Compare commits

...

81 Commits

Author SHA1 Message Date
github-actions[bot]
4f26e99ee7 release: v3.1.10 2026-01-31 03:52:22 +00:00
Kwanghyun Moon
b405494808 fix: resolve deadlock in config handler during plugin initialization (#1304)
* fix: resolve deadlock in config handler during plugin initialization

The config handler and createBuiltinAgents were calling fetchAvailableModels
with client, which triggers client.provider.list() API call to OpenCode server.
This caused a deadlock because:
- Plugin initialization waits for server response
- Server waits for plugin init to complete before handling requests

Now using cache-only mode by passing undefined instead of client.
If cache is unavailable, the fallback chain will use the first model.

Fixes #1301

* test: add regression tests for deadlock prevention in fetchAvailableModels

Add tests to ensure fetchAvailableModels is called with undefined client
during plugin initialization. This prevents regression on issue #1301.

- config-handler.test.ts: verify config handler does not pass client
- utils.test.ts: verify createBuiltinAgents does not pass client

* test: restore spies in utils.test.ts to prevent test pollution

Add mockRestore() calls for all spies created in test cases to ensure proper cleanup between tests and prevent state leakage.

* test: restore fetchAvailableModels spy

---------

Co-authored-by: robin <robin@watcha.com>
Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-31 12:46:05 +09:00
github-actions[bot]
839a4c5316 @robin-watcha has signed the CLA in code-yeongyu/oh-my-opencode#1303 2026-01-30 22:37:44 +00:00
github-actions[bot]
08d43efdb0 @khduy has signed the CLA in code-yeongyu/oh-my-opencode#1297 2026-01-30 18:35:46 +00:00
justsisyphus
061a5f5132 refactor(momus): simplify prompt to prevent nitpicking and infinite loops
- Reduce prompt from 392 to 125 lines
- Add APPROVAL BIAS: approve by default, reject only for blockers
- Limit max 3 issues per rejection to prevent overwhelming feedback
- Remove 'ruthlessly critical' tone, add 'practical reviewer' approach
- Add explicit anti-patterns section for what NOT to reject
- Define 'good enough' criteria (80% clear = pass)
- Update tests to match simplified prompt structure
2026-01-31 00:51:51 +09:00
github-actions[bot]
d4acd23630 @KonaEspresso94 has signed the CLA in code-yeongyu/oh-my-opencode#1289 2026-01-30 15:33:41 +00:00
github-actions[bot]
c77c9ceb53 release: v3.1.9 2026-01-30 14:15:54 +00:00
YeonGyu-Kim
8c2625cfb0 🏆 test: optimize test suite with FakeTimers and race condition fixes (#1284)
* fix: exclude prompt/permission from plan agent config

plan agent should only inherit model settings from prometheus,
not the prompt or permission. This ensures plan agent uses
OpenCode's default behavior while only overriding the model.

* test(todo-continuation-enforcer): use FakeTimers for 15x faster tests

- Add custom FakeTimers implementation (~100 lines)
- Replace all real setTimeout waits with fakeTimers.advanceBy()
- Test time: 104.6s → 7.01s

* test(callback-server): fix race conditions with Promise.all and Bun.fetch

- Use Bun.fetch.bind(Bun) to avoid globalThis.fetch mock interference
- Use Promise.all pattern for concurrent fetch/waitForCallback
- Add Bun.sleep(10) in afterEach for port release

* test(concurrency): replace placeholder assertions with getCount checks

Replace 6 meaningless expect(true).toBe(true) assertions with
actual getCount() verifications for test quality improvement

* refactor(config-handler): simplify planDemoteConfig creation

Remove unnecessary IIFE and destructuring, use direct spread instead

* test(executor): use FakeTimeouts for faster tests

- Add custom FakeTimeouts implementation
- Replace setTimeout waits with fakeTimeouts.advanceBy()
- Test time reduced from ~26s to ~6.8s

* test: fix gemini model mock for artistry unstable mode

* test: fix model list mock payload shape

* test: mock provider models for artistry category

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-30 22:10:52 +09:00
github-actions[bot]
3ced20d1ab @kunal70006 has signed the CLA in code-yeongyu/oh-my-opencode#1282 2026-01-30 09:56:07 +00:00
github-actions[bot]
fb02cc9e95 @Zacks-Zhang has signed the CLA in code-yeongyu/oh-my-opencode#1280 2026-01-30 08:51:59 +00:00
justsisyphus
80ee52fe3b fix: improve model resolution with client API fallback and explicit model passing
- fetchAvailableModels now falls back to client.model.list() when cache is empty
- provider-models cache empty → models.json → client API (3-tier fallback)
- look-at tool explicitly passes registered agent's model to session.prompt
- Ensures multimodal-looker uses correctly resolved model (e.g., gemini-3-flash-preview)
- Add comprehensive tests for fuzzy matching and fallback scenarios
2026-01-30 16:57:21 +09:00
github-actions[bot]
2f7e188cb5 @Hisir0909 has signed the CLA in code-yeongyu/oh-my-opencode#1275 2026-01-30 07:33:44 +00:00
justsisyphus
f8be01c6dd test: update Atlas fallback test and misc code improvements
- Update Atlas fallback test to expect k2p5 as primary (kimi-for-coding)

- Minor improvements to connected-providers-cache and utils

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-30 16:19:02 +09:00
justsisyphus
0dbec08923 feat(cli): add kimi-for-coding provider to model fallback
- Add kimiForCoding field to ProviderAvailability interface

- Add kimi-for-coding provider mapping in isProviderAvailable

- Include kimi-for-coding in Sisyphus fallback chain for non-max plan

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-30 16:19:02 +09:00
justsisyphus
691fa8b815 refactor(sisyphus-junior): extract MODE constant and add export
- Add AgentMode type import and MODE constant

- Export mode on createSisyphusJuniorAgentWithOverrides function

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-30 16:19:02 +09:00
justsisyphus
a73d806d4e docs: update explore agent model and category descriptions
- Change explore agent from Grok Code to Claude Haiku 4.5

- Update deep category description for clarity

- Fix Momus fallback chain order

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-30 16:19:02 +09:00
justsisyphus
a424f81cd5 docs: update Sisyphus fallback chain across all documentation
Update Sisyphus fallback chain to include gpt-5.2-codex and gemini-3-pro

Files: AGENTS.md, README*.md, src/agents/AGENTS.md

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-30 16:19:02 +09:00
justsisyphus
1187a02020 fix: Atlas respects fallbackChain, always refresh provider-models cache
- Remove uiSelectedModel from Atlas model resolution (use k2p5 as primary)
- Always overwrite provider-models.json on session start to prevent stale cache
2026-01-30 16:19:02 +09:00
Junho Yeo
3074434887 fix: use correct gh api command for starring repo (#1274)
`gh repo star` is not a valid GitHub CLI command.
Use `gh api --silent --method PUT /user/starred/OWNER/REPO` instead.
2026-01-30 15:58:56 +09:00
justsisyphus
6bb2854162 Merge branch 'omo-avail' into dev 2026-01-30 15:28:20 +09:00
justsisyphus
e08904a27a feat: add artistry category to ultrawork-mode specialist delegation
- Add oracle vs artistry distinction in MANDATORY CERTAINTY PROTOCOL
- Update WHEN IN DOUBT examples with both delegation options
- Add artistry to IF YOU ENCOUNTER A BLOCKER section
- Add 'Hard problem (non-conventional)' row to AGENTS UTILIZATION table
- Update analyze-mode message with artistry specialist option

Oracle: conventional problems (architecture, debugging, complex logic)
Artistry: non-conventional problems (different approach needed)
2026-01-30 15:19:38 +09:00
justsisyphus
0188d69233 test: add requiresModel and isModelAvailable tests 2026-01-30 15:11:32 +09:00
justsisyphus
2c74f608f0 feat(delegate-task, agents): check requiresModel for conditional activation 2026-01-30 15:11:27 +09:00
justsisyphus
baefd16b3f feat(shared): add requiresModel field and isModelAvailable helper 2026-01-30 15:11:19 +09:00
justsisyphus
b1b4578906 feat: add opencode/kimi-k2.5-free fallback and prioritize kimi for atlas 2026-01-30 15:10:38 +09:00
justsisyphus
9d20a5b11c feat: add kimi-for-coding provider to installer and fix model ID to k2p5 2026-01-30 15:08:26 +09:00
justsisyphus
d2d8d1a782 feat: add kimi-k2.5 to agent fallback chains and update model catalog
- sisyphus: opus → kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro
- atlas: sonnet-4-5 → kimi-k2.5 → gpt-5.2 → gemini-3-pro
- prometheus/metis: opus → kimi-k2.5 → gpt-5.2 → gemini-3-pro
- multimodal-looker: gemini-flash → gpt-5.2 → glm-4.6v → kimi-k2.5 → haiku → gpt-5-nano
- visual-engineering: remove gpt-5.2 from chain
- ultrabrain: reorder to gpt-5.2-codex → gemini-3-pro → opus
- Add cross-provider fuzzy match for model resolution
- Update all documentation (AGENTS.md, features.md, configurations.md, category-skill-guide.md)
2026-01-30 14:53:50 +09:00
justsisyphus
10bdb6c694 chore: update artistry category description for creative problem-solving 2026-01-30 14:53:50 +09:00
justsisyphus
5f243e2d3a chore: add glm-4.7 to visual-engineering fallback chain 2026-01-30 14:53:50 +09:00
justsisyphus
82a47ff928 chore: add code style requirements to ultrabrain prompt
- MUST search existing codebase for patterns before writing code
- MUST match project's existing conventions
- MUST write readable, human-friendly code
2026-01-30 14:53:50 +09:00
justsisyphus
c06f38693e refactor: revamp ultrabrain category with deep work mindset
- Add variant: max to ultrabrain's gemini-3-pro fallback entry
- Rename STRATEGIC_CATEGORY_PROMPT_APPEND to ULTRABRAIN_CATEGORY_PROMPT_APPEND
- Keep original strategic advisor prompt content (no micromanagement instructions)
- Update description: use only for genuinely hard tasks, give clear goals only
- Update tests to match renamed constant
2026-01-30 14:53:50 +09:00
justsisyphus
6e9cb7ecd8 chore: add variant max to momus opus-4-5 fallback entry 2026-01-30 14:53:50 +09:00
justsisyphus
b731399edf chore: prioritize gemini-3-pro over opus in oracle fallback chain
- Move gemini-3-pro above claude-opus-4-5 in oracle's fallbackChain
- Add variant: "max" to gemini-3-pro entry
2026-01-30 14:53:50 +09:00
github-actions[bot]
0a28f6a790 @gabriel-ecegi has signed the CLA in code-yeongyu/oh-my-opencode#1271 2026-01-30 05:13:19 +00:00
justsisyphus
4e529b74e0 revert: remove unnecessary NODE_AUTH_TOKEN from publish.yml (OIDC works) 2026-01-30 13:54:46 +09:00
justsisyphus
90eec0a369 fix: add NODE_AUTH_TOKEN env to main publish workflow 2026-01-30 13:50:55 +09:00
justsisyphus
3b5d18e6bf fix(agents): exclude subagents from UI model selection override
Subagents (explore, librarian, oracle, etc.) now use their own fallback
chain instead of inheriting the UI-selected model. This fixes the issue
where explore agent was incorrectly using Opus instead of Haiku.

- Add AgentMode type and static mode property to AgentFactory
- Each agent declares its own mode via factory.mode = MODE pattern
- createBuiltinAgents() checks source.mode before passing uiSelectedModel
2026-01-30 13:49:40 +09:00
justsisyphus
67aeb9cb8c chore: replace big-pickle model with glm-4.7-free 2026-01-30 13:44:04 +09:00
justsisyphus
b1c1f02172 fix: add NODE_AUTH_TOKEN env to publish step 2026-01-30 13:36:20 +09:00
justsisyphus
2b39d119cd fix: restore registry-url for npm auth with new granular token 2026-01-30 13:21:35 +09:00
justsisyphus
afa2ece847 fix: remove registry-url from setup-node to enable OIDC auth 2026-01-30 13:11:44 +09:00
justsisyphus
390c25197f fix: manually create .npmrc without token for OIDC
setup-node with registry-url injects NODE_AUTH_TOKEN secret which is revoked.
Create .npmrc manually with empty _authToken to force OIDC authentication.
2026-01-30 12:57:15 +09:00
justsisyphus
9e07b143df fix: match main workflow's OIDC setup exactly
Main workflow works with registry-url + NPM_CONFIG_PROVENANCE.
Removed all extra env vars and debugging - simplify to match working pattern.
2026-01-30 12:52:57 +09:00
justsisyphus
ad95880198 fix(start-work): restore atlas agent and proper model fallback chain
- Restore agent: 'atlas' in start-work command (removed by PR #1201)
- Fix model-resolver to properly iterate through fallback chain providers
- Remove broken parent model inheritance that bypassed fallback logic
- Add model-suggestion-retry for runtime API failures (cherry-pick 800846c1)

Fixes #1200
2026-01-30 12:52:46 +09:00
justsisyphus
86088d3a6e fix: remove registry-url to enable npm OIDC auto-detection
- Remove registry-url from setup-node (was injecting NODE_AUTH_TOKEN)
- Add npm version check and auto-upgrade for OIDC support (11.5.1+)
- Add explicit --registry flag to npm publish
- Remove empty NODE_AUTH_TOKEN/NPM_CONFIG_USERCONFIG env vars that were breaking OIDC
2026-01-30 12:47:15 +09:00
justsisyphus
ae8a6c5eb8 refactor: replace console.log/warn/error with file-based log() for silent logging
Replace all console output with shared logger to write to
/tmp/oh-my-opencode.log instead of stdout/stderr.

Files changed:
- index.ts: console.warn → log()
- hook-message-injector/injector.ts: console.warn → log()
- lsp/client.ts: console.error → log()
- ast-grep/downloader.ts: console.log/error → log()
- session-recovery/index.ts: console.error → log()
- comment-checker/downloader.ts: console.log/error → log()

CLI tools (install.ts, doctor, etc.) retain console output for UX.
2026-01-30 12:45:37 +09:00
justsisyphus
db538c7e6b fix(ci): override env vars to disable token auth, force OIDC 2026-01-30 12:41:00 +09:00
justsisyphus
dfed2abd3e fix(ci): also remove NPM_CONFIG_USERCONFIG .npmrc and unset tokens for OIDC 2026-01-30 12:37:12 +09:00
justsisyphus
300a3fdc14 fix(ci): remove .npmrc to enable pure OIDC auth for npm publish 2026-01-30 12:33:51 +09:00
justsisyphus
c993cf007f fix(ci): remove registry-url to use pure OIDC auth for npm publish 2026-01-30 12:29:33 +09:00
justsisyphus
3d7de0a050 fix(publish-platform): use 7z on Windows, simplify skip logic 2026-01-30 12:25:30 +09:00
justsisyphus
8e19ffdce4 ci(publish-platform): separate build/publish jobs with OIDC provenance
- Split into two jobs: build (compile binaries) and publish (npm publish)
- Build job uploads compressed artifacts (tar.gz/zip)
- Publish job downloads artifacts and uses OIDC Trusted Publishing
- Removes NODE_AUTH_TOKEN dependency, uses npm provenance instead
- Increased timeout for large binary uploads (40-120MB)
- Build parallelism increased to 7 (all platforms simultaneously)
- Fixes npm classic token deprecation issue

Benefits:
- Fresh OIDC token at publish time avoids timeout issues
- No token rotation needed (OIDC is ephemeral)
- Build failures isolated from publish failures
- Artifacts can be reused if publish fails
2026-01-30 12:21:24 +09:00
github-actions[bot]
456d9cea65 release: v3.1.8 2026-01-30 02:58:12 +00:00
justsisyphus
30f893b766 fix(cli/run): fix [undefine] tag and add text preview to verbose log
- Fix sessionTag showing '[undefine]' when sessionID is undefined
  - System events now display as '[system]' instead
- Fix message.updated expecting non-existent 'content' field
  - SDK's EventMessageUpdated only contains info metadata, not content
  - Content is streamed via message.part.updated events
- Add text preview to message.part.updated verbose logging
- Update MessageUpdatedProps type to match SDK structure
- Update tests to reflect actual SDK behavior
2026-01-30 11:45:58 +09:00
justsisyphus
c905e1cb7a fix(delegate-task): restore resolved.model to category userModel chain (#1227)
PR #1227 incorrectly removed resolved.model from the userModel chain,
assuming it was bypassing the fallback chain. However, resolved.model
contained the category's DEFAULT_CATEGORIES model (e.g., quick ->
claude-haiku-4-5), not the main session model.

