YeonGyu-Kim
fe4493c6a6
fix(model-fallback): keep model fallback opt-in by default
...
Restore the runtime default that was introduced for model fallback so unset config no longer enables automatic retries unexpectedly.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-16 10:38:55 +09:00
YeonGyu-Kim
674df1b1b8
fix(hooks): remove dead delegate-task-english-directive hook
2026-03-16 10:38:54 +09:00
YeonGyu-Kim
f3de122147
feat(hooks): add delegate-task-english-directive hook to enforce English for subagents
...
Appends bold uppercase English-only directive to explore, librarian,
oracle, and plan subagent prompts via tool.execute.before on the task tool.
2026-03-13 14:22:13 +09:00
YeonGyu-Kim
457f303adf
fix(background-agent): clean global subagentSessions and SessionCategoryRegistry on dispose
2026-03-13 10:56:44 +09:00
YeonGyu-Kim
38938508fa
test(model-fallback): update snapshots and kimi model expectations for opencode-go integration
2026-03-13 10:48:05 +09:00
YeonGyu-Kim
2210997c89
fix: skip ultrawork variant override when SDK validation unavailable
...
When provider.list is not available for SDK validation, do not apply the configured ultrawork variant. This prevents models without a max variant from being incorrectly forced to max when ultrawork mode activates.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-12 17:24:54 +09:00
YeonGyu-Kim
3ea23561f2
Merge pull request #2488 from code-yeongyu/fix/issue-2295-fallback-provider-preserve
...
fix: preserve session provider context in fallback chain
2026-03-12 11:24:43 +09:00
YeonGyu-Kim
b00fc89dfa
Merge pull request #2458 from code-yeongyu/fix/memory-leaks
...
fix: resolve 12 memory leaks (3 critical + 9 high)
2026-03-12 11:21:13 +09:00
YeonGyu-Kim
2912b6598c
fix: address Cubic findings for provider preserve fallback
...
- Reorder resolveFallbackProviderID: providerHint now checked before global connected-provider cache
- Revert require('bun:test') hack to standard ESM import in fallback-chain-from-models.test.ts
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-12 11:05:31 +09:00
YeonGyu-Kim
7870e43578
fix: preserve session provider context in fallback chain ( #2295 )
2026-03-12 01:49:16 +09:00
YeonGyu-Kim
9b792c3224
Merge pull request #2485 from code-yeongyu/fix/issue-2316-tool-after-error-boundary
...
fix: add error boundary around extract/discard hooks in tool-execute-after
2026-03-12 01:46:51 +09:00
YeonGyu-Kim
305389bd7f
fix: add error boundary around extract/discard hooks in tool-execute-after ( #2316 )
2026-03-12 01:41:07 +09:00
YeonGyu-Kim
f564404015
fix: address review-work round 6 findings (dispose isolation, event dispatch, disconnectedSessions ref-counting)
2026-03-12 01:37:03 +09:00
YeonGyu-Kim
142f8ac7d1
Merge pull request #2422 from MoerAI/fix/issue-2393-model-fallback-defaults
...
fix(model-fallback): enable by default and add missing error patterns for usage limits
2026-03-12 01:32:34 +09:00
YeonGyu-Kim
4a67044cd6
fix: register preemptive-compaction event handler in dispatchToHooks ( #2300 )
2026-03-12 00:55:15 +09:00
YeonGyu-Kim
f7085450f1
fix(compaction): guard model update during compaction and validate checkpoint model
2026-03-11 21:57:06 +09:00
YeonGyu-Kim
a1b060841f
fix(continuation): auto-continue GPT permission-seeking replies
...
Resume GPT sessions when the last assistant reply ends in a permission-seeking tail, while honoring stop-continuation and avoiding duplicate continuation across todo and atlas flows.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-11 21:20:59 +09:00
YeonGyu-Kim
3550305af8
Merge branch 'dev' into fix/issue-2232
2026-03-11 20:20:04 +09:00
YeonGyu-Kim
70edea2d7f
Merge pull request #2397 from code-yeongyu/fix/browser-provider-skill-context-playwright
...
fix(skill-context): gate discovered browser skills by provider
2026-03-11 17:30:37 +09:00
YeonGyu-Kim
35df4d5d1b
Merge pull request #2372 from code-yeongyu/fix/issue-2314
...
fix(plugin): preserve cross-zod tool arg metadata
2026-03-11 17:27:00 +09:00
YeonGyu-Kim
29e1136813
Guard ultrawork variant overrides with SDK metadata
...
