull request #1874 from code-yeongyu/fix/toast-manager-ghost-entries
fix: add toast cleanup to all BackgroundManager task removal paths
2026-02-16 13:54:01 +09:00
YeonGyu-Kim
a9dd6d2ce8 Merge pull request #1873 from code-yeongyu/fix/first-message-variant-override
fix: preserve user-selected variant on first message instead of overriding with fallback chain default
2026-02-16 13:51:38 +09:00
YeonGyu-Kim
33d290b346 fix: add toast cleanup to all BackgroundManager task removal paths
TaskToastManager entries were never removed when tasks completed via
error, session deletion, stale pruning, or cancelled with
skipNotification. Ghost entries accumulated indefinitely, causing the
'Queued (N)' count in toast messages to grow without bound.

Added toastManager.removeTask() calls to all 4 missing cleanup paths:
- session.error handler
- session.deleted handler
- cancelTask with skipNotification
- pruneStaleTasksAndNotifications

Closes #1866
2026-02-16 13:50:57 +09:00
YeonGyu-Kim
7108d244d1 fix: preserve user-selected variant on first message instead of overriding with fallback chain default
First message variant gate was unconditionally overwriting message.variant
with the fallback chain value (e.g. 'medium' for Hephaestus), ignoring
any variant the user had already selected via OpenCode UI.

Now checks message.variant === undefined before applying the resolved
variant, matching the behavior already used for subsequent messages.

Closes #1861
2026-02-16 13:44:54 +09:00
github-actions[bot]
418e0e9f76 @dankochetov has signed the CLA in code-yeongyu/oh-my-opencode#1870 2026-02-15 23:17:14 +00:00
github-actions[bot]
b963571642 @Decrabbityyy has signed the CLA in code-yeongyu/oh-my-opencode#1864 2026-02-15 15:07:23 +00:00
github-actions[bot]
18442a1637 release: v3.5.5 v3.5.5 2026-02-15 05:48:47 +00:00
YeonGyu-Kim
d076187f0a test(cli): update model-fallback snapshots for kimi k2.5 and gemini-3-pro changes 2026-02-15 14:45:51 +09:00
YeonGyu-Kim
8a5f61724d fix(background-agent): handle message.part.delta for heartbeat (OpenCode >=1.2.0)
OpenCode 1.2.0+ changed reasoning-delta and text-delta to emit
'message.part.delta' instead of 'message.part.updated'. Without
handling this event, lastUpdate was only refreshed at reasoning-start
and reasoning-end, leaving a gap where extended thinking (>3min)
could trigger stale timeout.

Accept both event types as heartbeat sources for forward compatibility.
2026-02-15 14:26:25 +09:00
YeonGyu-Kim
3f557e593c fix(background-agent): use correct OpenCode session status for stale guard
OpenCode uses 'busy'/'retry'/'idle' session statuses, not 'running'.
The stale timeout guard checked for type === 'running' which never
matched, leaving all background tasks vulnerable to stale-kill even
when their sessions were actively processing.