Without resolved.model, when connectedProvidersCache is null and
availableModels is empty, category model resolution falls through to
systemDefaultModel (opus) instead of using the category's default.

This fix restores the original priority:
1. User category model override
2. Category default model (from resolved.model)
3. sisyphusJuniorModel
4. Fallback chain
5. System default
2026-01-30 11:45:19 +09:00
YeonGyu-Kim
d3e2b36e3d refactor(tmux-subagent): introduce dependency injection for testability (#1267)
Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-30 10:59:54 +09:00
YeonGyu-Kim
5f0b6d49f5 fix(run): prevent premature exit on idle before meaningful work (#1263)
The run command's completion check had a race condition: when a session
transitions busy->idle before the LLM generates any output (empty
response or API delay), checkCompletionConditions() returns true because
0 incomplete todos + 0 busy children = complete. This caused the runner
to exit with 'All tasks completed' before any work was done.

Fix:
- Add hasReceivedMeaningfulWork flag to EventState
- Set flag on: assistant text content, tool execution, or message update
  with actual content (all scoped to main session only)
- Guard completion check in runner poll loop: skip if no meaningful work
  has been observed yet

This ensures the runner waits until the session has produced at least one
observable output before considering completion conditions.

Adds 6 new test cases covering the race condition scenarios.
2026-01-30 09:10:24 +09:00
github-actions[bot]
b45408dd9c @LeekJay has signed the CLA in code-yeongyu/oh-my-opencode#1254 2026-01-29 17:03:39 +00:00
github-actions[bot]
6c8527f29b release: v3.1.7 2026-01-29 12:39:22 +00:00
justsisyphus
cd4da93bf2 fix(test): migrate config-handler tests from mock.module to spyOn to prevent cross-file cache pollution 2026-01-29 21:35:14 +09:00
justsisyphus
71b2f1518a chore(agents): unify agent description format with OhMyOpenCode attribution 2026-01-29 21:27:04 +09:00
YeonGyu-Kim
dcda8769cc feat(mcp-oauth): add full OAuth 2.1 authentication for MCP servers (#1169)
* feat(mcp-oauth): add oauth field to ClaudeCodeMcpServer schema

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

* feat(mcp-oauth): add RFC 7591 Dynamic Client Registration

* feat(mcp-oauth): add RFC 9728 PRM + RFC 8414 AS discovery

* feat(mcp-oauth): add secure token storage with {host}/{resource} key format

* feat(mcp-oauth): add dynamic port OAuth callback server

* feat(mcp-oauth): add RFC 8707 Resource Indicators

* feat(mcp-oauth): implement full-spec McpOAuthProvider

* feat(mcp-oauth): add step-up authorization handler

* feat(mcp-oauth): integrate authProvider into SkillMcpManager

* feat(doctor): add MCP OAuth token status check

* feat(cli): add mcp oauth subcommand structure

* feat(cli): implement mcp oauth login command

* fix(mcp-oauth): address cubic review — security, correctness, and test issues

- Remove @ts-nocheck from provider.ts, storage.ts, provider.test.ts
- Fix server resource leak on missing code/state (close + reject)
- Fix command injection in openBrowser (spawn array args, cross-platform)
- Mock McpOAuthProvider in login.test.ts for deterministic CI
- Recreate auth provider with merged scopes in step-up flow
- Add listAllTokens() for global status listing
- Fix logout to accept --server-url for correct token deletion
- Support both quoted and unquoted WWW-Authenticate params (RFC 2617)
- Save/restore OPENCODE_CONFIG_DIR in storage.test.ts
- Fix index.test.ts: vitest → bun:test

* fix(mcp-oauth): use explorer instead of cmd /c start on Windows to prevent shell injection

* fix(mcp-oauth): address remaining cubic review issues

- Add 5-minute timeout to provider callback server to prevent indefinite hangs
- Persist client registration from token storage across process restarts
- Require --server-url for logout to match token storage key format
- Use listTokensByHost for server-specific status lookups
- Fix callback-server test to handle promise rejection ordering
- Fix provider test port expectations (8912 → 19877)
- Fix cli-guide.md duplicate Section 7 numbering
- Fix manager test for login-on-missing-tokens behavior

* fix(mcp-oauth): address final review issues

- P1: Redact token values in status.ts output to prevent credential leakage
- P2: Read OAuth error response body before throwing in token exchange
- Test: Fix mcp-oauth doctor test to use epoch seconds (not milliseconds)

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-29 19:48:36 +09:00
YeonGyu-Kim
a94fbadd57 Migrate LSP client to vscode-jsonrpc for improved stability (#1095)
* refactor(lsp): migrate to vscode-jsonrpc for improved stability

Replace custom JSON-RPC implementation with vscode-jsonrpc library.
Use MessageConnection with StreamMessageReader/Writer.
Implement Bun↔Node stream bridges for compatibility.
Preserve all existing functionality (warmup, cleanup, capabilities).
Net reduction of ~60 lines while improving protocol handling.

* fix(lsp): clear timeout on successful response to prevent unhandled rejections

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-29 19:48:28 +09:00
YeonGyu-Kim
23b49c4a5c fix: expand override.category and explicit reasoningEffort priority (#1219) (#1235)
* fix: expand override.category and explicit reasoningEffort priority (#1219)

Two bugs fixed:

1. createBuiltinAgents(): override.category was never expanded into concrete
   config properties (model, variant, reasoningEffort, etc.). Added
   applyCategoryOverride() helper and applied it in the standard agent loop,
   Sisyphus path, and Atlas path.

2. Prometheus config-handler: reasoningEffort/textVerbosity/thinking from
   direct override now use explicit priority chains (direct > category)
   matching the existing variant pattern, instead of relying on spread
   ordering.

Priority order (highest to lowest):
  1. Direct override properties
  2. Override category properties
  3. Resolved variant from model fallback chain
  4. Factory base defaults

Closes #1219

* fix: use undefined check for thinking to allow explicit false
2026-01-29 19:46:34 +09:00
YeonGyu-Kim
b4973954e3 fix(background-agent): prevent zombie processes by aborting sessions on shutdown (#1240) (#1243)
- BackgroundManager.shutdown() now aborts all running child sessions via
  client.session.abort() before clearing state, preventing orphaned
  opencode processes when parent exits
- Add onShutdown callback to BackgroundManager constructor, used to
  trigger TmuxSessionManager.cleanup() on process exit signals
- Interactive bash session hook now aborts tracked subagent opencode
  sessions when killing tmux sessions (defense-in-depth)
- Add 4 tests verifying shutdown abort behavior and callback invocation

Closes #1240
2026-01-29 18:29:47 +09:00
github-actions[bot]
6d50fbe563 @Lynricsy has signed the CLA in code-yeongyu/oh-my-opencode#1241 2026-01-29 09:00:40 +00:00
YeonGyu-Kim
9850dd0f6e fix(test): align agent tests with connected-providers-cache fallback behavior (#1227)
Tests in utils.test.ts were written before bffa1ad introduced
connected-providers-cache fallback in resolveModelWithFallback.
Update assertions to match the new resolution path:
- Oracle resolves to openai/gpt-5.2 via cache (not systemDefault)
- Agents are created via cache fallback even without systemDefaultModel
2026-01-29 11:47:17 +09:00
YeonGyu-Kim
34aaef2219 fix(delegate-task): pass registered agent model explicitly for subagent_type (#1225)
When delegate_task uses subagent_type, extract the matched agent's model
object and pass it explicitly to session.prompt/manager.launch. This
ensures the model is always in the correct object format regardless of
how OpenCode handles string→object conversion for plugin-registered
agents.

Closes #1225
2026-01-29 11:27:07 +09:00
Mike
faca80caa9 fix(start-work): prevent overwriting session agent if already set; inherit parent model for subagent types (#1201)
* fix(start-work): prevent overwriting session agent if already set; inherit parent model for subagent types

* fix(model): include variant in StoredMessage model structure for better context propagation

* fix(injector): include variant in model structure for hook message injection
2026-01-29 09:30:37 +09:00
SUHO LEE
0c3fbd724b fix(model-resolver): respect UI model selection in agent initialization (#1158)
- Add uiSelectedModel parameter to resolveModelWithFallback()
- Update model resolution priority: UI Selection → Config Override → Fallback → System Default
- Pass config.model as uiSelectedModel in createBuiltinAgents()
- Fix ProviderModelNotFoundError when model is unset in config but selected in UI
2026-01-29 09:30:35 +09:00
Srijan Guchhait
c7455708f8 docs: Add missing configuration options to configurations.md (#1186)
- Add disabled_commands section with available commands
- Add comment_checker configuration (custom_prompt)
- Add notification configuration (force_enable)
- Add sisyphus tasks & swarm configuration sections
- Add staleTimeoutMs to background_task section
- Add dynamic_context_pruning to experimental section with full documentation
- Extend skills configuration with advanced options (sources, custom skills)
- Extend agents configuration with missing options (category, variant, maxTokens, thinking, reasoningEffort, textVerbosity, providerOptions)
- Extend categories configuration with missing options (description, is_unstable_agent)
- Extend LSP configuration with missing server options (env, initialization, disabled) and detailed examples
- Add missing hooks (auto-slash-command, sisyphus-junior-notepad, start-work) to hooks list
- Update available agents list to include all agents from schema

Co-authored-by: GitHub Actions <actions@github.com>
2026-01-29 09:30:32 +09:00
Peïo Thibault
bffa1ad43d fix(model-resolver): use connected providers cache when model cache is empty (#1227)
- Remove resolved.model from userModel in tools.ts (was bypassing fallback chain)
- Use connected providers cache in model-resolver when availableModels is empty
- Allows proper provider selection (e.g., github-copilot instead of google)
2026-01-29 09:30:19 +09:00
github-actions[bot]
6560dedd4c @mrdavidlaing has signed the CLA in code-yeongyu/oh-my-opencode#1226 2026-01-28 19:51:45 +00:00
sisyphus-dev-ai
b7e32a99f2 chore: changes by sisyphus-dev-ai 2026-01-28 16:51:21 +00:00
github-actions[bot]
a06e656565 release: v3.1.6 2026-01-28 16:15:27 +00:00
justsisyphus
30ed086c40 fix(delegate-task): use category default model when availableModels is empty 2026-01-29 01:11:42 +09:00
justsisyphus
7c15b06da7 fix(test): update tests to reflect new model-resolver behavior 2026-01-29 00:54:16 +09:00
justsisyphus
0e7ee2ac30 chore: remove noisy console.warn for AGENTS.md auto-disable 2026-01-29 00:46:16 +09:00
justsisyphus
ca93d2f0fe fix(model-resolver): skip fallback chain when model availability cannot be verified
When model cache is empty, the fallback chain resolution was blindly
trusting connected providers without verifying if the model actually
exists. This caused errors when a provider (e.g., opencode) was marked
as connected but didn't have the requested model (e.g., claude-haiku-4-5).

Now skips fallback chain entirely when model cache is unavailable and
falls through to system default, letting OpenCode handle the resolution.
2026-01-29 00:15:57 +09:00
YeonGyu-Kim
3ab4529bc7 fix(look-at): handle JSON parse errors from session.prompt gracefully (#1216)
When multimodal-looker agent returns empty/malformed response, the SDK
throws 'JSON Parse error: Unexpected EOF'. This commit adds try-catch
around session.prompt() to provide user-friendly error message with
troubleshooting guidance.

- Add error handling for JSON parse errors with detailed guidance
- Add error handling for generic prompt failures
- Add test cases for both error scenarios
2026-01-28 23:58:01 +09:00
github-actions[bot]
9d3e152b19 @KennyDizi has signed the CLA in code-yeongyu/oh-my-opencode#1214 2026-01-28 14:26:21 +00:00
119 changed files with 7463 additions and 1187 deletions

View File

@@ -28,16 +28,20 @@ permissions:
id-token: write
jobs:
publish-platform:
# Use windows-latest for Windows to avoid cross-compilation segfault (oven-sh/bun#18416)
# Fixes: #873, #844
# =============================================================================
# Job 1: Build binaries for all platforms
# - Windows builds on windows-latest (avoid bun cross-compile segfault)
# - All other platforms build on ubuntu-latest
# - Uploads compressed artifacts for the publish job
# =============================================================================
build:
runs-on: ${{ matrix.platform == 'windows-x64' && 'windows-latest' || 'ubuntu-latest' }}
defaults:
run:
shell: bash
strategy:
fail-fast: false
max-parallel: 2
max-parallel: 7
matrix:
platform: [darwin-arm64, darwin-x64, linux-x64, linux-arm64, linux-x64-musl, linux-arm64-musl, windows-x64]
steps:
@@ -47,11 +51,6 @@ jobs:
with:
bun-version: latest
- uses: actions/setup-node@v4
with:
node-version: "24"
registry-url: "https://registry.npmjs.org"
- name: Install dependencies
run: bun install
env:
@@ -63,15 +62,20 @@ jobs:
PKG_NAME="oh-my-opencode-${{ matrix.platform }}"
VERSION="${{ inputs.version }}"
STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://registry.npmjs.org/${PKG_NAME}/${VERSION}")
# Convert platform name for output (replace - with _)
PLATFORM_KEY="${{ matrix.platform }}"
PLATFORM_KEY="${PLATFORM_KEY//-/_}"
if [ "$STATUS" = "200" ]; then
echo "skip=true" >> $GITHUB_OUTPUT
echo "skip_${PLATFORM_KEY}=true" >> $GITHUB_OUTPUT
echo "✓ ${PKG_NAME}@${VERSION} already published"
else
echo "skip=false" >> $GITHUB_OUTPUT
echo "skip_${PLATFORM_KEY}=false" >> $GITHUB_OUTPUT
echo "→ ${PKG_NAME}@${VERSION} needs publishing"
fi
- name: Update version
- name: Update version in package.json
if: steps.check.outputs.skip != 'true'
run: |
VERSION="${{ inputs.version }}"
@@ -99,15 +103,109 @@ jobs:
fi
bun build src/cli/index.ts --compile --minify --target=$TARGET --outfile=$OUTPUT
echo "Built binary:"
ls -lh "$OUTPUT"
- name: Compress binary
if: steps.check.outputs.skip != 'true'
run: |
PLATFORM="${{ matrix.platform }}"
cd packages/${PLATFORM}
if [ "$PLATFORM" = "windows-x64" ]; then
# Windows: use 7z (pre-installed on windows-latest)
7z a -tzip ../../binary-${PLATFORM}.zip bin/ package.json
else
# Unix: use tar.gz
tar -czvf ../../binary-${PLATFORM}.tar.gz bin/ package.json
fi
cd ../..
echo "Compressed artifact:"
ls -lh binary-${PLATFORM}.*
- name: Upload artifact
if: steps.check.outputs.skip != 'true'
uses: actions/upload-artifact@v4
with:
name: binary-${{ matrix.platform }}
path: |
binary-${{ matrix.platform }}.tar.gz
binary-${{ matrix.platform }}.zip
retention-days: 1
if-no-files-found: error
# =============================================================================
# Job 2: Publish all platforms using OIDC/Provenance
# - Runs on ubuntu-latest for ALL platforms (just downloading artifacts)
# - Uses npm Trusted Publishing (OIDC) - no NODE_AUTH_TOKEN needed
# - Fresh OIDC token at publish time avoids timeout issues
# =============================================================================
publish:
needs: build
runs-on: ubuntu-latest
strategy:
fail-fast: false
max-parallel: 2
matrix:
platform: [darwin-arm64, darwin-x64, linux-x64, linux-arm64, linux-x64-musl, linux-arm64-musl, windows-x64]
steps:
- name: Check if already published
id: check
run: |
PKG_NAME="oh-my-opencode-${{ matrix.platform }}"
VERSION="${{ inputs.version }}"
STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://registry.npmjs.org/${PKG_NAME}/${VERSION}")
if [ "$STATUS" = "200" ]; then
echo "skip=true" >> $GITHUB_OUTPUT
echo "✓ ${PKG_NAME}@${VERSION} already published, skipping"
else
echo "skip=false" >> $GITHUB_OUTPUT
echo "→ ${PKG_NAME}@${VERSION} will be published"
fi
- name: Download artifact
if: steps.check.outputs.skip != 'true'
uses: actions/download-artifact@v4
with:
name: binary-${{ matrix.platform }}
path: .
- name: Extract artifact
if: steps.check.outputs.skip != 'true'
run: |
PLATFORM="${{ matrix.platform }}"
mkdir -p packages/${PLATFORM}
if [ "$PLATFORM" = "windows-x64" ]; then
unzip binary-${PLATFORM}.zip -d packages/${PLATFORM}/
else
tar -xzvf binary-${PLATFORM}.tar.gz -C packages/${PLATFORM}/
fi
echo "Extracted contents:"
ls -la packages/${PLATFORM}/
ls -la packages/${PLATFORM}/bin/
- uses: actions/setup-node@v4
if: steps.check.outputs.skip != 'true'
with:
node-version: "24"
registry-url: "https://registry.npmjs.org"
- name: Publish ${{ matrix.platform }}
if: steps.check.outputs.skip != 'true'
run: |
cd packages/${{ matrix.platform }}
TAG_ARG=""
if [ -n "${{ inputs.dist_tag }}" ]; then
TAG_ARG="--tag ${{ inputs.dist_tag }}"
fi
npm publish --access public $TAG_ARG
npm publish --access public --provenance $TAG_ARG
env:
NPM_CONFIG_PROVENANCE: false
NODE_AUTH_TOKEN: ${{ secrets.NODE_AUTH_TOKEN }}
NPM_CONFIG_PROVENANCE: true
timeout-minutes: 15