Ultrawork now checks provider SDK metadata before forcing a variant, so unsupported variants are skipped instead of being written into the message state.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-11 15:33:05 +09:00
MoerAI
059853554d
fix(model-fallback): enable by default and add missing error patterns for usage limits ( #2393 )
2026-03-10 17:04:17 +09:00
YeonGyu-Kim
7d1607dc16
fix: align sync fallback chain, fix model-fallback test determinism
...
- Hoist resolveFallbackChainForCallOmoAgent before sync/background branch
so sync executor also receives the fallback chain
- Add fallbackChain parameter to sync-executor with setSessionFallbackChain
- Mock connected-providers-cache in event.model-fallback tests for
deterministic behavior (no dependency on local cache files)
- Update test expectations to account for no-op fallback skip when
normalized current model matches first fallback entry
- Add cache spy isolation for subagent-resolver fallback_models tests
2026-03-09 13:11:03 +09:00
Ravi Tharuma
c598afa521
Address PR review follow-ups for retry status handling
2026-03-09 12:43:30 +09:00
Ravi Tharuma
86c6bc7716
Unify dynamic fallback chains for background subagents
2026-03-09 12:43:30 +09:00
Ravi Tharuma
e65433861c
Stabilize provider assertions after rebase
2026-03-09 12:43:01 +09:00
Ravi Tharuma
eab5be666d
Fix cooldown fallback switching across model/runtime fallback hooks
2026-03-09 12:43:01 +09:00
YeonGyu-Kim
4f088c7ab8
test(plugin): run tool output truncation before claude transcript hooks
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-09 11:27:58 +09:00
YeonGyu-Kim
1528e46faa
fix(skill-context): gate discovered browser skills by provider
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-09 11:16:24 +09:00
YeonGyu-Kim
df36efacf4
fix(plugin): dispatch compaction context hook events
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-08 02:23:46 +09:00
YeonGyu-Kim
65edddac41
fix(plugin): wire compaction context hook creation
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-08 02:23:41 +09:00
YeonGyu-Kim
d84c28dbab
fix(plugin): preserve cross-zod tool arg metadata
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-08 02:21:42 +09:00
YeonGyu-Kim
60bc9a7609
feat(model-requirements): add k2p5, kimi-k2.5, gpt-5.4 medium to Sisyphus fallback chain
...
Sisyphus can now fall back through Kimi and OpenAI models when Claude
is unavailable, enabling OpenAI-only users to use Sisyphus directly
instead of being redirected to Hephaestus.
Runtime chain: claude-opus-4-6 max → k2p5 → kimi-k2.5 → gpt-5.4 medium → glm-5 → big-pickle
CLI chain: claude-opus-4-6 max → k2p5 → gpt-5.4 medium → glm-5
2026-03-08 01:41:45 +09:00
YeonGyu-Kim
e193002775
fix(plugin): ignore compaction session agent updates
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-07 15:39:25 +09:00
YeonGyu-Kim
898b628d3d
fix(ulw-loop): track Oracle verification sessions explicitly
...
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode )
2026-03-06 22:37:41 +09:00
YeonGyu-Kim
c17f7215f2
test(ulw-loop): cover Oracle verification flow
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-06 22:00:21 +09:00
YeonGyu-Kim
a010de1db2
feat(ulw-loop): require Oracle verification before completion
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-06 22:00:14 +09:00
YeonGyu-Kim
23dcd99c9a
docs(agents): refresh generated AGENTS guides
...
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode )
2026-03-06 17:59:05 +09:00
YeonGyu-Kim
a61f8bb853
Update @opencode-ai/plugin and SDK to v1.2.x and align system transform handler signature
...