Change sessionIsRunning to check type !== 'idle' instead, protecting
busy and retrying sessions from premature termination.
2026-02-15 14:24:45 +09:00
YeonGyu-Kim
284fafad11 feat(writing): switch primary model to kimi k2.5, add anti-AI-slop rules to prompt 2026-02-15 14:00:03 +09:00
YeonGyu-Kim
884a3addf8 feat(visual-engineering): add variant high to gemini-3-pro, update fallback chain to gemini→glm-5→opus→kimi 2026-02-15 13:59:00 +09:00
github-actions[bot]
c8172697d9 release: v3.5.4 v3.5.4 2026-02-15 04:40:15 +00:00
YeonGyu-Kim
6dc8b7b875 fix(ci): sync publish.yml test steps with ci.yml to prevent mock pollution 2026-02-15 13:37:25 +09:00
github-actions[bot]
361d9a82d7 @iyoda has signed the CLA in code-yeongyu/oh-my-opencode#1845 2026-02-14 19:58:31 +00:00
github-actions[bot]
d8b4dba963 @liu-qingyuan has signed the CLA in code-yeongyu/oh-my-opencode#1844 2026-02-14 19:40:11 +00:00
YeonGyu-Kim
7b89df01a3 chore(schema): regenerate JSON schema 2026-02-14 22:07:05 +09:00
YeonGyu-Kim
dcb76f7efd test(directory-readme-injector): use real files instead of fs module mocks 2026-02-14 22:06:57 +09:00
YeonGyu-Kim
7b62f0c68b test(directory-agents-injector): use real files instead of fs module mocks 2026-02-14 22:06:52 +09:00
YeonGyu-Kim
2a7dfac50e test(skill-tool): restore bun mocks after tests 2026-02-14 22:06:46 +09:00
YeonGyu-Kim
2b4651e119 test(rules-injector): restore bun mocks after suite 2026-02-14 22:06:39 +09:00
YeonGyu-Kim
37d3086658 test(atlas): reset session state instead of module mocking 2026-02-14 22:06:34 +09:00
YeonGyu-Kim
e7dc3721df test(prometheus-md-only): avoid hook-message storage constant mocking 2026-02-14 22:06:28 +09:00
YeonGyu-Kim
e995443120 refactor(call-omo-agent): inject executeSync dependencies for tests 2026-02-14 22:06:23 +09:00
YeonGyu-Kim
3a690965fd test(todo-continuation-enforcer): stabilize fake timers 2026-02-14 22:06:18 +09:00
YeonGyu-Kim
74d2ae1023 fix(shared): normalize macOS realpath output 2026-02-14 22:06:13 +09:00
YeonGyu-Kim
a0c9381672 fix: prevent stale timeout from killing actively running background tasks
The stale detection was checking lastUpdate timestamps BEFORE
consulting session.status(), causing tasks to be unfairly killed
after 3 minutes even when the session was actively running
(e.g., during long tool executions or extended thinking).

Changes:
- Reorder pollRunningTasks to fetch session.status() before stale check
- Skip stale-kill entirely when session status is 'running'
- Port no-lastUpdate handling from task-poller.ts into manager.ts
  (previously manager silently skipped tasks without lastUpdate)
- Add sessionStatuses parameter to checkAndInterruptStaleTasks
- Add 7 new test cases covering session-status-aware stale detection
2026-02-14 17:59:01 +09:00
YeonGyu-Kim
65a06aa2b7 Merge pull request #1833 from code-yeongyu/fix/inherit-parent-session-tools
fix: inherit parent session tool restrictions in background task notifications
2026-02-14 15:01:37 +09:00
YeonGyu-Kim
754e6ee064 Merge pull request #1829 from code-yeongyu/fix/issue-1805-lsp-windows-binary
fix(lsp): remove unreliable Windows binary availability check
2026-02-14 15:01:35 +09:00
YeonGyu-Kim
affefee12f Merge pull request #1835 from code-yeongyu/fix/issue-1781-tmux-pane-width
fix(tmux): thread agent_pane_min_width config through pane management
2026-02-14 15:01:21 +09:00
YeonGyu-Kim
90463bafd2 Merge pull request #1834 from code-yeongyu/fix/issue-1818-agents-skills-path
fix(skill-loader): discover skills from .agents/skills/ directory
2026-02-14 15:01:18 +09:00
YeonGyu-Kim
073a074f8d Merge pull request #1828 from code-yeongyu/fix/issue-1825-run-never-exits
fix(cli-run): bounded shutdown wait for event stream processor
2026-02-14 15:01:16 +09:00
YeonGyu-Kim
cdda08cdb0 Merge pull request #1832 from code-yeongyu/fix/issue-1691-antigravity-error
fix: resilient error parsing for non-standard providers
2026-02-14 15:01:14 +09:00
YeonGyu-Kim
a8d26e3f74 Merge pull request #1831 from code-yeongyu/fix/issue-1701-load-skills-string
fix(delegate-task): parse load_skills when passed as JSON string
2026-02-14 15:01:12 +09:00
YeonGyu-Kim
8401f0a918 Merge pull request #1830 from code-yeongyu/fix/issue-980-zai-glm-thinking
fix: disable thinking params for Z.ai GLM models
2026-02-14 15:01:09 +09:00
YeonGyu-Kim
32470f5ca0 Merge pull request #1836 from code-yeongyu/fix/issue-1769-background-staleness
fix(background-agent): detect stale tasks that never received progress updates
2026-02-14 15:00:11 +09:00
github-actions[bot]
c3793f779b @code-yeongyu has signed the CLA in code-yeongyu/oh-my-opencode#1699 2026-02-14 05:59:47 +00:00
YeonGyu-Kim
3de05f6442 fix: apply parentTools in all parent session notification paths
Both parent-session-notifier.ts and notify-parent-session.ts now include
parentTools in the promptAsync body, ensuring tool restrictions are
consistently applied across all notification code paths.
2026-02-14 14:58:25 +09:00
YeonGyu-Kim
8514906c3d fix: inherit parent session tool restrictions in background task notifications
Pass parentTools from session-tools-store through the background task
lifecycle (launch → task → notify) so that when notifyParentSession
sends promptAsync, the original tool restrictions (e.g., question: false)
are preserved. This prevents the Question tool from re-enabling after
call_omo_agent background tasks complete.
2026-02-14 14:58:25 +09:00
YeonGyu-Kim
f20e1aa0d0 feat: store tool restrictions in session-tools-store at prompt-send sites
Call setSessionTools(sessionID, tools) before every prompt dispatch so
the tools object is captured and available for later retrieval when
background tasks complete.
2026-02-14 14:58:25 +09:00
YeonGyu-Kim
936b51de79 feat: add parentTools field to BackgroundTask, LaunchInput, ResumeInput
Allows background tasks to carry the parent session's tool restriction
map so it can be applied when notifying the parent session on completion.
2026-02-14 14:58:25 +09:00
YeonGyu-Kim
38a4bbc75f feat: add session-tools-store for tracking tool restrictions per session
In-memory Map-based store that records tool restriction objects (e.g.,
question: false) by sessionID when prompts are sent. This enables
retrieving the original session's tool parameters when background tasks
complete and need to notify the parent session.
2026-02-14 14:58:25 +09:00
YeonGyu-Kim
7186c368b9 fix(skill-loader): discover skills from .agents/skills/ directory
Add discoverProjectAgentsSkills() for project-level .agents/skills/ and
discoverGlobalAgentsSkills() for ~/.agents/skills/ — matching OpenCode's
native skill discovery paths (https://opencode.ai/docs/skills/).