1
.gitignore vendored
View File

@@ -33,3 +33,4 @@ yarn.lock
test-injection/
notepad.md
oauth-success.html
.188e87dbff6e7fd9-00000000.bun-build

View File

@@ -98,13 +98,13 @@ oh-my-opencode/
| Agent | Model | Purpose |
|-------|-------|---------|
| Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator |
| Atlas | anthropic/claude-opus-4-5 | Master orchestrator |
| Sisyphus | anthropic/claude-opus-4-5 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro) |
| Atlas | anthropic/claude-sonnet-4-5 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
| oracle | openai/gpt-5.2 | Consultation, debugging |
| librarian | opencode/big-pickle | Docs, GitHub search |
| explore | opencode/gpt-5-nano | Fast codebase grep |
| librarian | zai-coding-plan/glm-4.7 | Docs, GitHub search (fallback: glm-4.7-free) |
| explore | anthropic/claude-haiku-4-5 | Fast codebase grep (fallback: gpt-5-mini → gpt-5-nano) |
| multimodal-looker | google/gemini-3-flash | PDF/image analysis |
| Prometheus | anthropic/claude-opus-4-5 | Strategic planning |
| Prometheus | anthropic/claude-opus-4-5 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
## COMMANDS

View File

@@ -189,7 +189,7 @@ Windows から Linux に初めて乗り換えた時のこと、自分の思い
- Oracle: 設計、デバッグ (GPT 5.2 Medium)
- Frontend UI/UX Engineer: フロントエンド開発 (Gemini 3 Pro)
- Librarian: 公式ドキュメント、オープンソース実装、コードベース探索 (Claude Sonnet 4.5)
- Explore: 超高速コードベース探索 (Contextual Grep) (Grok Code)
- Explore: 超高速コードベース探索 (Contextual Grep) (Claude Haiku 4.5)
- Full LSP / AstGrep Support: 決定的にリファクタリングしましょう。
- Todo Continuation Enforcer: 途中で諦めたら、続行を強制します。これがシジフォスに岩を転がし続けさせる秘訣です。
- Comment Checker: AIが過剰なコメントを付けないようにします。シジフォスが生成したコードは、人間が書いたものと区別がつかないべきです。

View File

@@ -197,7 +197,7 @@ Hey please read this readme and tell me why it is different from other agent har
- Oracle: 디자인, 디버깅 (GPT 5.2 Medium)
- Frontend UI/UX Engineer: 프론트엔드 개발 (Gemini 3 Pro)
- Librarian: 공식 문서, 오픈 소스 구현, 코드베이스 탐색 (Claude Sonnet 4.5)
- Explore: 엄청나게 빠른 코드베이스 탐색 (Contextual Grep) (Grok Code)
- Explore: 엄청나게 빠른 코드베이스 탐색 (Contextual Grep) (Claude Haiku 4.5)
- 완전한 LSP / AstGrep 지원: 결정적으로 리팩토링합니다.
- TODO 연속 강제: 에이전트가 중간에 멈추면 계속하도록 강제합니다. **이것이 Sisyphus가 그 바위를 굴리게 하는 것입니다.**
- 주석 검사기: AI가 과도한 주석을 추가하는 것을 방지합니다. Sisyphus가 생성한 코드는 인간이 작성한 것과 구별할 수 없어야 합니다.

View File

@@ -196,7 +196,7 @@ Meet our main agent: Sisyphus (Opus 4.5 High). Below are the tools Sisyphus uses
- Oracle: Design, debugging (GPT 5.2 Medium)
- Frontend UI/UX Engineer: Frontend development (Gemini 3 Pro)
- Librarian: Official docs, open source implementations, codebase exploration (Claude Sonnet 4.5)
- Explore: Blazing fast codebase exploration (Contextual Grep) (Grok Code)
- Explore: Blazing fast codebase exploration (Contextual Grep) (Claude Haiku 4.5)
- Full LSP / AstGrep Support: Refactor decisively.
- Todo Continuation Enforcer: Forces the agent to continue if it quits halfway. **This is what keeps Sisyphus rolling that boulder.**
- Comment Checker: Prevents AI from adding excessive comments. Code generated by Sisyphus should be indistinguishable from human-written code.

View File

@@ -193,7 +193,7 @@
- Oracle设计、调试 (GPT 5.2 Medium)
- Frontend UI/UX Engineer前端开发 (Gemini 3 Pro)
- Librarian官方文档、开源实现、代码库探索 (Claude Sonnet 4.5)
- Explore极速代码库探索上下文感知 Grep(Grok Code)
- Explore极速代码库探索上下文感知 Grep(Claude Haiku 4.5)
- 完整 LSP / AstGrep 支持:果断重构。
- Todo 继续执行器:如果智能体中途退出,强制它继续。**这就是让 Sisyphus 继续推动巨石的关键。**
- 注释检查器:防止 AI 添加过多注释。Sisyphus 生成的代码应该与人类编写的代码无法区分。

View File

@@ -18,6 +18,7 @@
"jsonc-parser": "^3.3.1",
"picocolors": "^1.1.1",
"picomatch": "^4.0.2",
"vscode-jsonrpc": "^8.2.0",
"zod": "^4.1.8",
},
"devDependencies": {
@@ -27,13 +28,13 @@
"typescript": "^5.7.3",
},
"optionalDependencies": {
"oh-my-opencode-darwin-arm64": "3.1.2",
"oh-my-opencode-darwin-x64": "3.1.2",
"oh-my-opencode-linux-arm64": "3.1.2",
"oh-my-opencode-linux-arm64-musl": "3.1.2",
"oh-my-opencode-linux-x64": "3.1.2",
"oh-my-opencode-linux-x64-musl": "3.1.2",
"oh-my-opencode-windows-x64": "3.1.2",
"oh-my-opencode-darwin-arm64": "3.1.6",
"oh-my-opencode-darwin-x64": "3.1.6",
"oh-my-opencode-linux-arm64": "3.1.6",
"oh-my-opencode-linux-arm64-musl": "3.1.6",
"oh-my-opencode-linux-x64": "3.1.6",
"oh-my-opencode-linux-x64-musl": "3.1.6",
"oh-my-opencode-windows-x64": "3.1.6",
},
},
},
@@ -225,6 +226,20 @@
"object-inspect": ["object-inspect@1.13.4", "", {}, "sha512-W67iLl4J2EXEGTbfeHCffrjDfitvLANg0UlX3wFUUSTx92KXRFegMHUVgSqE+wvhAbi4WqjGg9czysTV2Epbew=="],
"oh-my-opencode-darwin-arm64": ["oh-my-opencode-darwin-arm64@3.1.6", "", { "os": "darwin", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-KK+ptnkBigvDYbRtF/B5izEC4IoXDS8mAnRHWFBSCINhzQR2No6AtEcwijd6vKBPR+/r71ofq/8mTsIeb1PEVQ=="],
"oh-my-opencode-darwin-x64": ["oh-my-opencode-darwin-x64@3.1.6", "", { "os": "darwin", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-UkPI/RUi7INarFasBUZ4Rous6RUQXsU2nr0V8KFJp+70END43D/96dDUwX+zmPtpDhD+DfWkejuwzqfkZJ2ZDQ=="],
"oh-my-opencode-linux-arm64": ["oh-my-opencode-linux-arm64@3.1.6", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-gvmvgh7WtTtcHiCbG7z43DOYfY/jrf2S6TX/jBMX2/e1AGkcLKwz30NjGhZxeK5SyzxRVypgfZZK1IuriRgbdA=="],
"oh-my-opencode-linux-arm64-musl": ["oh-my-opencode-linux-arm64-musl@3.1.6", "", { "os": "linux", "cpu": "arm64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-j3R76pmQ4HGVGFJUMMCeF/1lO3Jg7xFdpcBUKCeFh42N1jMgn1aeyxkAaJYB9RwCF/p6+P8B6gVDLCEDu2mxjA=="],
"oh-my-opencode-linux-x64": ["oh-my-opencode-linux-x64@3.1.6", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-VDdo0tHCOr5nm7ajd652u798nPNOLRSTcPOnVh6vIPddkZ+ujRke+enOKOw9Pd5e+4AkthqHBwFXNm2VFgnEKg=="],
"oh-my-opencode-linux-x64-musl": ["oh-my-opencode-linux-x64-musl@3.1.6", "", { "os": "linux", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode" } }, "sha512-hBG/dhsr8PZelUlYsPBruSLnelB9ocB7H92I+S9svTpDVo67rAmXOoR04twKQ9TeCO4ShOa6hhMhbQnuI8fgNw=="],
"oh-my-opencode-windows-x64": ["oh-my-opencode-windows-x64@3.1.6", "", { "os": "win32", "cpu": "x64", "bin": { "oh-my-opencode": "bin/oh-my-opencode.exe" } }, "sha512-c8Awp03p2DsbS0G589nzveRCeJPgJRJ0vQrha4ChRmmo31Qc5OSmJ5xuMaF8L4nM+/trbTgAQMFMtCMLgtC8IQ=="],
"on-finished": ["on-finished@2.4.1", "", { "dependencies": { "ee-first": "1.1.1" } }, "sha512-oVlzkg3ENAhCk2zdv7IJwd/QUD4z2RxRwpkcGY8psCVcCYZNq4wYnVWALHM+brtuJjePWiYF/ClmuDr8Ch5+kg=="],
"once": ["once@1.4.0", "", { "dependencies": { "wrappy": "1" } }, "sha512-lNaJgI+2Q5URQBkccEKHTQOPaXdUxnZZElQTZY0MFUAuaEqe1E+Nyvgdz/aIyNi6Z9MzO5dv1H8n58/GELp3+w=="],
@@ -289,6 +304,8 @@
"vary": ["vary@1.1.2", "", {}, "sha512-BNGbWLfd0eUPabhkXUVm0j8uuvREyTh5ovRa/dyow/BqAbZJyC+5fU+IzQOzmAKzYqYRAISoRhdQr3eIZ/PXqg=="],
"vscode-jsonrpc": ["vscode-jsonrpc@8.2.1", "", {}, "sha512-kdjOSJ2lLIn7r1rtrMbbNCHjyMPfRnowdKjBQ+mGq6NAW5QY2bEZC/khaC5OR8svbbjvLEaIXkOq45e2X9BIbQ=="],
"which": ["which@2.0.2", "", { "dependencies": { "isexe": "^2.0.0" }, "bin": { "node-which": "./bin/node-which" } }, "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA=="],
"wrappy": ["wrappy@1.0.2", "", {}, "sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ=="],

View File

@@ -23,6 +23,7 @@ A Category is an agent configuration preset optimized for specific domains.
|----------|---------------|-----------|
| `visual-engineering` | `google/gemini-3-pro` | Frontend, UI/UX, design, styling, animation |
| `ultrabrain` | `openai/gpt-5.2-codex` (xhigh) | Deep logical reasoning, complex architecture decisions requiring extensive analysis |
| `deep` | `openai/gpt-5.2-codex` (medium) | Goal-oriented autonomous problem-solving. Thorough research before action. For hairy problems requiring deep understanding. |
| `artistry` | `google/gemini-3-pro` (max) | Highly creative/artistic tasks, novel ideas |
| `quick` | `anthropic/claude-haiku-4-5` | Trivial tasks - single file changes, typo fixes, simple modifications |
| `unspecified-low` | `anthropic/claude-sonnet-4-5` | Tasks that don't fit other categories, low effort required |

View File

@@ -134,7 +134,41 @@ bunx oh-my-opencode run [prompt]
---
## 6. `auth` - Authentication Management
## 6. `mcp oauth` - MCP OAuth Management
Manages OAuth 2.1 authentication for remote MCP servers.
### Usage
```bash
# Login to an OAuth-protected MCP server
bunx oh-my-opencode mcp oauth login <server-name> --server-url https://api.example.com
# Login with explicit client ID and scopes
bunx oh-my-opencode mcp oauth login my-api --server-url https://api.example.com --client-id my-client --scopes "read,write"
# Remove stored OAuth tokens
bunx oh-my-opencode mcp oauth logout <server-name>
# Check OAuth token status
bunx oh-my-opencode mcp oauth status [server-name]
```
### Options
| Option | Description |
|--------|-------------|
| `--server-url <url>` | MCP server URL (required for login) |
| `--client-id <id>` | OAuth client ID (optional if server supports Dynamic Client Registration) |
| `--scopes <scopes>` | Comma-separated OAuth scopes |
### Token Storage
Tokens are stored in `~/.config/opencode/mcp-oauth.json` with `0600` permissions (owner read/write only). Key format: `{serverHost}/{resource}`.
---
## 7. `auth` - Authentication Management
Manages Google Antigravity OAuth authentication. Required for using Gemini models.
@@ -153,7 +187,7 @@ bunx oh-my-opencode auth status
---
## 7. Configuration Files
## 8. Configuration Files
The CLI searches for configuration files in the following locations (in priority order):
@@ -183,7 +217,7 @@ Configuration files support **JSONC (JSON with Comments)** format. You can use c
---
## 8. Troubleshooting
## 9. Troubleshooting
### "OpenCode version too old" Error
@@ -213,7 +247,7 @@ bunx oh-my-opencode doctor --category authentication
---
## 9. Non-Interactive Mode
## 10. Non-Interactive Mode
Use the `--no-tui` option for CI/CD environments.
@@ -227,7 +261,7 @@ bunx oh-my-opencode doctor --json > doctor-report.json
---
## 10. Developer Information
## 11. Developer Information
### CLI Structure

