e9a09b39b3
Merge branch 'fix/ub5-regression' into dev
2026-03-31 17:08:45 -07:00
91d5b06495
Merge branch 'fix/ub4-regression' into dev
2026-03-31 17:08:45 -07:00
f77ac22e16
Merge branch 'fix/ub3-regression' into dev
2026-03-31 17:08:45 -07:00
cafaeee94d
Merge branch 'fix/ub2-regression' into dev
2026-03-31 17:08:44 -07:00
11ee88f28f
fix: use jsonc-parser for safe JSONC migration and add project-local config detection
2026-03-31 17:06:46 -07:00
8fba90766d
fix: apply scope filter to getSystemMcpServerNames and fix async native skill description refresh
2026-03-31 17:05:55 -07:00
3cce7406ea
fix: distinguish transient errors from missing sessions in crash detection
2026-03-31 17:04:07 -07:00
de7d72db27
fix: honor category-derived model overrides in call_omo_agent
2026-03-31 17:03:42 -07:00
87445a2ef3
fix: add missing run_in_background to resume snippet and fix background launch detection
2026-03-31 17:02:56 -07:00
7d6f47bf3d
fix: resolve process-cleanup signal delay and hashline_edit tool name mismatch
2026-03-31 16:59:04 -07:00
67429af358
fix(tmux): allow subsequent subagents to spawn in existing isolated container
2026-03-31 16:58:45 -07:00
62a46fbabd
fix: normalize zero-width prefix in agent registration lookup
2026-03-31 16:58:15 -07:00
9a0f2ff9a7
test(delegate-task): cover aborted concurrent background launches
2026-03-31 15:11:12 -07:00
56cf16c4c5
refactor(background-task): stop cancelling launched tasks during session wait
2026-03-31 15:11:05 -07:00
e2e57bb2dd
fix(agents): use list display names for ordered agent config
2026-03-31 15:11:00 -07:00
1d0135b230
fix(delegate-task): reject stray backend-style categories
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-31 13:05:44 -07:00
68ae9dca4b
fix(agents): stop advertising custom agents to orchestrators
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-31 13:05:38 -07:00
33c8b7f675
fix(tests): resolve 6 test isolation failures in full suite
...
3 failures in fallback.cliproxyapi-matrix.test.ts:
- Root cause: leaked spyOn(getMainSessionID) in
tool-execute-before-session-notification.test.ts was never restored,
poisoning module state for subsequent tests in the same worker
- Added mockRestore() call and _resetModelFallbackForTesting in afterEach
3 failures in background-agent/manager.test.ts:
- Root cause: connected-providers-cache memConnected/memProviderModels
persisted across test files, making isReachable() skip fallback
candidates in retry tests
- Added mock.module for connected-providers-cache at file level
- Added _resetMemCacheForTesting export and global beforeEach cleanup
Full suite: 4638/4638 pass, 0 fail
2026-04-01 04:30:34 +09:00
fd281deba7
fix(tests): resolve 25 pre-publish test failures
...
- Add providerModelsCache/fetchAvailableModels mocks to 20 utils.test.ts
tests that broke when createBuiltinAgents started reading the cache
- Isolate ALL src/plugin and src/features/background-agent test files in CI
(mock.module pollution crosses between files in the same bun process)
- Mirror CI isolation changes in publish.yml
25 failures → 0 in CI (all mock-pollution tests run individually)
2026-03-31 18:12:57 +09:00
71c60e1be4
fix: skip thinking param injection for GLM models in sisyphus-junior ( #2967 )
...
GLM-5 has native reasoning built-in. Injecting thinking: {type: 'enabled'}
causes a param conflict (400 error). Add isGlmModel() check to return base
config without thinking/reasoningEffort for GLM models.
- Add isGlmModel() helper to types.ts
- Early return in createSisyphusJuniorAgentWithOverrides for GLM models
- Add tests for isGlmModel and GLM reasoning config behavior
2026-03-31 16:32:32 +09:00
51194e9434
Merge pull request #2919 from ryandielhenn/feat/config_tdd
...
Add Configurable TDD To Sisyphus Agent Schema
2026-03-29 18:55:21 -07:00
2d46a71da4
Merge pull request #2929 from quangtran88/fix/rules-injector-respect-claude-code-config
...
fix(rules-injector): respect claude_code config for user rule loading
2026-03-29 18:54:27 -07:00
1998d5a35d
Merge pull request #2936 from HOYALIM/fix-2696-skill-xml-names
...
fix: preserve nested async skill names in discovery
2026-03-29 18:53:35 -07:00
59f11680a7
Merge pull request #2874 from sanoyphilippe/feat/plugin-tool-session-navigation
...
feat(atlas): support plugin tools with metadata.sessionId in orchestration hook
2026-03-29 18:45:43 -07:00
b12e32d855
Merge pull request #2912 from RaviTharuma/test/quotio-fallback-matrix-upstream
...
test(fallback): add CLIProxyAPI-only integration matrix
2026-03-29 18:45:34 -07:00
44c6a2ad5c
Merge pull request #2931 from sjawhar/feat/tmux-session-isolation
...
feat(tmux): add session isolation mode for subagent panes
2026-03-29 18:44:29 -07:00
8b437ee1d9
Merge pull request #2930 from sjawhar/fix/agent-name-duplication
...
fix: permanently resolve agent name duplication yo-yo bug
2026-03-29 18:42:50 -07:00
aa6632a3b4
Merge pull request #2935 from HOYALIM/fix/issue-2903-timestamp-tests
...
fix: stabilize timestamp-output tests across timezones
2026-03-29 18:42:23 -07:00
500f10b0bc
Merge pull request #2939 from sjawhar/fix/delegate-task-category-override
...
fix(delegate-task): replace mutual exclusion throw with category-wins override (#2847 )
2026-03-29 18:41:48 -07:00
0f6c7a9ca0
fix(config): accept object-format fallback_models in Zod validation ( fixes #2943 )
...
