luna/oh-my-opencode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
6,259 Commits 102 Branches 0 Tags
df198d8b2dd991a7d31009faba6fad560581a532
Commit Graph

338 Commits

Author SHA1 Message Date
YeonGyu-Kim 55312cc4b6 fix(session-recovery): preflight idle recovery fanout 2026-05-17 16:17:36 +09:00
YeonGyu-Kim a7b7ace7ed fix(prompt-gate): block prompts into pending tool turns 2026-05-17 15:42:58 +09:00
YeonGyu-Kim f43effb842 fix(session-recovery): recover interrupted idle tool turns 2026-05-17 15:08:39 +09:00
YeonGyu-Kim a43215f24e fix(plugin/event): bind team-idle-wake-hint client methods to SDK Session 
The team-mode wiring at `createEventHandler` extracted
`pluginContext.client.session.promptAsync` and `.status` into a fresh
wrapper object. The methods were copied by reference, so the prompt-async
gate's `session.promptAsync.bind(session)` was binding to that plain
wrapper rather than the underlying SDK `Session` instance. The opencode
SDK's `promptAsync` reads `this._client.post(...)`, so production calls
threw `TypeError: undefined is not an object (evaluating 'this._client')`
on the very first dispatch — fingerprinted in /tmp/oh-my-opencode.log as
688 `background-agent-parent-wake`, 47 `model-suggestion-retry`, and 4
`team-idle-wake-hint` failures over the past three days.

Move the wrapper construction into `buildTeamIdleWakeHintClient`, which
preserves the narrow factory contract while binding both methods back to
the SDK `Session` so `_client` survives the dispatch. Cover the contract
with four BDD-style tests including the historical destructure-only
failure mode so any future regression is caught at unit-test time.
 2026-05-17 02:06:52 +09:00
YeonGyu-Kim 36e373cdbb feat(workspace): point planning guardrails at omo 2026-05-16 17:41:35 +09:00
Enoch d11613999a fix tool execute after hook boundary 2026-05-15 23:37:45 +09:00
YeonGyu-Kim c580b8f2ce fix(session): ignore internal synthetic turns 2026-05-15 23:16:05 +09:00
YeonGyu-Kim 2bd4944bad fix(prompt-gate): scope reservation releases 2026-05-15 21:52:29 +09:00
rshks b504fb1deb fix(tool-pair-validator): emit schema-compatible synthetic tool results 2026-05-15 21:04:03 +09:00
YeonGyu-Kim 8dcbccf063 fix(tmux): inject pane action dependencies 2026-05-15 17:54:43 +09:00
YeonGyu-Kim 462b55efc7 Merge pull request #4040 from code-yeongyu/cleanup/typescript-ai-slop-20260515 
Refactor TypeScript cleanup patterns
 2026-05-15 16:42:10 +09:00
YeonGyu-Kim a9886ccbb7 refactor(plugin): remove metadata assertions 
Guard optional plugin metadata and pane identifiers before passing them to cleanup and warning paths.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-15 16:31:13 +09:00
YeonGyu-Kim d8f52aae7f test: run suite without split runner 2026-05-15 16:26:57 +09:00
YeonGyu-Kim 15e7330ff0 fix(team-mode): gate status injection by keyword 2026-05-15 15:35:35 +09:00
YeonGyu-Kim 9f6d0d2281 docs(agents-md): refresh hierarchical knowledge base for v4.1.2 
- Bump root AGENTS.md header: 2026-05-14 → 2026-05-15, commit 5ffbe0e24 → 53a740636, release v4.1.1 → v4.1.2
- Update file counts: 2034 (1337+697) → 2041 (1340+701), LOC ~292k → ~294k
- Fix STRUCTURE: openclaw lives at src/openclaw/ (not src/features/); list more accurate feature modules in the parenthetical
- Clarify interactive_bash gate: tmux binary on PATH via isInteractiveBashEnabled() (not 'tmux enabled')
- Fix docs/reference/features.md hook counts: Tool Guard 14→16, Total base 52→54, total with team-mode 59→61
- Bump 'Generated' date on all 43 subdir AGENTS.md files to 2026-05-15
- Preserve promptAsync injection cautions verbatim (per request)
 2026-05-15 13:48:11 +09:00
YeonGyu-Kim c2aa180e7e fix(prompt-gate): pin duplicate prompt dispatches 
Keep prompt reservations briefly after successful dispatch so rapid idle/message/error transitions cannot inject the same follow-up twice.

Route all production session prompt calls through the shared gate, restore skipped background resume state, release holds after abort/recovery paths, and preserve Ralph/ULW loop state when a dispatch is deferred.