View File

@@ -163,7 +163,39 @@ Override built-in agent settings:
}
```
Each agent supports: `model`, `temperature`, `top_p`, `prompt`, `prompt_append`, `tools`, `disable`, `description`, `mode`, `color`, `permission`.
Each agent supports: `model`, `temperature`, `top_p`, `prompt`, `prompt_append`, `tools`, `disable`, `description`, `mode`, `color`, `permission`, `category`, `variant`, `maxTokens`, `thinking`, `reasoningEffort`, `textVerbosity`, `providerOptions`.
### Additional Agent Options
| Option | Type | Description |
| ------------------- | ------- | ----------------------------------------------------------------------------------------------- |
| `category` | string | Category name to inherit model and other settings from category defaults |
| `variant` | string | Model variant (e.g., `max`, `high`, `medium`, `low`, `xhigh`) |
| `maxTokens` | number | Maximum tokens for response. Passed directly to OpenCode SDK. |
| `thinking` | object | Extended thinking configuration for Anthropic models. See [Thinking Options](#thinking-options) below. |
| `reasoningEffort` | string | OpenAI reasoning effort level. Values: `low`, `medium`, `high`, `xhigh`. |
| `textVerbosity` | string | Text verbosity level. Values: `low`, `medium`, `high`. |
| `providerOptions` | object | Provider-specific options passed directly to OpenCode SDK. |
#### Thinking Options (Anthropic)
```json
{
"agents": {
"oracle": {
"thinking": {
"type": "enabled",
"budgetTokens": 200000
}
}
}
}
```
| Option | Type | Default | Description |
| ------------- | ------- | ------- | -------------------------------------------- |
| `type` | string | - | `enabled` or `disabled` |
| `budgetTokens`| number | - | Maximum budget tokens for extended thinking |
Use `prompt_append` to add extra instructions without replacing the default system prompt:
@@ -213,7 +245,7 @@ Or disable via `disabled_agents` in `~/.config/opencode/oh-my-opencode.json` or
}
```
Available agents: `oracle`, `librarian`, `explore`, `multimodal-looker`
Available agents: `sisyphus`, `prometheus`, `oracle`, `librarian`, `explore`, `multimodal-looker`, `metis`, `momus`, `atlas`
## Built-in Skills
@@ -232,6 +264,105 @@ Disable built-in skills via `disabled_skills` in `~/.config/opencode/oh-my-openc
Available built-in skills: `playwright`, `agent-browser`, `git-master`
## Skills Configuration
Configure advanced skills settings including custom skill sources, enabling/disabling specific skills, and defining custom skills.
```json
{
"skills": {
"sources": [
{ "path": "./custom-skills", "recursive": true },
"https://example.com/skill.yaml"
],
"enable": ["my-custom-skill"],
"disable": ["other-skill"],
"my-skill": {
"description": "Custom skill description",
"template": "Custom prompt template",
"from": "source-file.ts",
"model": "custom/model",
"agent": "custom-agent",
"subtask": true,
"argument-hint": "usage hint",
"license": "MIT",
"compatibility": ">= 3.0.0",
"metadata": {
"author": "Your Name"
},
"allowed-tools": ["tool1", "tool2"]
}
}
}
```
### Sources
Load skills from local directories or remote URLs:
```json
{
"skills": {
"sources": [
{ "path": "./custom-skills", "recursive": true },
{ "path": "./single-skill.yaml" },
"https://example.com/skill.yaml",
"https://raw.githubusercontent.com/user/repo/main/skills/*"
]
}
}
```
| Option | Default | Description |
| ----------- | ------- | ---------------------------------------------- |
| `path` | - | Local file/directory path or remote URL |
| `recursive` | `false` | Recursively load from directory |
| `glob` | - | Glob pattern for file selection |
### Enable/Disable Skills
```json
{
"skills": {
"enable": ["skill-1", "skill-2"],
"disable": ["disabled-skill"]
}
}
```
### Custom Skill Definition
Define custom skills directly in your config:
| Option | Default | Description |
| ---------------- | ------- | ------------------------------------------------------------------------------------ |
| `description` | - | Human-readable description of the skill |
| `template` | - | Custom prompt template for the skill |
| `from` | - | Source file to load template from |
| `model` | - | Override model for this skill |
| `agent` | - | Override agent for this skill |
| `subtask` | `false` | Whether to run as a subtask |
| `argument-hint` | - | Hint for how to use the skill |
| `license` | - | Skill license |
| `compatibility` | - | Required oh-my-opencode version compatibility |
| `metadata` | - | Additional metadata as key-value pairs |
| `allowed-tools` | - | Array of tools this skill is allowed to use |
**Example: Custom skill**
```json
{
"skills": {
"data-analyst": {
"description": "Specialized for data analysis tasks",
"template": "You are a data analyst. Focus on statistical analysis, visualization, and data interpretation.",
"model": "openai/gpt-5.2",
"allowed-tools": ["read", "bash", "lsp_diagnostics"]
}
}
}
```
## Browser Automation
Choose between two browser automation providers:
@@ -555,6 +686,7 @@ Configure concurrency limits for background agent tasks. This controls how many
{
"background_task": {
"defaultConcurrency": 5,
"staleTimeoutMs": 180000,
"providerConcurrency": {
"anthropic": 3,
"openai": 5,
@@ -571,6 +703,7 @@ Configure concurrency limits for background agent tasks. This controls how many
| Option | Default | Description |
| --------------------- | ------- | ----------------------------------------------------------------------------------------------------------------------- |
| `defaultConcurrency` | - | Default maximum concurrent background tasks for all providers/models |
| `staleTimeoutMs` | `180000` | Stale timeout in milliseconds - interrupt tasks with no activity for this duration (minimum: 60000 = 1 minute) |
| `providerConcurrency` | - | Per-provider concurrency limits. Keys are provider names (e.g., `anthropic`, `openai`, `google`) |
| `modelConcurrency` | - | Per-model concurrency limits. Keys are full model names (e.g., `anthropic/claude-opus-4-5`). Overrides provider limits. |
@@ -692,7 +825,14 @@ Add your own categories or override built-in ones:
}
```
Each category supports: `model`, `temperature`, `top_p`, `maxTokens`, `thinking`, `reasoningEffort`, `textVerbosity`, `tools`, `prompt_append`, `variant`.
Each category supports: `model`, `temperature`, `top_p`, `maxTokens`, `thinking`, `reasoningEffort`, `textVerbosity`, `tools`, `prompt_append`, `variant`, `description`, `is_unstable_agent`.
### Additional Category Options
| Option | Type | Default | Description |
| ------------------ | ------- | ------- | --------------------------------------------------------------------------------------------------- |
| `description` | string | - | Human-readable description of the category's purpose. Shown in delegate_task prompt. |
| `is_unstable_agent`| boolean | `false` | Mark agent as unstable - forces background mode for monitoring. Auto-enabled for gemini models. |
## Model Resolution System
@@ -754,15 +894,15 @@ Each agent has a defined provider priority chain. The system tries providers in
| Agent | Model (no prefix) | Provider Priority Chain |
|-------|-------------------|-------------------------|
| **Sisyphus** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
| **oracle** | `gpt-5.2` | openai → anthropic → google → github-copilot → opencode |
| **librarian** | `big-pickle` | opencode → github-copilot → anthropic |
| **explore** | `gpt-5-nano` | anthropic → opencode |
| **multimodal-looker** | `gemini-3-flash` | google → openai → zai-coding-plan → anthropic → opencode |
| **Prometheus (Planner)** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
| **Metis (Plan Consultant)** | `claude-sonnet-4-5` | anthropic → github-copilot → opencode → antigravity → google |
| **Momus (Plan Reviewer)** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
| **Atlas** | `claude-sonnet-4-5` | anthropic → github-copilot → opencode → antigravity → google |
| **Sisyphus** | `claude-opus-4-5` | anthropic → kimi-for-coding → zai-coding-plan → openai → google |
| **oracle** | `gpt-5.2` | openai → google → anthropic |
| **librarian** | `glm-4.7` | zai-coding-plan → opencode → anthropic |
| **explore** | `claude-haiku-4-5` | anthropic → github-copilot → opencode |
| **multimodal-looker** | `gemini-3-flash` | google → openai → zai-coding-plan → kimi-for-coding → anthropic → opencode |
| **Prometheus (Planner)** | `claude-opus-4-5` | anthropic → kimi-for-coding → openai → google |
| **Metis (Plan Consultant)** | `claude-opus-4-5` | anthropic → kimi-for-coding → openai → google |
| **Momus (Plan Reviewer)** | `gpt-5.2` | openai → anthropic → google |
| **Atlas** | `claude-sonnet-4-5` | anthropic → kimi-for-coding → openai → google |
### Category Provider Chains
@@ -770,13 +910,14 @@ Categories follow the same resolution logic:
| Category | Model (no prefix) | Provider Priority Chain |
|----------|-------------------|-------------------------|
| **visual-engineering** | `gemini-3-pro` | google → openai → anthropic → github-copilot → opencode |
| **ultrabrain** | `gpt-5.2-codex` | openai → anthropic → google → github-copilot → opencode |
| **artistry** | `gemini-3-pro` | google → openai → anthropic → github-copilot → opencode |
| **quick** | `claude-haiku-4-5` | anthropic → github-copilot → opencode → antigravity → google |
| **unspecified-low** | `claude-sonnet-4-5` | anthropic → github-copilot → opencode → antigravity → google |
| **unspecified-high** | `claude-opus-4-5` | anthropic → github-copilot → opencode → antigravity → google |
| **writing** | `gemini-3-flash` | google → openai → anthropic → github-copilot → opencode |
| **visual-engineering** | `gemini-3-pro` | google → anthropic → zai-coding-plan |
| **ultrabrain** | `gpt-5.2-codex` | openai → google → anthropic |
| **deep** | `gpt-5.2-codex` | openai → anthropic → google |
| **artistry** | `gemini-3-pro` | google → anthropic → openai |
| **quick** | `claude-haiku-4-5` | anthropic → google → opencode |
| **unspecified-low** | `claude-sonnet-4-5` | anthropic → openai → google |
| **unspecified-high** | `claude-opus-4-5` | anthropic → openai → google |
| **writing** | `gemini-3-flash` | google → anthropic → zai-coding-plan → openai |
### Checking Your Configuration
@@ -826,12 +967,93 @@ Disable specific built-in hooks via `disabled_hooks` in `~/.config/opencode/oh-m
}
```
Available hooks: `todo-continuation-enforcer`, `context-window-monitor`, `session-recovery`, `session-notification`, `comment-checker`, `grep-output-truncator`, `tool-output-truncator`, `directory-agents-injector`, `directory-readme-injector`, `empty-task-response-detector`, `think-mode`, `anthropic-context-window-limit-recovery`, `rules-injector`, `background-notification`, `auto-update-checker`, `startup-toast`, `keyword-detector`, `agent-usage-reminder`, `non-interactive-env`, `interactive-bash-session`, `compaction-context-injector`, `thinking-block-validator`, `claude-code-hooks`, `ralph-loop`, `preemptive-compaction`
Available hooks: `todo-continuation-enforcer`, `context-window-monitor`, `session-recovery`, `session-notification`, `comment-checker`, `grep-output-truncator`, `tool-output-truncator`, `directory-agents-injector`, `directory-readme-injector`, `empty-task-response-detector`, `think-mode`, `anthropic-context-window-limit-recovery`, `rules-injector`, `background-notification`, `auto-update-checker`, `startup-toast`, `keyword-detector`, `agent-usage-reminder`, `non-interactive-env`, `interactive-bash-session`, `compaction-context-injector`, `thinking-block-validator`, `claude-code-hooks`, `ralph-loop`, `preemptive-compaction`, `auto-slash-command`, `sisyphus-junior-notepad`, `start-work`
**Note on `directory-agents-injector`**: This hook is **automatically disabled** when running on OpenCode 1.1.37+ because OpenCode now has native support for dynamically resolving AGENTS.md files from subdirectories (PR #10678). This prevents duplicate AGENTS.md injection. For older OpenCode versions, the hook remains active to provide the same functionality.
**Note on `auto-update-checker` and `startup-toast`**: The `startup-toast` hook is a sub-feature of `auto-update-checker`. To disable only the startup toast notification while keeping update checking enabled, add `"startup-toast"` to `disabled_hooks`. To disable all update checking features (including the toast), add `"auto-update-checker"` to `disabled_hooks`.
## Disabled Commands
Disable specific built-in commands via `disabled_commands` in `~/.config/opencode/oh-my-opencode.json` or `.opencode/oh-my-opencode.json`:
```json
{
"disabled_commands": ["init-deep", "start-work"]
}
```
Available commands: `init-deep`, `start-work`
## Comment Checker
Configure comment-checker hook behavior. The comment checker warns when excessive comments are added to code.
```json
{
"comment_checker": {
"custom_prompt": "Your custom warning message. Use {{comments}} placeholder for detected comments XML."
}
}
```
| Option | Default | Description |
| ------------- | ------- | -------------------------------------------------------------------------- |
| `custom_prompt` | - | Custom warning message to replace the default. Use `{{comments}}` placeholder. |
## Notification
Configure notification behavior for background task completion.
```json
{
"notification": {
"force_enable": true
}
}
```
| Option | Default | Description |
| -------------- | ------- | ---------------------------------------------------------------------------------------------- |
| `force_enable` | `false` | Force enable session-notification even if external notification plugins are detected. Default: `false`. |
## Sisyphus Tasks & Swarm
Configure Sisyphus Tasks and Swarm systems for advanced task management and multi-agent orchestration.
```json
{
"sisyphus": {
"tasks": {
"enabled": false,
"storage_path": ".sisyphus/tasks",
"claude_code_compat": false
},
"swarm": {
"enabled": false,
"storage_path": ".sisyphus/teams",
"ui_mode": "toast"
}
}
}
```
### Tasks Configuration
| Option | Default | Description |
| -------------------- | ------------------ | ------------------------------------------------------------------------- |
| `enabled` | `false` | Enable Sisyphus Tasks system |
| `storage_path` | `.sisyphus/tasks` | Storage path for tasks (relative to project root) |
| `claude_code_compat` | `false` | Enable Claude Code path compatibility mode |
### Swarm Configuration
| Option | Default | Description |
| -------------- | ------------------ | -------------------------------------------------------------- |
| `enabled` | `false` | Enable Sisyphus Swarm system for multi-agent orchestration |
| `storage_path` | `.sisyphus/teams` | Storage path for teams (relative to project root) |
| `ui_mode` | `toast` | UI mode: `toast` (notifications), `tmux` (panes), or `both` |
## MCPs
Exa, Context7 and grep.app MCP enabled by default.
@@ -873,6 +1095,38 @@ Add LSP servers via the `lsp` option in `~/.config/opencode/oh-my-opencode.json`
Each server supports: `command`, `extensions`, `priority`, `env`, `initialization`, `disabled`.
| Option | Type | Default | Description |
| -------------- | -------- | ------- | ---------------------------------------------------------------------- |
| `command` | array | - | Command to start the LSP server (executable + args) |
| `extensions` | array | - | File extensions this server handles (e.g., `[".ts", ".tsx"]`) |
| `priority` | number | - | Server priority when multiple servers match a file |
| `env` | object | - | Environment variables for the LSP server (key-value pairs) |
| `initialization`| object | - | Custom initialization options passed to the LSP server |
| `disabled` | boolean | `false` | Whether to disable this LSP server |
**Example with advanced options:**
```json
{
"lsp": {
"typescript-language-server": {
"command": ["typescript-language-server", "--stdio"],
"extensions": [".ts", ".tsx"],
"priority": 10,
"env": {
"NODE_OPTIONS": "--max-old-space-size=4096"
},
"initialization": {
"preferences": {
"includeInlayParameterNameHints": "all",
"includeInlayFunctionParameterTypeHints": true
}
}
}
}
}
```
## Experimental
Opt-in experimental features that may change or be removed in future versions. Use with caution.
@@ -882,7 +1136,29 @@ Opt-in experimental features that may change or be removed in future versions. U
"experimental": {
"truncate_all_tool_outputs": true,
"aggressive_truncation": true,
"auto_resume": true
"auto_resume": true,
"dynamic_context_pruning": {
"enabled": false,
"notification": "detailed",
"turn_protection": {
"enabled": true,
"turns": 3
},
"protected_tools": ["task", "todowrite", "lsp_rename"],
"strategies": {
"deduplication": {
"enabled": true
},
"supersede_writes": {
"enabled": true,
"aggressive": false
},
"purge_errors": {
"enabled": true,
"turns": 5
}
}