FallbackModelsSchema now explicitly accepts string[], object[], and
mixed array formats, matching the JSON schema definition.
Verified: 15 config schema tests pass, typecheck clean
2026-03-30 10:35:06 +09:00
67253447b7
fix(anthropic-effort): skip effort injection for internal agents ( fixes #2940 )
...
Internal agents (title, summary, compaction) no longer receive the
anthropic-beta effort header, preventing 400 errors on Google Vertex
Anthropic provider.
Verified: 12 tests pass, typecheck clean
2026-03-30 10:33:38 +09:00
a3cc2d1c95
feat(tmux): add session isolation mode for subagent panes
2026-03-29 17:53:30 +00:00
4314a3e482
fix: permanently resolve agent name duplication yo-yo bug
2026-03-29 15:13:47 +00:00
3905d07273
fix(delegate-task): replace mutual exclusion throw with category-wins override
2026-03-29 15:07:42 +00:00
f9e487f55a
address bot review
2026-03-29 06:01:31 -07:00
1d13250654
address bot review
2026-03-29 05:56:44 -07:00
e27f183b65
test: cover remaining nested async skill paths
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-29 01:16:10 -07:00
c132185d17
fix: preserve nested async skill names in discovery
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-29 00:35:59 -07:00
fa64c31ae2
fix: stabilize timestamp-output tests across timezones
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-03-29 00:25:29 -07:00
738b045e9b
fix: use strict equality for claude_code flag checks
...
Use `=== false` instead of falsy negation so that missing/undefined
fields are not treated as explicitly disabled. Only skip ~/.claude/rules
when all three flags are explicitly set to false.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-29 10:22:54 +07:00
a1a2bb4b07
fix(rules-injector): respect claude_code config for user rule loading
...
When claude_code integration is disabled in oh-my-opencode.json, the
rules-injector now skips loading rules from ~/.claude/rules/ to prevent
Claude Code-specific instructions from leaking into non-Claude agents
(e.g., GPT-5.4 Sisyphus), which causes agent hallucination.
Also adds ~/.sisyphus/rules/ and ~/.opencode/rules/ as OpenCode-native
user rule directories that are always searched regardless of config.
Fixes #2920
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-29 10:13:55 +07:00
b2497f1327
fix: resolve 3 community-reported bugs ( #2915 , #2917 , #2918 )
...
- background_output: snapshot read cursor before consuming, restore on
/undo message removal so re-reads return data (fixes #2915 )
- MCP loader: preserve oauth field in transformMcpServer, add scope/
projectPath filtering so local-scoped MCPs only load in matching
directories (fixes #2917 )
- runtime-fallback: add 'reached your usage limit' to retryable error
patterns so quota exhaustion triggers model fallback (fixes #2918 )
Verified: bun test (4606 pass / 0 fail), tsc --noEmit clean
2026-03-29 04:53:43 +09:00
e9e0aef847
use optional instead of required for tdd config for backwards compatibility
2026-03-28 11:10:26 -07:00
2b6a02ee97
nit
2026-03-28 09:37:13 -07:00
571dfe23a4
add bool value: tdd to sisyphus_agent config
2026-03-28 09:34:58 -07:00
92069d2e7f
test(fallback): rename quotio matrix to cliproxyapi
2026-03-28 09:11:41 +01:00
57fcc9e842
test(fallback): add quotio-only integration matrix
2026-03-28 08:58:17 +01:00
4e214cba4e
fix(recovery): ignore empty summary-only assistant messages
2026-03-28 08:57:36 +01:00
4a029258a4
fix: resolve 5 remaining pre-publish blockers (14, 15, 17, 21, 25c)
...
- completion-promise-detector: restrict to assistant text parts only,
remove tool_result from completion detection (blocker 14)
- ralph-loop tests: flip tool_result completion expectations to negative
coverage, add false-positive rejection tests (blocker 15)
- skill tools: merge nativeSkills into initial cachedDescription
synchronously before any execute() call (blocker 17)
- skill tools test: add assertion for initial description including
native skills before execute() (blocker 25c)
- docs: sync all 4 fallback-chain docs with model-requirements.ts
runtime source of truth (blocker 21)
Verified: bun test (4599 pass / 0 fail), tsc --noEmit clean
2026-03-28 15:57:27 +09:00
d2c576c510
fix: resolve 25 pre-publish blockers
...
- postinstall.mjs: fix alias package detection
- migrate-legacy-plugin-entry: dedupe + regression tests
- task_system: default consistency across runtime paths
- task() contract: consistent tool behavior
- runtime model selection, tool cap, stale-task cancellation
- recovery sanitization, context-limit gating
- Ralph semantic DONE hardening, Atlas fallback persistence
- native-skill description/content, skill path traversal guard
- publish workflow: platform awaited via reusable workflow job
- release: version edits reapplied before commit/tag
- JSONC plugin migration: top-level plugin key safety
- cold-cache: user fallback models skip disconnected providers
- docs/version/release framing updates
Verified: bun test (4599 pass), tsc --noEmit clean, bun run build clean
2026-03-28 15:24:18 +09:00
YeonGyu-Kim