Add regression coverage for session routing, static prompt route auditing, team-mode live messaging, model suggestion retries, call-omo-agent reuse, background parent wakes, runtime fallback, compaction recovery, Atlas, and Ralph/ULW loops.
 2026-05-15 13:19:10 +09:00
YeonGyu-Kim edf3e530d4 fix(hooks): gate sync injected prompts 2026-05-15 12:55:56 +09:00
YeonGyu-Kim dd6271bbf4 fix(babysitter): gate reminder prompts 2026-05-15 12:55:56 +09:00
YeonGyu-Kim c75f548863 fix(fallback): gate model retry prompts 2026-05-15 12:55:56 +09:00
YeonGyu-Kim 23dfe7eec2 fix(fallback): skip duplicate fallback re-arms 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-15 11:45:21 +09:00
YeonGyu-Kim b7482ea727 test(fallback): type chat output assertions 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-15 11:28:18 +09:00
YeonGyu-Kim 26bb6231b6 fix(fallback): preserve provider-specific fallback retries 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-15 11:14:26 +09:00
YeonGyu-Kim 005d16dd96 fix(fallback): dedupe providerless fallback errors 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-15 11:14:26 +09:00
YeonGyu-Kim da339204bb fix(fallback): dedupe overlapping fallback continuations 
Guard model fallback continuation dispatch so overlapping message.updated/session.error surfaces issue only one abort+promptAsync cycle for the same failed fallback.

Refs https://github.com/code-yeongyu/oh-my-openagent/issues/4019

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-15 11:14:26 +09:00
YeonGyu-Kim 1e7a7600a2 docs(agents-md): regenerate hierarchical AGENTS.md knowledge base for v4.1.1 
Refresh all AGENTS.md files to reflect codebase state at 5ffbe0e24 (was cd31d2a1a, 197 commits behind).

Key drift corrections across 45 modified + 1 new file:

Root AGENTS.md:
- TS file counts: 1967 -> 2034 in src/ (1337 source + 697 test)
- LOC: 278k -> 292k
- Barrel index.ts: 120 -> 122
- Hook tier composition: 52/59 -> 54/61 (base/with team-mode)
- Tool Guard hooks: 14 -> 16 (add fsync-skip-warning, bash-file-read-guard)
- Add boulder feature, agent-ordering schema, .agents/ directory, v4.1.1 release tag
- Add generated/ directory entry

src/AGENTS.md:
- Subsystem inventory: agents 96->102, hooks 570->581, tools 306->314,
  features 389->400, shared 258->278, cli 150->158, plugin 55->56
- LOC totals refreshed for every subsystem
- Schema files: 32 -> 30

src/hooks/AGENTS.md:
- Tier 2 (Tool Guard): 14 -> 16 hooks, add fsyncSkipWarning row
- Total: 52 base / 59 team-mode -> 54 base / 61 team-mode
- zauc-mocks count: 7 -> 5

src/features/AGENTS.md:
- background-agent: 47 -> 57 files, mention archive fallback
- opencode-skill-loader: 33 -> 30
- tmux-subagent: 34 -> 32

src/plugin/AGENTS.md:
- Tool Guard composer count: 14 -> 16
- Aggregator total: 43 -> 45

src/cli/AGENTS.md:
- Add new boulder subcommand (BoulderState inspector)
- Command count: 6 -> 7

NEW: src/features/boulder-state/AGENTS.md
- Document the new Boulder work tracking feature
- Schema v2 with BoulderState/BoulderWorkState/TaskSessionState
- Lifecycle, storage, integration points with atlas/ralph-loop hooks

All other AGENTS.md files: Generated date 2026-05-08 -> 2026-05-14.
 2026-05-14 12:57:46 +09:00
YeonGyu-Kim 5ffbe0e24e fix(fallback): guard duplicate prompt injections 2026-05-14 01:03:19 +09:00
YeonGyu-Kim 36f51ddb16 fix(continuation): mark fallback resumes synthetic 2026-05-13 13:36:25 +09:00
YeonGyu-Kim d5fbada13d test: make unsafe test coercion explicit 
Move test coercion out of a hidden global and require each test to import the helper so review tools and runtime scripts can see the unsafe boundary.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-12 15:51:31 +09:00
YeonGyu-Kim f05aeaa63a test(plugin): remove unsafe test assertions 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-12 15:41:17 +09:00
YeonGyu-Kim 9ffef79dbb fix(ralph-loop): ignore synthetic idle replays 2026-05-12 15:28:46 +09:00
YeonGyu-Kim 4da48555ee fix(plugin): normalize event session ids 
Handle OpenCode session events that carry the session ID under properties.info.id or properties.info.sessionID so background tasks and continuation hooks do not miss idle/error/delete events.