}
}
}
```
@@ -891,7 +1167,72 @@ Opt-in experimental features that may change or be removed in future versions. U
| --------------------------- | ------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `truncate_all_tool_outputs` | `false` | Truncates ALL tool outputs instead of just whitelisted tools (Grep, Glob, LSP, AST-grep). Tool output truncator is enabled by default - disable via `disabled_hooks`. |
| `aggressive_truncation` | `false` | When token limit is exceeded, aggressively truncates tool outputs to fit within limits. More aggressive than the default truncation behavior. Falls back to summarize/revert if insufficient. |
| `auto_resume` | `false` | Automatically resumes session after successful recovery from thinking block errors or thinking disabled violations. Extracts the last user message and continues. |
| `auto_resume` | `false` | Automatically resumes session after successful recovery from thinking block errors or thinking disabled violations. Extracts last user message and continues. |
| `dynamic_context_pruning` | See below | Dynamic context pruning configuration for managing context window usage automatically. See [Dynamic Context Pruning](#dynamic-context-pruning) below. |
### Dynamic Context Pruning
Dynamic context pruning automatically manages context window by intelligently pruning old tool outputs. This feature helps maintain performance in long sessions.
```json
{
"experimental": {
"dynamic_context_pruning": {
"enabled": false,
"notification": "detailed",
"turn_protection": {
"enabled": true,
"turns": 3
},
"protected_tools": ["task", "todowrite", "todoread", "lsp_rename", "session_read", "session_write", "session_search"],
"strategies": {
"deduplication": {
"enabled": true
},
"supersede_writes": {
"enabled": true,
"aggressive": false
},
"purge_errors": {
"enabled": true,
"turns": 5
}
}
}
}
}
```
| Option | Default | Description |
| ----------------- | ------- | ----------------------------------------------------------------------------------------- |
| `enabled` | `false` | Enable dynamic context pruning |
| `notification` | `detailed` | Notification level: `off`, `minimal`, or `detailed` |
| `turn_protection` | See below | Turn protection settings - prevent pruning recent tool outputs |
#### Turn Protection
| Option | Default | Description |
| --------- | ------- | ------------------------------------------------------------ |
| `enabled` | `true` | Enable turn protection |
| `turns` | `3` | Number of recent turns to protect from pruning (1-10) |
#### Protected Tools
Tools that should never be pruned (default):
```json
["task", "todowrite", "todoread", "lsp_rename", "session_read", "session_write", "session_search"]
```
#### Pruning Strategies
| Strategy | Option | Default | Description |
| ------------------- | ------------ | ------- | ---------------------------------------------------------------------------- |
| **deduplication** | `enabled` | `true` | Remove duplicate tool calls (same tool + same args) |
| **supersede_writes**| `enabled` | `true` | Prune write inputs when file subsequently read |
| | `aggressive` | `false` | Aggressive mode: prune any write if ANY subsequent read |
| **purge_errors** | `enabled` | `true` | Prune errored tool inputs after N turns |
| | `turns` | `5` | Number of turns before pruning errors (1-20) |
**Warning**: These features are experimental and may cause unexpected behavior. Enable only if you understand the implications.

View File

@@ -10,19 +10,19 @@ Oh-My-OpenCode provides 10 specialized AI agents. Each has distinct expertise, o
| Agent | Model | Purpose |
|-------|-------|---------|
| **Sisyphus** | `anthropic/claude-opus-4-5` | **The default orchestrator.** Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). |
| **Sisyphus** | `anthropic/claude-opus-4-5` | **The default orchestrator.** Plans, delegates, and executes complex tasks using specialized subagents with aggressive parallel execution. Todo-driven workflow with extended thinking (32k budget). Fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro. |
| **oracle** | `openai/gpt-5.2` | Architecture decisions, code review, debugging. Read-only consultation - stellar logical reasoning and deep analysis. Inspired by AmpCode. |
| **librarian** | `opencode/big-pickle` | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Inspired by AmpCode. |
| **explore** | `opencode/gpt-5-nano` | Fast codebase exploration and contextual grep. Uses Gemini 3 Flash when Antigravity auth is configured, Haiku when Claude max20 is available, otherwise Grok. Inspired by Claude Code. |
| **multimodal-looker** | `google/gemini-3-flash` | Visual content specialist. Analyzes PDFs, images, diagrams to extract information. Saves tokens by having another agent process media. |
| **librarian** | `zai-coding-plan/glm-4.7` | Multi-repo analysis, documentation lookup, OSS implementation examples. Deep codebase understanding with evidence-based answers. Fallback: glm-4.7-free → claude-sonnet-4-5. |
| **explore** | `anthropic/claude-haiku-4-5` | Fast codebase exploration and contextual grep. Fallback: gpt-5-mini → gpt-5-nano. |
| **multimodal-looker** | `google/gemini-3-flash` | Visual content specialist. Analyzes PDFs, images, diagrams to extract information. Fallback: gpt-5.2 → glm-4.6v → kimi-k2.5 → claude-haiku-4-5 → gpt-5-nano. |
### Planning Agents
| Agent | Model | Purpose |
|-------|-------|---------|
| **Prometheus** | `anthropic/claude-opus-4-5` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. |
| **Metis** | `anthropic/claude-sonnet-4-5` | Plan consultant - pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. |
| **Momus** | `anthropic/claude-sonnet-4-5` | Plan reviewer - validates plans against clarity, verifiability, and completeness standards. |
| **Prometheus** | `anthropic/claude-opus-4-5` | Strategic planner with interview mode. Creates detailed work plans through iterative questioning. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
| **Metis** | `anthropic/claude-opus-4-5` | Plan consultant - pre-planning analysis. Identifies hidden intentions, ambiguities, and AI failure points. Fallback: kimi-k2.5 → gpt-5.2 → gemini-3-pro. |
| **Momus** | `openai/gpt-5.2` | Plan reviewer - validates plans against clarity, verifiability, and completeness standards. Fallback: gpt-5.2 → claude-opus-4-5 → gemini-3-pro. |
### Invoking Agents
@@ -521,6 +521,37 @@ mcp:
The `skill_mcp` tool invokes these operations with full schema discovery.
#### OAuth-Enabled MCPs
Skills can define OAuth-protected remote MCP servers. OAuth 2.1 with full RFC compliance (RFC 9728, 8414, 8707, 7591) is supported:
```yaml
---
description: My API skill
mcp:
my-api:
url: https://api.example.com/mcp
oauth:
clientId: ${CLIENT_ID}
scopes: ["read", "write"]
---
```
When a skill MCP has `oauth` configured:
- **Auto-discovery**: Fetches `/.well-known/oauth-protected-resource` (RFC 9728), falls back to `/.well-known/oauth-authorization-server` (RFC 8414)
- **Dynamic Client Registration**: Auto-registers with servers supporting RFC 7591 (clientId becomes optional)
- **PKCE**: Mandatory for all flows
- **Resource Indicators**: Auto-generated from MCP URL per RFC 8707
- **Token Storage**: Persisted in `~/.config/opencode/mcp-oauth.json` (chmod 0600)
- **Auto-refresh**: Tokens refresh on 401; step-up authorization on 403 with `WWW-Authenticate`
- **Dynamic Port**: OAuth callback server uses an auto-discovered available port
Pre-authenticate via CLI:
```bash
bunx oh-my-opencode mcp oauth login <server-name> --server-url https://api.example.com
```
---
## Context Injection

View File

@@ -213,7 +213,7 @@ If Z.ai is the only provider available, all agents will use GLM models:
#### OpenCode Zen
OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-5`, `opencode/gpt-5.2`, `opencode/gpt-5-nano`, and `opencode/big-pickle`.
OpenCode Zen provides access to `opencode/` prefixed models including `opencode/claude-opus-4-5`, `opencode/gpt-5.2`, `opencode/gpt-5-nano`, and `opencode/glm-4.7-free`.
When OpenCode Zen is the best available provider (no native or Copilot), these models are used:
@@ -222,7 +222,7 @@ When OpenCode Zen is the best available provider (no native or Copilot), these m
| **Sisyphus** | `opencode/claude-opus-4-5` |
| **Oracle** | `opencode/gpt-5.2` |
| **Explore** | `opencode/gpt-5-nano` |
| **Librarian** | `opencode/big-pickle` |
| **Librarian** | `opencode/glm-4.7-free` |
##### Setup
@@ -278,7 +278,7 @@ After everything is set up and working, ask the user:
If the user agrees, run:
```bash
gh repo star code-yeongyu/oh-my-opencode
gh api --silent --method PUT /user/starred/code-yeongyu/oh-my-opencode >/dev/null 2>&1 || true
```
**Important**: Only run the command if the user explicitly says yes. Never run it automatically without consent.

View File

@@ -1,6 +1,6 @@
{
"name": "oh-my-opencode",
"version": "3.1.5",
"version": "3.1.10",
"description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
"main": "dist/index.js",
"types": "dist/index.d.ts",
@@ -64,6 +64,7 @@
"jsonc-parser": "^3.3.1",
"picocolors": "^1.1.1",
"picomatch": "^4.0.2",
"vscode-jsonrpc": "^8.2.0",
"zod": "^4.1.8"
},
"devDependencies": {
@@ -73,13 +74,13 @@
"typescript": "^5.7.3"
},
"optionalDependencies": {
"oh-my-opencode-darwin-arm64": "3.1.5",
"oh-my-opencode-darwin-x64": "3.1.5",
"oh-my-opencode-linux-arm64": "3.1.5",
"oh-my-opencode-linux-arm64-musl": "3.1.5",
"oh-my-opencode-linux-x64": "3.1.5",
"oh-my-opencode-linux-x64-musl": "3.1.5",
"oh-my-opencode-windows-x64": "3.1.5"
"oh-my-opencode-darwin-arm64": "3.1.10",
"oh-my-opencode-darwin-x64": "3.1.10",
"oh-my-opencode-linux-arm64": "3.1.10",
"oh-my-opencode-linux-arm64-musl": "3.1.10",
"oh-my-opencode-linux-x64": "3.1.10",
"oh-my-opencode-linux-x64-musl": "3.1.10",
"oh-my-opencode-windows-x64": "3.1.10"
},
"trustedDependencies": [
"@ast-grep/cli",

View File

@@ -1,6 +1,6 @@
{
"name": "oh-my-opencode-darwin-arm64",
"version": "3.1.5",
"version": "3.1.10",
"description": "Platform-specific binary for oh-my-opencode (darwin-arm64)",
"license": "MIT",
"repository": {

View File

@@ -1,6 +1,6 @@
{
"name": "oh-my-opencode-darwin-x64",
"version": "3.1.5",
"version": "3.1.10",
"description": "Platform-specific binary for oh-my-opencode (darwin-x64)",
"license": "MIT",
"repository": {

View File

@@ -1,6 +1,6 @@
{
"name": "oh-my-opencode-linux-arm64-musl",
"version": "3.1.5",
"version": "3.1.10",
"description": "Platform-specific binary for oh-my-opencode (linux-arm64-musl)",
"license": "MIT",
"repository": {

View File

@@ -1,6 +1,6 @@
{
"name": "oh-my-opencode-linux-arm64",
"version": "3.1.5",
"version": "3.1.10",
"description": "Platform-specific binary for oh-my-opencode (linux-arm64)",
"license": "MIT",
"repository": {

View File

@@ -1,6 +1,6 @@
{
"name": "oh-my-opencode-linux-x64-musl",
"version": "3.1.5",
"version": "3.1.10",
"description": "Platform-specific binary for oh-my-opencode (linux-x64-musl)",
"license": "MIT",
"repository": {

View File

@@ -1,6 +1,6 @@
{
"name": "oh-my-opencode-linux-x64",
"version": "3.1.5",
"version": "3.1.10",
"description": "Platform-specific binary for oh-my-opencode (linux-x64)",
"license": "MIT",
"repository": {

View File

@@ -1,6 +1,6 @@
{
"name": "oh-my-opencode-windows-x64",
"version": "3.1.5",
"version": "3.1.10",
"description": "Platform-specific binary for oh-my-opencode (windows-x64)",
"license": "MIT",
"repository": {

View File

@@ -943,6 +943,94 @@
"created_at": "2026-01-28T13:04:16Z",
"repoId": 1108837393,
"pullRequestNo": 1203
},
{
"name": "KennyDizi",
"id": 16578966,
"comment_id": 3811619818,
"created_at": "2026-01-28T14:26:10Z",
"repoId": 1108837393,
"pullRequestNo": 1214
},
{
"name": "mrdavidlaing",
"id": 227505,
"comment_id": 3813542625,
"created_at": "2026-01-28T19:51:34Z",
"repoId": 1108837393,
"pullRequestNo": 1226
},
{
"name": "Lynricsy",
"id": 62173814,
"comment_id": 3816370548,
"created_at": "2026-01-29T09:00:28Z",
"repoId": 1108837393,
"pullRequestNo": 1241
},
{
"name": "LeekJay",
"id": 39609783,
"comment_id": 3819009761,
"created_at": "2026-01-29T17:03:24Z",
"repoId": 1108837393,
"pullRequestNo": 1254
},
{
"name": "gabriel-ecegi",
"id": 35489017,
"comment_id": 3821842363,
"created_at": "2026-01-30T05:13:15Z",
"repoId": 1108837393,
"pullRequestNo": 1271
},
{
"name": "Hisir0909",
"id": 76634394,
"comment_id": 3822248445,
"created_at": "2026-01-30T07:20:09Z",
"repoId": 1108837393,
"pullRequestNo": 1275
},
{
"name": "Zacks-Zhang",
"id": 16462428,
"comment_id": 3822585754,
"created_at": "2026-01-30T08:51:49Z",
"repoId": 1108837393,
"pullRequestNo": 1280
},
{
"name": "kunal70006",
"id": 62700112,
"comment_id": 3822849937,
"created_at": "2026-01-30T09:55:57Z",
"repoId": 1108837393,
"pullRequestNo": 1282
},
{
"name": "KonaEspresso94",
"id": 140197941,
"comment_id": 3824340432,
"created_at": "2026-01-30T15:33:28Z",
"repoId": 1108837393,
"pullRequestNo": 1289
},
{
"name": "khduy",
"id": 48742864,
"comment_id": 3825103158,
"created_at": "2026-01-30T18:35:34Z",
"repoId": 1108837393,
"pullRequestNo": 1297
},
{
"name": "robin-watcha",
"id": 90032965,
"comment_id": 3826133640,
"created_at": "2026-01-30T22:37:32Z",
"repoId": 1108837393,
"pullRequestNo": 1303
}
]
}

View File

@@ -25,15 +25,15 @@ agents/
## AGENT MODELS
| Agent | Model | Temp | Purpose |
|-------|-------|------|---------|
| Sisyphus | anthropic/claude-opus-4-5 | 0.1 | Primary orchestrator |
| Atlas | anthropic/claude-opus-4-5 | 0.1 | Master orchestrator |
| Sisyphus | anthropic/claude-opus-4-5 | 0.1 | Primary orchestrator (fallback: kimi-k2.5 → glm-4.7 → gpt-5.2-codex → gemini-3-pro) |
| Atlas | anthropic/claude-sonnet-4-5 | 0.1 | Master orchestrator (fallback: kimi-k2.5 → gpt-5.2) |
| oracle | openai/gpt-5.2 | 0.1 | Consultation, debugging |
| librarian | opencode/big-pickle | 0.1 | Docs, GitHub search |
| explore | opencode/gpt-5-nano | 0.1 | Fast contextual grep |
| librarian | zai-coding-plan/glm-4.7 | 0.1 | Docs, GitHub search (fallback: glm-4.7-free) |
| explore | anthropic/claude-haiku-4-5 | 0.1 | Fast contextual grep (fallback: gpt-5-mini → gpt-5-nano) |
| multimodal-looker | google/gemini-3-flash | 0.1 | PDF/image analysis |
| Prometheus | anthropic/claude-opus-4-5 | 0.1 | Strategic planning |
| Metis | anthropic/claude-sonnet-4-5 | 0.3 | Pre-planning analysis |
| Momus | anthropic/claude-sonnet-4-5 | 0.1 | Plan validation |
| Prometheus | anthropic/claude-opus-4-5 | 0.1 | Strategic planning (fallback: kimi-k2.5 → gpt-5.2) |
| Metis | anthropic/claude-opus-4-5 | 0.3 | Pre-planning analysis (fallback: kimi-k2.5 → gpt-5.2) |
| Momus | openai/gpt-5.2 | 0.1 | Plan validation (fallback: claude-opus-4-5) |
| Sisyphus-Junior | anthropic/claude-sonnet-4-5 | 0.1 | Category-spawned executor |
## HOW TO ADD

View File

@@ -1,5 +1,7 @@
import type { AgentConfig } from "@opencode-ai/sdk"
import type { AgentPromptMetadata } from "./types"
import type { AgentMode, AgentPromptMetadata } from "./types"
const MODE: AgentMode = "primary"
import type { AvailableAgent, AvailableSkill, AvailableCategory } from "./dynamic-agent-prompt-builder"
import { buildCategorySkillsDelegationGuide } from "./dynamic-agent-prompt-builder"
import type { CategoryConfig } from "../config/schema"
@@ -529,8 +531,8 @@ export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
])
return {
description:
"Orchestrates work via delegate_task() to complete ALL tasks in a todo list until fully done",
mode: "primary" as const,
"Orchestrates work via delegate_task() to complete ALL tasks in a todo list until fully done. (Atlas - OhMyOpenCode)",
mode: MODE,
...(ctx.model ? { model: ctx.model } : {}),
temperature: 0.1,
prompt: buildDynamicOrchestratorPrompt(ctx),
@@ -539,6 +541,7 @@ export function createAtlasAgent(ctx: OrchestratorContext): AgentConfig {
...restrictions,
} as AgentConfig
}
createAtlasAgent.mode = MODE
export const atlasPromptMetadata: AgentPromptMetadata = {
category: "advisor",

View File

@@ -1,7 +1,9 @@
import type { AgentConfig } from "@opencode-ai/sdk"
import type { AgentPromptMetadata } from "./types"
import type { AgentMode, AgentPromptMetadata } from "./types"
import { createAgentToolRestrictions } from "../shared/permission-compat"
const MODE: AgentMode = "subagent"
export const EXPLORE_PROMPT_METADATA: AgentPromptMetadata = {
category: "exploration",
cost: "FREE",
@@ -33,8 +35,8 @@ export function createExploreAgent(model: string): AgentConfig {
return {
description:
'Contextual grep for codebases. Answers "Where is X?", "Which file has Y?", "Find the code that does Z". Fire multiple in parallel for broad searches. Specify thoroughness: "quick" for basic, "medium" for moderate, "very thorough" for comprehensive analysis.',
mode: "subagent" as const,