Updated discoverAllSkills(), discoverSkills(), and createSkillContext()
to include these new sources with correct priority ordering.

Co-authored-by: dtateks <dtateks@users.noreply.github.com>
Closes #1818
2026-02-14 14:58:09 +09:00
YeonGyu-Kim
121a3c45c5 fix(tmux): thread agent_pane_min_width config through pane management
The agent_pane_min_width config value was accepted in the schema and
passed as CapacityConfig.agentPaneWidth but never actually used — the
underscore-prefixed _config parameter in decideSpawnActions was unused,
and all split/capacity calculations used the hardcoded MIN_PANE_WIDTH.

Now decideSpawnActions, canSplitPane, isSplittableAtCount,
findMinimalEvictions, and calculateCapacity all accept and use the
configured minimum pane width, falling back to the default (52) when
not provided.

Closes #1781
2026-02-14 14:58:07 +09:00
YeonGyu-Kim
072b30593e fix(parser): wrap parseAnthropicTokenLimitError in try/catch
Add outer try/catch to prevent crashes from non-standard error objects
returned by proxy providers (e.g., Antigravity). Add parser tests
covering edge cases: circular refs, non-object data fields, invalid
JSON in responseBody.
2026-02-14 14:58:06 +09:00
YeonGyu-Kim
dd9eeaa6d6 test(session-recovery): add tests for detect-error-type resilience
Add test coverage for detectErrorType and extractMessageIndex with
edge cases: circular references, non-standard proxy errors, null input.
Wrap both functions in try/catch to prevent crashes from malformed
error objects returned by non-standard providers like Antigravity.
2026-02-14 14:58:06 +09:00
YeonGyu-Kim
3fa543e851 fix(delegate-task): parse load_skills when passed as JSON string
LLMs sometimes pass load_skills as a serialized JSON string instead
of an array. Add defensive JSON.parse before validation to handle
this gracefully.

Fixes #1701

Community-reported-by: @omarmciver
2026-02-14 14:58:04 +09:00