Add regression coverage for nested session.idle events completing background tasks and waking continuation hooks.
 2026-05-12 12:32:26 +09:00
YeonGyu-Kim 3ed4651b7a fix(compaction): skip autocontinue for compaction agent 2026-05-11 18:46:29 +09:00
YeonGyu-Kim 0fd918ea80 fix(delegate-task): preserve native task metadata 2026-05-11 13:08:56 +09:00
YeonGyu-Kim 954aa1f121 fix(compaction): isolate preservation hook failures 2026-05-11 12:54:32 +09:00
YeonGyu-Kim 4b281f949e Merge pull request #3914 from code-yeongyu/fix/max-output-tokens 
fix: prevent non-positive maxOutputTokens from leaking to SDK
 2026-05-11 09:22:39 +09:00
YeonGyu-Kim 50dffc9952 Merge pull request #3911 from code-yeongyu/fix/todo-diag-blocked-alert 
fix(plugin): allow real session.idle after synthetic idle within dedup window
 2026-05-11 09:22:31 +09:00
YeonGyu-Kim 2f8ce576dc fix(chat-params): use conservative token fallback for invalid limits 
Avoid inflating non-positive maxOutputTokens values to model capability maxima by always falling back to a safe fixed budget.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-11 08:47:49 +09:00
YeonGyu-Kim 2168040ac6 fix(plugin): scope synthetic-idle dedup bypass to matching marker 
Only clear recentAnyIdles when the stored marker matches the synthetic idle timestamp for the same session, preventing accidental clobbering of newer idle markers. Add a regression test to verify other sessions keep their dedup state during this bypass path.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-11 08:45:34 +09:00
acamq 299275094f Revert "fix(tool-execute-after): cap excessively long tool output to prevent TUI flooding (fixes #3586)" 2026-05-10 17:33:36 -06:00
YeonGyu-Kim 41629b5262 fix(plugin): guard assistant prefill message tails 2026-05-10 15:54:29 +09:00
YeonGyu-Kim 279f0d150f fix(chat-params): guard non-positive max output tokens 2026-05-10 15:03:01 +09:00
YeonGyu-Kim a196d84c2e fix(plugin): allow real session.idle after synthetic idle within dedup window 
When session.status(idle) is converted to synthetic session.idle and recorded in recentAnyIdles, a real session.idle arriving within 500ms was being dropped by the dedup logic. recentSyntheticIdles was cleared but recentAnyIdles persisted, causing TODO-DIAG to red-alert with 'no todossession.idle event'.

Fix: when real session.idle arrives, also clear recentAnyIdles entry so dedup does not drop it. Test renamed and expected dispatchCalls updated 1 → 2.

Fixes #2667
 2026-05-10 14:54:01 +09:00
YeonGyu-Kim dd29e9b96a fix(compaction): restore context and todos before continue 2026-05-10 13:54:27 +09:00
YeonGyu-Kim 43b0529557 feat(hooks): surface fsync-skip warnings to AI agent via tool output 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-05-08 15:08:34 +09:00
YeonGyu-Kim 838b5ae216 docs(agents): refresh hierarchical AGENTS.md with team-mode coverage 
Update root + 43 directory-level AGENTS.md files to reflect current state:
- Root AGENTS.md rewritten with accurate counts (1967 TS files, 1304 source +
  663 test, 278k LOC, 120 barrel index.ts), 7-step init flow, 5-tier hook
  composition, and full Team Mode section (12 team_* tools, eligibility,
  storage layout, config gate)
- src/AGENTS.md adds team-mode init step, current per-subdir file/LOC table
- src/tools/AGENTS.md documents conditional gates (team-mode +12, task
  system +4, hashline +1, interactive_bash +1, look_at +1) with always-on
  baseline of 20
- src/hooks/AGENTS.md splits into 5 tiers + 4 conditional team-mode hooks
- src/features/team-mode/AGENTS.md surfaces 12 tools, eligible agents,
  spawn-race-safe invariants, and integration points
- src/features/builtin-skills/AGENTS.md tracks 10 skills incl. team-mode
- src/agents/AGENTS.md, src/plugin/AGENTS.md, src/config/AGENTS.md updated
  for team-mode awareness, accurate counts, and current schema field list
- All other AGENTS.md files refreshed to 2026-05-08 generation date
 2026-05-08 12:08:42 +09:00
YeonGyu-Kim ee938aa097 fix full-suite isolation regressions 2026-05-07 18:36:03 +09:00
herjarsa 3a93a40e68 fix(desktop): hide bun:sqlite import from Node.js/Electron ESM loader 
Uses new Function() to prevent the static ESM loader from seeing
the bun: protocol import at parse time. In Electron/Node.js, the
import() call is evaluated at runtime and gracefully returns null
when bun:sqlite is unavailable.

Fixes #3829, likely fixes #3762
 2026-05-07 10:38:31 +02:00
YeonGyu-Kim 1ad0fd4ac8 Merge pull request #3748 from code-yeongyu/fix/simple-github-bugs-1948-3564 
fix: resolve simple triaged GitHub bugs
 2026-05-06 18:43:58 +09:00
YeonGyu-Kim 9dd0e9fb0e Merge pull request #3622 from MoerAI/fix/truncate-tool-error-output 
fix(tool-execute-after): cap excessively long tool output to prevent TUI flooding (fixes #3586)
 2026-05-06 17:22:53 +09:00
YeonGyu-Kim 62a7356de3 Merge pull request #3621 from MoerAI/fix/skill-tool-respects-plugins-config 
fix(tool-registry): pass plugins config to skill tool for proper command filtering (fixes #3582)
 2026-05-06 17:15:01 +09:00