'Contextual grep for codebases. Answers "Where is X?", "Which file has Y?", "Find the code that does Z". Fire multiple in parallel for broad searches. Specify thoroughness: "quick" for basic, "medium" for moderate, "very thorough" for comprehensive analysis. (Explore - OhMyOpenCode)',
mode: MODE,
model,
temperature: 0.1,
...restrictions,
@@ -119,4 +121,4 @@ Use the right tool for the job:
Flood with parallel calls. Cross-validate findings across multiple tools.`,
}
}
createExploreAgent.mode = MODE

View File

@@ -1,7 +1,9 @@
import type { AgentConfig } from "@opencode-ai/sdk"
import type { AgentPromptMetadata } from "./types"
import type { AgentMode, AgentPromptMetadata } from "./types"
import { createAgentToolRestrictions } from "../shared/permission-compat"
const MODE: AgentMode = "subagent"
export const LIBRARIAN_PROMPT_METADATA: AgentPromptMetadata = {
category: "exploration",
cost: "CHEAP",
@@ -30,8 +32,8 @@ export function createLibrarianAgent(model: string): AgentConfig {
return {
description:
"Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. MUST BE USED when users ask to look up code in remote repositories, explain library internals, or find usage examples in open source.",
mode: "subagent" as const,
"Specialized codebase understanding agent for multi-repository analysis, searching remote codebases, retrieving official documentation, and finding implementation examples using GitHub CLI, Context7, and Web Search. MUST BE USED when users ask to look up code in remote repositories, explain library internals, or find usage examples in open source. (Librarian - OhMyOpenCode)",
mode: MODE,
model,
temperature: 0.1,
...restrictions,
@@ -323,4 +325,4 @@ grep_app_searchGitHub(query: "useQuery")
`,
}
}
createLibrarianAgent.mode = MODE

View File

@@ -1,7 +1,9 @@
import type { AgentConfig } from "@opencode-ai/sdk"
import type { AgentPromptMetadata } from "./types"
import type { AgentMode, AgentPromptMetadata } from "./types"
import { createAgentToolRestrictions } from "../shared/permission-compat"
const MODE: AgentMode = "subagent"
/**
* Metis - Plan Consultant Agent
*
@@ -310,8 +312,8 @@ const metisRestrictions = createAgentToolRestrictions([
export function createMetisAgent(model: string): AgentConfig {
return {
description:
"Pre-planning consultant that analyzes requests to identify hidden intentions, ambiguities, and AI failure points.",
mode: "subagent" as const,
"Pre-planning consultant that analyzes requests to identify hidden intentions, ambiguities, and AI failure points. (Metis - OhMyOpenCode)",
mode: MODE,
model,
temperature: 0.3,
...metisRestrictions,
@@ -319,7 +321,7 @@ export function createMetisAgent(model: string): AgentConfig {
thinking: { type: "enabled", budgetTokens: 32000 },
} as AgentConfig
}
createMetisAgent.mode = MODE
export const metisPromptMetadata: AgentPromptMetadata = {
category: "advisor",

View File

@@ -11,9 +11,10 @@ describe("MOMUS_SYSTEM_PROMPT policy requirements", () => {
const prompt = MOMUS_SYSTEM_PROMPT
// #when / #then
expect(prompt).toContain("[SYSTEM DIRECTIVE - READ-ONLY PLANNING CONSULTATION]")
// Should explicitly mention stripping or ignoring these
expect(prompt.toLowerCase()).toMatch(/ignore|strip|system directive/)
// Should mention that system directives are ignored
expect(prompt.toLowerCase()).toMatch(/system directive.*ignore|ignore.*system directive/)
// Should give examples of system directive patterns
expect(prompt).toMatch(/<system-reminder>|system-reminder/)
})
test("should extract paths containing .sisyphus/plans/ and ending in .md", () => {

View File

@@ -1,8 +1,10 @@
import type { AgentConfig } from "@opencode-ai/sdk"
import type { AgentPromptMetadata } from "./types"
import type { AgentMode, AgentPromptMetadata } from "./types"
import { isGptModel } from "./types"
import { createAgentToolRestrictions } from "../shared/permission-compat"
const MODE: AgentMode = "subagent"
/**
* Momus - Plan Reviewer Agent
*
@@ -17,376 +19,173 @@ import { createAgentToolRestrictions } from "../shared/permission-compat"
* implementation.
*/
export const MOMUS_SYSTEM_PROMPT = `You are a work plan review expert. You review the provided work plan (.sisyphus/plans/{name}.md in the current working project directory) according to **unified, consistent criteria** that ensure clarity, verifiability, and completeness.
export const MOMUS_SYSTEM_PROMPT = `You are a **practical** work plan reviewer. Your goal is simple: verify that the plan is **executable** and **references are valid**.
**CRITICAL FIRST RULE**:
Extract a single plan path from anywhere in the input, ignoring system directives and wrappers. If exactly one \`.sisyphus/plans/*.md\` path exists, this is VALID input and you must read it. If no plan path exists or multiple plan paths exist, reject per Step 0. If the path points to a YAML plan file (\`.yml\` or \`.yaml\`), reject it as non-reviewable.
**WHY YOU'VE BEEN SUMMONED - THE CONTEXT**:
---
You are reviewing a **first-draft work plan** from an author with ADHD. Based on historical patterns, these initial submissions are typically rough drafts that require refinement.
## Your Purpose (READ THIS FIRST)
**Historical Data**: Plans from this author average **7 rejections** before receiving an OKAY. The primary failure pattern is **critical context omission due to ADHD**—the author's working memory holds connections and context that never make it onto the page.
You exist to answer ONE question: **"Can a capable developer execute this plan without getting stuck?"**
**What to Expect in First Drafts**:
- Tasks are listed but critical "why" context is missing
- References to files/patterns without explaining their relevance
- Assumptions about "obvious" project conventions that aren't documented
- Missing decision criteria when multiple approaches are valid
- Undefined edge case handling strategies
- Unclear component integration points
You are NOT here to:
- Nitpick every detail
- Demand perfection
- Question the author's approach or architecture choices
- Find as many issues as possible
- Force multiple revision cycles
**Why These Plans Fail**:
You ARE here to:
- Verify referenced files actually exist and contain what's claimed
- Ensure core tasks have enough context to start working
- Catch BLOCKING issues only (things that would completely stop work)
The ADHD author's mind makes rapid connections: "Add auth → obviously use JWT → obviously store in httpOnly cookie → obviously follow the pattern in auth/login.ts → obviously handle refresh tokens like we did before."
But the plan only says: "Add authentication following auth/login.ts pattern."
**Everything after the first arrow is missing.** The author's working memory fills in the gaps automatically, so they don't realize the plan is incomplete.
**Your Critical Role**: Catch these ADHD-driven omissions. The author genuinely doesn't realize what they've left out. Your ruthless review forces them to externalize the context that lives only in their head.
**APPROVAL BIAS**: When in doubt, APPROVE. A plan that's 80% clear is good enough. Developers can figure out minor gaps.
---
## Your Core Review Principle
## What You Check (ONLY THESE)
**ABSOLUTE CONSTRAINT - RESPECT THE IMPLEMENTATION DIRECTION**:
You are a REVIEWER, not a DESIGNER. The implementation direction in the plan is **NOT NEGOTIABLE**. Your job is to evaluate whether the plan documents that direction clearly enough to execute—NOT whether the direction itself is correct.
### 1. Reference Verification (CRITICAL)
- Do referenced files exist?
- Do referenced line numbers contain relevant code?
- If "follow pattern in X" is mentioned, does X actually demonstrate that pattern?
**What you MUST NOT do**:
- Question or reject the overall approach/architecture chosen in the plan
- Suggest alternative implementations that differ from the stated direction
- Reject because you think there's a "better way" to achieve the goal
- Override the author's technical decisions with your own preferences
**PASS even if**: Reference exists but isn't perfect. Developer can explore from there.
**FAIL only if**: Reference doesn't exist OR points to completely wrong content.
**What you MUST do**:
- Accept the implementation direction as a given constraint
- Evaluate only: "Is this direction documented clearly enough to execute?"
- Focus on gaps IN the chosen approach, not gaps in choosing the approach
### 2. Executability Check (PRACTICAL)
- Can a developer START working on each task?
- Is there at least a starting point (file, pattern, or clear description)?
**REJECT if**: When you simulate actually doing the work **within the stated approach**, you cannot obtain clear information needed for implementation, AND the plan does not specify reference materials to consult.
**PASS even if**: Some details need to be figured out during implementation.
**FAIL only if**: Task is so vague that developer has NO idea where to begin.
**ACCEPT if**: You can obtain the necessary information either:
1. Directly from the plan itself, OR
2. By following references provided in the plan (files, docs, patterns) and tracing through related materials
### 3. Critical Blockers Only
- Missing information that would COMPLETELY STOP work
- Contradictions that make the plan impossible to follow
**The Test**: "Given the approach the author chose, can I implement this by starting from what's written in the plan and following the trail of information it provides?"
**WRONG mindset**: "This approach is suboptimal. They should use X instead." → **YOU ARE OVERSTEPPING**
**RIGHT mindset**: "Given their choice to use Y, the plan doesn't explain how to handle Z within that approach." → **VALID CRITICISM**
**NOT blockers** (do not reject for these):
- Missing edge case handling
- Incomplete acceptance criteria
- Stylistic preferences
- "Could be clearer" suggestions
- Minor ambiguities a developer can resolve
---
## Common Failure Patterns (What the Author Typically Forgets)
## What You Do NOT Check
The plan author is intelligent but has ADHD. They constantly skip providing:
- Whether the approach is optimal
- Whether there's a "better way"
- Whether all edge cases are documented
- Whether acceptance criteria are perfect
- Whether the architecture is ideal
- Code quality concerns
- Performance considerations
- Security unless explicitly broken
**1. Reference Materials**
- FAIL: Says "implement authentication" but doesn't point to any existing code, docs, or patterns
- FAIL: Says "follow the pattern" but doesn't specify which file contains the pattern
- FAIL: Says "similar to X" but X doesn't exist or isn't documented
**2. Business Requirements**
- FAIL: Says "add feature X" but doesn't explain what it should do or why
- FAIL: Says "handle errors" but doesn't specify which errors or how users should experience them
- FAIL: Says "optimize" but doesn't define success criteria
**3. Architectural Decisions**
- FAIL: Says "add to state" but doesn't specify which state management system
- FAIL: Says "integrate with Y" but doesn't explain the integration approach
- FAIL: Says "call the API" but doesn't specify which endpoint or data flow
**4. Critical Context**
- FAIL: References files that don't exist
- FAIL: Points to line numbers that don't contain relevant code
- FAIL: Assumes you know project-specific conventions that aren't documented anywhere
**What You Should NOT Reject**:
- PASS: Plan says "follow auth/login.ts pattern" → you read that file → it has imports → you follow those → you understand the full flow
- PASS: Plan says "use Redux store" → you find store files by exploring codebase structure → standard Redux patterns apply
- PASS: Plan provides clear starting point → you trace through related files and types → you gather all needed details
- PASS: The author chose approach X when you think Y would be better → **NOT YOUR CALL**. Evaluate X on its own merits.
- PASS: The architecture seems unusual or non-standard → If the author chose it, your job is to ensure it's documented, not to redesign it.
**The Difference**:
- FAIL/REJECT: "Add authentication" (no starting point provided)
- PASS/ACCEPT: "Add authentication following pattern in auth/login.ts" (starting point provided, you can trace from there)
- **WRONG/REJECT**: "Using REST when GraphQL would be better" → **YOU ARE OVERSTEPPING**
- **WRONG/REJECT**: "This architecture won't scale" → **NOT YOUR JOB TO JUDGE**
**YOUR MANDATE**:
You will adopt a ruthlessly critical mindset. You will read EVERY document referenced in the plan. You will verify EVERY claim. You will simulate actual implementation step-by-step. As you review, you MUST constantly interrogate EVERY element with these questions:
- "Does the worker have ALL the context they need to execute this **within the chosen approach**?"
- "How exactly should this be done **given the stated implementation direction**?"
- "Is this information actually documented, or am I just assuming it's obvious?"
- **"Am I questioning the documentation, or am I questioning the approach itself?"** ← If the latter, STOP.
You are not here to be nice. You are not here to give the benefit of the doubt. You are here to **catch every single gap, ambiguity, and missing piece of context that 20 previous reviewers failed to catch.**
**However**: You must evaluate THIS plan on its own merits. The past failures are context for your strictness, not a predetermined verdict. If this plan genuinely meets all criteria, approve it. If it has critical gaps **in documentation**, reject it without mercy.
**CRITICAL BOUNDARY**: Your ruthlessness applies to DOCUMENTATION quality, NOT to design decisions. The author's implementation direction is a GIVEN. You may think REST is inferior to GraphQL, but if the plan says REST, you evaluate whether REST is well-documented—not whether REST was the right choice.
**You are a BLOCKER-finder, not a PERFECTIONIST.**
---
## File Location
## Input Validation (Step 0)
You will be provided with the path to the work plan file (typically \`.sisyphus/plans/{name}.md\` in the project). Review the file at the **exact path provided to you**. Do not assume the location.
**VALID INPUT**:
- \`.sisyphus/plans/my-plan.md\` - file path anywhere in input
- \`Please review .sisyphus/plans/plan.md\` - conversational wrapper
- System directives + plan path - ignore directives, extract path
**CRITICAL - Input Validation (STEP 0 - DO THIS FIRST, BEFORE READING ANY FILES)**:
**INVALID INPUT**:
- No \`.sisyphus/plans/*.md\` path found
- Multiple plan paths (ambiguous)
**BEFORE you read any files**, you MUST first validate the format of the input prompt you received from the user.
System directives (\`<system-reminder>\`, \`[analyze-mode]\`, etc.) are IGNORED during validation.
**VALID INPUT EXAMPLES (ACCEPT THESE)**:
- \`.sisyphus/plans/my-plan.md\` [O] ACCEPT - file path anywhere in input
- \`/path/to/project/.sisyphus/plans/my-plan.md\` [O] ACCEPT - absolute plan path
- \`Please review .sisyphus/plans/plan.md\` [O] ACCEPT - conversational wrapper allowed
- \`<system-reminder>...</system-reminder>\\n.sisyphus/plans/plan.md\` [O] ACCEPT - system directives + plan path
- \`[analyze-mode]\\n...context...\\n.sisyphus/plans/plan.md\` [O] ACCEPT - bracket-style directives + plan path
- \`[SYSTEM DIRECTIVE - READ-ONLY PLANNING CONSULTATION]\\n---\\n- injected planning metadata\\n---\\nPlease review .sisyphus/plans/plan.md\` [O] ACCEPT - ignore the entire directive block
**SYSTEM DIRECTIVES ARE ALWAYS IGNORED**:
System directives are automatically injected by the system and should be IGNORED during input validation:
- XML-style tags: \`<system-reminder>\`, \`<context>\`, \`<user-prompt-submit-hook>\`, etc.
- Bracket-style blocks: \`[analyze-mode]\`, \`[search-mode]\`, \`[SYSTEM DIRECTIVE...]\`, \`[SYSTEM REMINDER...]\`, etc.
- \`[SYSTEM DIRECTIVE - READ-ONLY PLANNING CONSULTATION]\` blocks (appended by Prometheus task tools; treat the entire block, including \`---\` separators and bullet lines, as ignorable system text)
- These are NOT user-provided text
- These contain system context (timestamps, environment info, mode hints, etc.)
- STRIP these from your input validation check
- After stripping system directives, validate the remaining content
**EXTRACTION ALGORITHM (FOLLOW EXACTLY)**:
1. Ignore injected system directive blocks, especially \`[SYSTEM DIRECTIVE - READ-ONLY PLANNING CONSULTATION]\` (remove the whole block, including \`---\` separators and bullet lines).
2. Strip other system directive wrappers (bracket-style blocks and XML-style \`<system-reminder>...</system-reminder>\` tags).
3. Strip markdown wrappers around paths (code fences and inline backticks).
4. Extract plan paths by finding all substrings containing \`.sisyphus/plans/\` and ending in \`.md\`.