- Bump @opencode-ai/plugin ^1.1.19 → ^1.2.16, @opencode-ai/sdk ^1.1.19 → ^1.2.17
- Update system-transform handler input type to match new plugin contract (optional sessionID, required model)
- Add @opencode-ai/sdk override in bun.lock
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode )
2026-03-05 11:18:12 +09:00
YeonGyu-Kim
85690b69a8
test: update snapshots and assertions for kimi-k2.5-free removal
2026-03-04 11:33:11 +09:00
YeonGyu-Kim
33d39597ae
docs(agents): regenerate AGENTS.md hierarchy with updated metrics and model configs
...
- 1208→1243 TS files (+35), 143k→155k LOC (+12k)
- Update all agent models: Sisyphus, Hephaestus, Oracle, Librarian, Atlas, Metis, Momus
- Add 6 new hook directories (39→45 dirs): beast-mode-system, hashline-edit-diff-enhancer, anthropic-image-context, task-reminder, compaction-todo-preserver, runtime-fallback
- Update category models: visual-engineering/artistry gemini-3-pro→gemini-3.1-pro
- Add 2 config schema files: fallback-models.ts, runtime-fallback.ts
- Timestamp: 2026-03-02 | Commit: 1c2caa09
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode )
2026-03-02 23:40:38 +09:00
YeonGyu-Kim
4905e6fc7c
Merge pull request #2021 from cruzanstx/feat/marketplace-plugin-dispatch
...
feat(dispatch): wire marketplace plugin commands into slash command dispatch
2026-03-02 23:28:20 +09:00
YeonGyu-Kim
fdd806e729
Merge pull request #2173 from Lynricsy/feat/sync-poll-timeout-config
...
feat(delegate-task): ⚙️ make sync subagent timeout configurable via syncPollTimeoutMs
2026-03-02 23:28:15 +09:00
YeonGyu-Kim
0f6e9c7bfa
Merge pull request #2125 from zhzy0077/fix/copilot-invalid-initiator
...
fix(chat-headers): skip x-initiator override for @ai-sdk/github-copilot models
2026-03-02 23:27:59 +09:00
YeonGyu-Kim
efa959895a
Merge pull request #2198 from acamq/feat/no-auto-commit-work-plan
...
feat(start-work): add auto_commit config option
2026-03-02 23:27:44 +09:00
YeonGyu-Kim
3db46a58a7
feat(hashline): change hashline_edit default from true to false
...
Hashline edit tool and companion hooks now require explicit opt-in
via `"hashline_edit": true` in config. Previously enabled by default.
- tool-registry: hashline edit tool not registered unless opted in
- create-tool-guard-hooks: hashline-read-enhancer disabled by default
- Updated config schema comment and documentation
- Added TDD tests for default behavior
2026-03-02 15:20:31 +09:00
YeonGyu-Kim
cc6ab1addc
feat(hooks): add read-image-resizer hook
...
Intercepts Read tool output with image attachments and resizes to comply with Anthropic API limits (≤1568px long edge, ≤5MB). Only activates for Anthropic provider sessions and appends resize metadata (original/new resolution, token count) to tool output.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-02-28 13:21:40 +09:00
acamq
e2e3d110b7
feat(start-work): add auto_commit config option
...
Add start_work.auto_commit configuration option to allow users to
disable the automatic commit step in the /start-work workflow.
When auto_commit is false:
- STEP 8: COMMIT ATOMIC UNIT is removed from orchestrator reminder
- STEP 9: PROCEED TO NEXT TASK becomes STEP 8
Resolves #2197
2026-02-27 13:38:52 -07:00
Lynricsy
d09cf56e15
feat(delegate-task): ⚙️ make sync subagent timeout configurable via syncPollTimeoutMs
...
Allow users to set `background_task.syncPollTimeoutMs` in config to override
the default 10-minute sync subagent timeout. Affects sync task, sync continuation,
and unstable agent task paths. Minimum value: 60000ms (1 minute).
Co-authored-by: Wine Fox <fox@ling.plus >
2026-02-27 16:17:39 +08:00
YeonGyu-Kim
2ffa803b05
fix(ultrawork-db): write $.thinking alongside $.variant in deferred model override
2026-02-27 02:59:22 +09:00