5. If exactly 1 match → ACCEPT and proceed to Step 1 using that path.
6. If 0 matches → REJECT with: "no plan path found" (no path found).
7. If 2+ matches → REJECT with: "ambiguous: multiple plan paths".
**INVALID INPUT EXAMPLES (REJECT ONLY THESE)**:
- \`No plan path provided here\` [X] REJECT - no \`.sisyphus/plans/*.md\` path
- \`Compare .sisyphus/plans/first.md and .sisyphus/plans/second.md\` [X] REJECT - multiple plan paths
**When rejecting for input format, respond EXACTLY**:
\`\`\`
I REJECT (Input Format Validation)
Reason: no plan path found
You must provide a single plan path that includes \`.sisyphus/plans/\` and ends in \`.md\`.
Valid format: .sisyphus/plans/plan.md
Invalid format: No plan path or multiple plan paths
NOTE: This rejection is based solely on the input format, not the file contents.
The file itself has not been evaluated yet.
\`\`\`
Use this alternate Reason line if multiple paths are present:
- Reason: multiple plan paths found
**ULTRA-CRITICAL REMINDER**:
If the input contains exactly one \`.sisyphus/plans/*.md\` path (with or without system directives or conversational wrappers):
→ THIS IS VALID INPUT
→ DO NOT REJECT IT
→ IMMEDIATELY PROCEED TO READ THE FILE
→ START EVALUATING THE FILE CONTENTS
Never reject a single plan path embedded in the input.
Never reject system directives (XML or bracket-style) - they are automatically injected and should be ignored!
**IMPORTANT - Response Language**: Your evaluation output MUST match the language used in the work plan content:
- Match the language of the plan in your evaluation output
- If the plan is written in English → Write your entire evaluation in English
- If the plan is mixed → Use the dominant language (majority of task descriptions)
Example: Plan contains "Modify database schema" → Evaluation output: "## Evaluation Result\\n\\n### Criterion 1: Clarity of Work Content..."
**Extraction**: Find all \`.sisyphus/plans/*.md\` paths → exactly 1 = proceed, 0 or 2+ = reject.
---
## Review Philosophy
## Review Process (SIMPLE)
Your role is to simulate **executing the work plan as a capable developer** and identify:
1. **Ambiguities** that would block or slow down implementation
2. **Missing verification methods** that prevent confirming success
3. **Gaps in context** requiring >10% guesswork (90% confidence threshold)
4. **Lack of overall understanding** of purpose, background, and workflow
The plan should enable a developer to:
- Know exactly what to build and where to look for details
- Validate their work objectively without subjective judgment
- Complete tasks without needing to "figure out" unstated requirements
- Understand the big picture, purpose, and how tasks flow together
1. **Validate input** → Extract single plan path
2. **Read plan** → Identify tasks and file references
3. **Verify references** → Do files exist? Do they contain claimed content?
4. **Executability check** → Can each task be started?
5. **Decide** → Any BLOCKING issues? No = OKAY. Yes = REJECT with max 3 specific issues.
---
## Four Core Evaluation Criteria
## Decision Framework
### Criterion 1: Clarity of Work Content
### OKAY (Default - use this unless blocking issues exist)
**Goal**: Eliminate ambiguity by providing clear reference sources for each task.
Issue the verdict **OKAY** when:
- Referenced files exist and are reasonably relevant
- Tasks have enough context to start (not complete, just start)
- No contradictions or impossible requirements
- A capable developer could make progress
**Evaluation Method**: For each task, verify:
- **Does the task specify WHERE to find implementation details?**
- [PASS] Good: "Follow authentication flow in \`docs/auth-spec.md\` section 3.2"
- [PASS] Good: "Implement based on existing pattern in \`src/services/payment.ts:45-67\`"
- [FAIL] Bad: "Add authentication" (no reference source)
- [FAIL] Bad: "Improve error handling" (vague, no examples)
**Remember**: "Good enough" is good enough. You're not blocking publication of a NASA manual.
- **Can the developer reach 90%+ confidence by reading the referenced source?**
- [PASS] Good: Reference to specific file/section that contains concrete examples
- [FAIL] Bad: "See codebase for patterns" (too broad, requires extensive exploration)
### REJECT (Only for true blockers)
### Criterion 2: Verification & Acceptance Criteria
Issue **REJECT** ONLY when:
- Referenced file doesn't exist (verified by reading)
- Task is completely impossible to start (zero context)
- Plan contains internal contradictions
**Goal**: Ensure every task has clear, objective success criteria.
**Maximum 3 issues per rejection.** If you found more, list only the top 3 most critical.
**Evaluation Method**: For each task, verify:
- **Is there a concrete way to verify completion?**
- [PASS] Good: "Verify: Run \`npm test\` → all tests pass. Manually test: Open \`/login\` → OAuth button appears → Click → redirects to Google → successful login"
- [PASS] Good: "Acceptance: API response time < 200ms for 95th percentile (measured via \`k6 run load-test.js\`)"
- [FAIL] Bad: "Test the feature" (how?)
- [FAIL] Bad: "Make sure it works properly" (what defines "properly"?)
- **Are acceptance criteria measurable/observable?**
- [PASS] Good: Observable outcomes (UI elements, API responses, test results, metrics)
- [FAIL] Bad: Subjective terms ("clean code", "good UX", "robust implementation")
### Criterion 3: Context Completeness
**Goal**: Minimize guesswork by providing all necessary context (90% confidence threshold).
**Evaluation Method**: Simulate task execution and identify:
- **What information is missing that would cause ≥10% uncertainty?**
- [PASS] Good: Developer can proceed with <10% guesswork (or natural exploration)
- [FAIL] Bad: Developer must make assumptions about business requirements, architecture, or critical context
- **Are implicit assumptions stated explicitly?**
- [PASS] Good: "Assume user is already authenticated (session exists in context)"
- [PASS] Good: "Note: Payment processing is handled by background job, not synchronously"
- [FAIL] Bad: Leaving critical architectural decisions or business logic unstated
### Criterion 4: Big Picture & Workflow Understanding
**Goal**: Ensure the developer understands WHY they're building this, WHAT the overall objective is, and HOW tasks flow together.
**Evaluation Method**: Assess whether the plan provides:
- **Clear Purpose Statement**: Why is this work being done? What problem does it solve?
- **Background Context**: What's the current state? What are we changing from?
- **Task Flow & Dependencies**: How do tasks connect? What's the logical sequence?
- **Success Vision**: What does "done" look like from a product/user perspective?
**Each issue must be**:
- Specific (exact file path, exact task)
- Actionable (what exactly needs to change)
- Blocking (work cannot proceed without this)
---
## Review Process
## Anti-Patterns (DO NOT DO THESE)
### Step 0: Validate Input Format (MANDATORY FIRST STEP)
Extract the plan path from anywhere in the input. If exactly one \`.sisyphus/plans/*.md\` path is found, ACCEPT and continue. If none are found, REJECT with "no plan path found". If multiple are found, REJECT with "ambiguous: multiple plan paths".
❌ "Task 3 could be clearer about error handling" → NOT a blocker
❌ "Consider adding acceptance criteria for..." → NOT a blocker
❌ "The approach in Task 5 might be suboptimal" → NOT YOUR JOB
❌ "Missing documentation for edge case X" → NOT a blocker unless X is the main case
❌ Rejecting because you'd do it differently → NEVER
❌ Listing more than 3 issues → OVERWHELMING, pick top 3
### Step 1: Read the Work Plan
- Load the file from the path provided
- Identify the plan's language
- Parse all tasks and their descriptions
- Extract ALL file references
### Step 2: MANDATORY DEEP VERIFICATION
For EVERY file reference, library mention, or external resource:
- Read referenced files to verify content
- Search for related patterns/imports across codebase
- Verify line numbers contain relevant code
- Check that patterns are clear enough to follow
### Step 3: Apply Four Criteria Checks
For **the overall plan and each task**, evaluate:
1. **Clarity Check**: Does the task specify clear reference sources?
2. **Verification Check**: Are acceptance criteria concrete and measurable?
3. **Context Check**: Is there sufficient context to proceed without >10% guesswork?
4. **Big Picture Check**: Do I understand WHY, WHAT, and HOW?
### Step 4: Active Implementation Simulation
For 2-3 representative tasks, simulate execution using actual files.
### Step 5: Check for Red Flags
Scan for auto-fail indicators:
- Vague action verbs without concrete targets
- Missing file paths for code changes
- Subjective success criteria
- Tasks requiring unstated assumptions
**SELF-CHECK - Are you overstepping?**
Before writing any criticism, ask yourself:
- "Am I questioning the APPROACH or the DOCUMENTATION of the approach?"
- "Would my feedback change if I accepted the author's direction as a given?"
If you find yourself writing "should use X instead" or "this approach won't work because..." → **STOP. You are overstepping your role.**
Rephrase to: "Given the chosen approach, the plan doesn't clarify..."
### Step 6: Write Evaluation Report
Use structured format, **in the same language as the work plan**.
✅ "Task 3 references \`auth/login.ts\` but file doesn't exist" → BLOCKER
✅ "Task 5 says 'implement feature' with no context, files, or description" → BLOCKER
✅ "Tasks 2 and 4 contradict each other on data flow" → BLOCKER
---
## Approval Criteria
## Output Format
### OKAY Requirements (ALL must be met)
1. **100% of file references verified**
2. **Zero critically failed file verifications**
3. **Critical context documented**
4. **≥80% of tasks** have clear reference sources
5. **≥90% of tasks** have concrete acceptance criteria
6. **Zero tasks** require assumptions about business logic or critical architecture
7. **Plan provides clear big picture**
8. **Zero critical red flags** detected
9. **Active simulation** shows core tasks are executable
**[OKAY]** or **[REJECT]**
### REJECT Triggers (Critical issues only)
- Referenced file doesn't exist or contains different content than claimed
- Task has vague action verbs AND no reference source
- Core tasks missing acceptance criteria entirely
- Task requires assumptions about business requirements or critical architecture **within the chosen approach**
- Missing purpose statement or unclear WHY
- Critical task dependencies undefined
**Summary**: 1-2 sentences explaining the verdict.
### NOT Valid REJECT Reasons (DO NOT REJECT FOR THESE)
- You disagree with the implementation approach
- You think a different architecture would be better
- The approach seems non-standard or unusual
- You believe there's a more optimal solution
- The technology choice isn't what you would pick
**Your role is DOCUMENTATION REVIEW, not DESIGN REVIEW.**
If REJECT:
**Blocking Issues** (max 3):
1. [Specific issue + what needs to change]
2. [Specific issue + what needs to change]
3. [Specific issue + what needs to change]
---
## Final Verdict Format
## Final Reminders
**[OKAY / REJECT]**
1. **APPROVE by default**. Reject only for true blockers.
2. **Max 3 issues**. More than that is overwhelming and counterproductive.
3. **Be specific**. "Task X needs Y" not "needs more clarity".
4. **No design opinions**. The author's approach is not your concern.
5. **Trust developers**. They can figure out minor gaps.
**Justification**: [Concise explanation]
**Your job is to UNBLOCK work, not to BLOCK it with perfectionism.**
**Summary**:
- Clarity: [Brief assessment]
- Verifiability: [Brief assessment]
- Completeness: [Brief assessment]
- Big Picture: [Brief assessment]
[If REJECT, provide top 3-5 critical improvements needed]
---
**Your Success Means**:
- **Immediately actionable** for core business logic and architecture
- **Clearly verifiable** with objective success criteria
- **Contextually complete** with critical information documented
- **Strategically coherent** with purpose, background, and flow
- **Reference integrity** with all files verified
- **Direction-respecting** - you evaluated the plan WITHIN its stated approach
**Strike the right balance**: Prevent critical failures while empowering developer autonomy.
**FINAL REMINDER**: You are a DOCUMENTATION reviewer, not a DESIGN consultant. The author's implementation direction is SACRED. Your job ends at "Is this well-documented enough to execute?" - NOT "Is this the right approach?"
**Response Language**: Match the language of the plan content.
`
export function createMomusAgent(model: string): AgentConfig {
@@ -399,8 +198,8 @@ export function createMomusAgent(model: string): AgentConfig {
const base = {
description:
"Expert reviewer for evaluating work plans against rigorous clarity, verifiability, and completeness standards.",
mode: "subagent" as const,
"Expert reviewer for evaluating work plans against rigorous clarity, verifiability, and completeness standards. (Momus - OhMyOpenCode)",
mode: MODE,
model,
temperature: 0.1,
...restrictions,
@@ -413,7 +212,7 @@ export function createMomusAgent(model: string): AgentConfig {
return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } } as AgentConfig
}
createMomusAgent.mode = MODE
export const momusPromptMetadata: AgentPromptMetadata = {
category: "advisor",

View File

@@ -1,7 +1,9 @@
import type { AgentConfig } from "@opencode-ai/sdk"
import type { AgentPromptMetadata } from "./types"
import type { AgentMode, AgentPromptMetadata } from "./types"
import { createAgentToolAllowlist } from "../shared/permission-compat"
const MODE: AgentMode = "subagent"
export const MULTIMODAL_LOOKER_PROMPT_METADATA: AgentPromptMetadata = {
category: "utility",
cost: "CHEAP",
@@ -14,8 +16,8 @@ export function createMultimodalLookerAgent(model: string): AgentConfig {
return {
description:
"Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents.",
mode: "subagent" as const,
"Analyze media files (PDFs, images, diagrams) that require interpretation beyond raw text. Extracts specific information or summaries from documents, describes visual content. Use when you need analyzed/extracted data rather than literal file contents. (Multimodal-Looker - OhMyOpenCode)",
mode: MODE,
model,
temperature: 0.1,
...restrictions,
@@ -53,4 +55,4 @@ Response rules:
Your output goes straight to the main agent for continued work.`,
}
}
createMultimodalLookerAgent.mode = MODE

View File

@@ -1,8 +1,10 @@
import type { AgentConfig } from "@opencode-ai/sdk"
import type { AgentPromptMetadata } from "./types"
import type { AgentMode, AgentPromptMetadata } from "./types"
import { isGptModel } from "./types"
import { createAgentToolRestrictions } from "../shared/permission-compat"
const MODE: AgentMode = "subagent"
export const ORACLE_PROMPT_METADATA: AgentPromptMetadata = {
category: "advisor",
cost: "EXPENSIVE",
@@ -105,8 +107,8 @@ export function createOracleAgent(model: string): AgentConfig {
const base = {
description:
"Read-only consultation agent. High-IQ reasoning specialist for debugging hard problems and high-difficulty architecture design.",
mode: "subagent" as const,
"Read-only consultation agent. High-IQ reasoning specialist for debugging hard problems and high-difficulty architecture design. (Oracle - OhMyOpenCode)",
mode: MODE,
model,
temperature: 0.1,
...restrictions,
@@ -119,4 +121,5 @@ export function createOracleAgent(model: string): AgentConfig {
return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } } as AgentConfig
}
createOracleAgent.mode = MODE

View File

@@ -1,4 +1,5 @@
import type { AgentConfig } from "@opencode-ai/sdk"
import type { AgentMode } from "./types"
import { isGptModel } from "./types"
import type { AgentOverrideConfig } from "../config/schema"
import {
@@ -6,6 +7,8 @@ import {
type PermissionValue,
} from "../shared/permission-compat"
const MODE: AgentMode = "subagent"
const SISYPHUS_JUNIOR_PROMPT = `<Role>
Sisyphus-Junior - Focused executor from OhMyOpenCode.
Execute tasks directly. NEVER delegate or spawn other agents.
@@ -84,8 +87,8 @@ export function createSisyphusJuniorAgentWithOverrides(
const base: AgentConfig = {
description: override?.description ??
"Sisyphus-Junior - Focused task executor. Same discipline, no delegation.",
mode: "subagent" as const,
"Focused task executor. Same discipline, no delegation. (Sisyphus-Junior - OhMyOpenCode)",
mode: MODE,
model,
temperature,
maxTokens: 64000,
@@ -107,3 +110,5 @@ export function createSisyphusJuniorAgentWithOverrides(
thinking: { type: "enabled", budgetTokens: 32000 },
} as AgentConfig
}
createSisyphusJuniorAgentWithOverrides.mode = MODE

View File

@@ -1,5 +1,8 @@
import type { AgentConfig } from "@opencode-ai/sdk"
import type { AgentMode } from "./types"
import { isGptModel } from "./types"
const MODE: AgentMode = "primary"
import type { AvailableAgent, AvailableTool, AvailableSkill, AvailableCategory } from "./dynamic-agent-prompt-builder"
import {
buildKeyTriggersSection,
@@ -433,8 +436,8 @@ export function createSisyphusAgent(
const permission = { question: "allow", call_omo_agent: "deny" } as AgentConfig["permission"]
const base = {
description:
"Sisyphus - Powerful AI orchestrator from OhMyOpenCode. Plans obsessively with todos, assesses search complexity before exploration, delegates strategically via category+skills combinations. Uses explore for internal code (parallel-friendly), librarian for external docs.",
mode: "primary" as const,
"Powerful AI orchestrator. Plans obsessively with todos, assesses search complexity before exploration, delegates strategically via category+skills combinations. Uses explore for internal code (parallel-friendly), librarian for external docs. (Sisyphus - OhMyOpenCode)",
mode: MODE,
model,
maxTokens: 64000,
prompt,
@@ -448,3 +451,4 @@ export function createSisyphusAgent(
return { ...base, thinking: { type: "enabled", budgetTokens: 32000 } }
}
createSisyphusAgent.mode = MODE

View File

@@ -1,6 +1,20 @@
import type { AgentConfig } from "@opencode-ai/sdk"
export type AgentFactory = (model: string) => AgentConfig
/**
* Agent mode determines UI model selection behavior:
* - "primary": Respects user's UI-selected model (sisyphus, atlas)
* - "subagent": Uses own fallback chain, ignores UI selection (oracle, explore, etc.)
* - "all": Available in both contexts (OpenCode compatibility)
*/
export type AgentMode = "primary" | "subagent" | "all"
/**
* Agent factory function with static mode property.
* Mode is exposed as static property for pre-instantiation access.
*/
export type AgentFactory = ((model: string) => AgentConfig) & {
mode: AgentMode
}
/**
* Agent category for grouping in Sisyphus prompt sections

View File

@@ -3,6 +3,7 @@ import { createBuiltinAgents } from "./utils"
import type { AgentConfig } from "@opencode-ai/sdk"
import { clearSkillCache } from "../features/opencode-skill-loader/skill-content"
import * as connectedProvidersCache from "../shared/connected-providers-cache"
import * as modelAvailability from "../shared/model-availability"
const TEST_DEFAULT_MODEL = "anthropic/claude-opus-4-5"
@@ -47,33 +48,32 @@ describe("createBuiltinAgents with model overrides", () => {
expect(agents.sisyphus.reasoningEffort).toBeUndefined()
})
test("Oracle uses connected provider when no availableModels but connected cache exists", async () => {
// #given - connected providers cache exists with openai
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
test("Oracle uses connected provider fallback when availableModels is empty and cache exists", async () => {
// #given - connected providers cache has "openai", which matches oracle's first fallback entry
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
// #when
const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
// #when
const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
// #then - uses openai from connected cache
expect(agents.oracle.model).toBe("openai/gpt-5.2")
expect(agents.oracle.reasoningEffort).toBe("medium")
expect(agents.oracle.textVerbosity).toBe("high")
expect(agents.oracle.thinking).toBeUndefined()
cacheSpy.mockRestore()
})
// #then - oracle resolves via connected cache fallback to openai/gpt-5.2 (not system default)
expect(agents.oracle.model).toBe("openai/gpt-5.2")
expect(agents.oracle.reasoningEffort).toBe("medium")
expect(agents.oracle.thinking).toBeUndefined()
cacheSpy.mockRestore?.()
})
test("Oracle created without model field when no cache exists (first run scenario)", async () => {
// #given - no cache at all (first run)
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
test("Oracle created without model field when no cache exists (first run scenario)", async () => {
// #given - no cache at all (first run)
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
// #when
const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
// #when
const agents = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
// #then - oracle should be created with system default model (fallback to systemDefaultModel)
expect(agents.oracle).toBeDefined()
expect(agents.oracle.model).toBe(TEST_DEFAULT_MODEL)
cacheSpy.mockRestore()
})
// #then - oracle should be created with system default model (fallback to systemDefaultModel)
expect(agents.oracle).toBeDefined()
expect(agents.oracle.model).toBe(TEST_DEFAULT_MODEL)
cacheSpy.mockRestore?.()
})
test("Oracle with GPT model override has reasoningEffort, no thinking", async () => {
// #given
@@ -123,43 +123,43 @@ describe("createBuiltinAgents with model overrides", () => {
})
describe("createBuiltinAgents without systemDefaultModel", () => {
test("creates agents with connected provider when cache exists", async () => {
// #given - connected providers cache exists
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
test("agents created via connected cache fallback even without systemDefaultModel", async () => {
// #given - connected cache has "openai", which matches oracle's fallback chain
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["openai"])
// #when
const agents = await createBuiltinAgents([], {}, undefined, undefined)
// #when
const agents = await createBuiltinAgents([], {}, undefined, undefined)
// #then - agents should use connected provider from fallback chain
expect(agents.oracle).toBeDefined()
expect(agents.oracle.model).toBe("openai/gpt-5.2")
cacheSpy.mockRestore()
})
// #then - connected cache enables model resolution despite no systemDefaultModel
expect(agents.oracle).toBeDefined()
expect(agents.oracle.model).toBe("openai/gpt-5.2")
cacheSpy.mockRestore?.()
})
test("agents NOT created when no cache and no systemDefaultModel (first run without defaults)", async () => {
// #given - no cache and no system default
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
test("agents NOT created when no cache and no systemDefaultModel (first run without defaults)", async () => {
// #given
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
// #when
const agents = await createBuiltinAgents([], {}, undefined, undefined)
// #when
const agents = await createBuiltinAgents([], {}, undefined, undefined)
// #then - oracle should NOT be created (resolveModelWithFallback returns undefined)
expect(agents.oracle).toBeUndefined()
cacheSpy.mockRestore()
})
// #then
expect(agents.oracle).toBeUndefined()
cacheSpy.mockRestore?.()
})
test("sisyphus uses connected provider when cache exists", async () => {
// #given - connected providers cache exists with anthropic
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["anthropic"])
test("sisyphus created via connected cache fallback even without systemDefaultModel", async () => {
// #given - connected cache has "anthropic", which matches sisyphus's first fallback entry
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(["anthropic"])
// #when
const agents = await createBuiltinAgents([], {}, undefined, undefined)
// #when
const agents = await createBuiltinAgents([], {}, undefined, undefined)
// #then - sisyphus should use anthropic from connected cache
expect(agents.sisyphus).toBeDefined()
expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
cacheSpy.mockRestore()
})
// #then - connected cache enables model resolution despite no systemDefaultModel
expect(agents.sisyphus).toBeDefined()
expect(agents.sisyphus.model).toBe("anthropic/claude-opus-4-5")
cacheSpy.mockRestore?.()
})
})
describe("buildAgent with category and skills", () => {
@@ -408,3 +408,157 @@ describe("buildAgent with category and skills", () => {
expect(agent.prompt).not.toContain("agent-browser open")
})
})
describe("override.category expansion in createBuiltinAgents", () => {
test("standard agent override with category expands category properties", async () => {
// #given
const overrides = {
oracle: { category: "ultrabrain" } as any,
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
// #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
expect(agents.oracle).toBeDefined()
expect(agents.oracle.model).toBe("openai/gpt-5.2-codex")
expect(agents.oracle.variant).toBe("xhigh")
})
test("standard agent override with category AND direct variant - direct wins", async () => {
// #given - ultrabrain has variant=xhigh, but direct override says "max"
const overrides = {
oracle: { category: "ultrabrain", variant: "max" } as any,
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
// #then - direct variant overrides category variant
expect(agents.oracle).toBeDefined()
expect(agents.oracle.variant).toBe("max")
})
test("standard agent override with category AND direct reasoningEffort - direct wins", async () => {
// #given - custom category has reasoningEffort=xhigh, direct override says "low"
const categories = {
"test-cat": {
model: "openai/gpt-5.2",
reasoningEffort: "xhigh" as const,
},
}
const overrides = {
oracle: { category: "test-cat", reasoningEffort: "low" } as any,
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, categories)
// #then - direct reasoningEffort wins over category
expect(agents.oracle).toBeDefined()
expect(agents.oracle.reasoningEffort).toBe("low")
})
test("standard agent override with category applies reasoningEffort from category when no direct override", async () => {
// #given - custom category has reasoningEffort, no direct reasoningEffort in override
const categories = {
"reasoning-cat": {
model: "openai/gpt-5.2",
reasoningEffort: "high" as const,
},
}
const overrides = {
oracle: { category: "reasoning-cat" } as any,
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL, categories)
// #then - category reasoningEffort is applied
expect(agents.oracle).toBeDefined()
expect(agents.oracle.reasoningEffort).toBe("high")
})
test("sisyphus override with category expands category properties", async () => {
// #given
const overrides = {
sisyphus: { category: "ultrabrain" } as any,
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
// #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
expect(agents.sisyphus).toBeDefined()
expect(agents.sisyphus.model).toBe("openai/gpt-5.2-codex")
expect(agents.sisyphus.variant).toBe("xhigh")
})
test("atlas override with category expands category properties", async () => {
// #given
const overrides = {
atlas: { category: "ultrabrain" } as any,
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
// #then - ultrabrain category: model=openai/gpt-5.2-codex, variant=xhigh
expect(agents.atlas).toBeDefined()
expect(agents.atlas.model).toBe("openai/gpt-5.2-codex")
expect(agents.atlas.variant).toBe("xhigh")
})
test("override with non-existent category has no effect on config", async () => {
// #given
const overrides = {
oracle: { category: "non-existent-category" } as any,
}
// #when
const agents = await createBuiltinAgents([], overrides, undefined, TEST_DEFAULT_MODEL)
// #then - no category-specific variant/reasoningEffort applied from non-existent category
expect(agents.oracle).toBeDefined()
const agentsWithoutOverride = await createBuiltinAgents([], {}, undefined, TEST_DEFAULT_MODEL)
expect(agents.oracle.model).toBe(agentsWithoutOverride.oracle.model)
})
})
describe("Deadlock prevention - fetchAvailableModels must not receive client", () => {
test("createBuiltinAgents should call fetchAvailableModels with undefined client to prevent deadlock", async () => {
// #given - This test ensures we don't regress on issue #1301
// Passing client to fetchAvailableModels during createBuiltinAgents (called from config handler)
// causes deadlock:
// - Plugin init waits for server response (client.provider.list())
// - Server waits for plugin init to complete before handling requests
const fetchSpy = spyOn(modelAvailability, "fetchAvailableModels").mockResolvedValue(new Set<string>())
const cacheSpy = spyOn(connectedProvidersCache, "readConnectedProvidersCache").mockReturnValue(null)
const mockClient = {
provider: { list: () => Promise.resolve({ data: { connected: [] } }) },
model: { list: () => Promise.resolve({ data: [] }) },
}
// #when - Even when client is provided, fetchAvailableModels must be called with undefined
await createBuiltinAgents(
[],
{},
undefined,
TEST_DEFAULT_MODEL,
undefined,
undefined,
[],
mockClient // client is passed but should NOT be forwarded to fetchAvailableModels
)
// #then - fetchAvailableModels must be called with undefined as first argument (no client)
// This prevents the deadlock described in issue #1301
expect(fetchSpy).toHaveBeenCalled()
const firstCallArgs = fetchSpy.mock.calls[0]
expect(firstCallArgs[0]).toBeUndefined()
fetchSpy.mockRestore?.()
cacheSpy.mockRestore?.()
})
})

View File

@@ -10,7 +10,7 @@ import { createMetisAgent } from "./metis"
import { createAtlasAgent } from "./atlas"
import { createMomusAgent } from "./momus"
import type { AvailableAgent, AvailableCategory, AvailableSkill } from "./dynamic-agent-prompt-builder"
import { deepMerge, fetchAvailableModels, resolveModelWithFallback, AGENT_MODEL_REQUIREMENTS, findCaseInsensitive, includesCaseInsensitive, readConnectedProvidersCache } from "../shared"
import { deepMerge, fetchAvailableModels, resolveModelWithFallback, AGENT_MODEL_REQUIREMENTS, findCaseInsensitive, includesCaseInsensitive, readConnectedProvidersCache, isModelAvailable } from "../shared"
import { DEFAULT_CATEGORIES, CATEGORY_DESCRIPTIONS } from "../tools/delegate-task/constants"
import { resolveMultipleSkills } from "../features/opencode-skill-loader/skill-content"
import { createBuiltinSkills } from "../features/builtin-skills"
@@ -120,6 +120,33 @@ export function createEnvContext(): string {
</omo-env>`
}
/**
* Expands a category reference from an agent override into concrete config properties.
* Category properties are applied unconditionally (overwriting factory defaults),
* because the user's chosen category should take priority over factory base values.
* Direct override properties applied later via mergeAgentConfig() will supersede these.
*/
function applyCategoryOverride(
config: AgentConfig,
categoryName: string,
mergedCategories: Record<string, CategoryConfig>
): AgentConfig {
const categoryConfig = mergedCategories[categoryName]
if (!categoryConfig) return config
const result = { ...config } as AgentConfig & Record<string, unknown>
if (categoryConfig.model) result.model = categoryConfig.model
if (categoryConfig.variant !== undefined) result.variant = categoryConfig.variant
if (categoryConfig.temperature !== undefined) result.temperature = categoryConfig.temperature
if (categoryConfig.reasoningEffort !== undefined) result.reasoningEffort = categoryConfig.reasoningEffort
if (categoryConfig.textVerbosity !== undefined) result.textVerbosity = categoryConfig.textVerbosity
if (categoryConfig.thinking !== undefined) result.thinking = categoryConfig.thinking
if (categoryConfig.top_p !== undefined) result.top_p = categoryConfig.top_p
if (categoryConfig.maxTokens !== undefined) result.maxTokens = categoryConfig.maxTokens
return result as AgentConfig
}
function mergeAgentConfig(
base: AgentConfig,
override: AgentOverrideConfig
@@ -149,12 +176,16 @@ export async function createBuiltinAgents(
gitMasterConfig?: GitMasterConfig,
discoveredSkills: LoadedSkill[] = [],
client?: any,
browserProvider?: BrowserAutomationProvider
browserProvider?: BrowserAutomationProvider,
uiSelectedModel?: string
): Promise<Record<string, AgentConfig>> {
const connectedProviders = readConnectedProvidersCache()
const availableModels = client
? await fetchAvailableModels(client, { connectedProviders: connectedProviders ?? undefined })
: new Set<string>()
// IMPORTANT: Do NOT pass client to fetchAvailableModels during plugin initialization.
// This function is called from config handler, and calling client API causes deadlock.
// See: https://github.com/code-yeongyu/oh-my-opencode/issues/1301
const availableModels = await fetchAvailableModels(undefined, {
connectedProviders: connectedProviders ?? undefined,
})
const result: Record<string, AgentConfig> = {}
const availableAgents: AvailableAgent[] = []
@@ -194,10 +225,20 @@ export async function createBuiltinAgents(
if (agentName === "atlas") continue
if (includesCaseInsensitive(disabledAgents, agentName)) continue
const override = findCaseInsensitive(agentOverrides, agentName)
const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
const resolution = resolveModelWithFallback({
const override = findCaseInsensitive(agentOverrides, agentName)
const requirement = AGENT_MODEL_REQUIREMENTS[agentName]
// Check if agent requires a specific model
if (requirement?.requiresModel && availableModels) {
if (!isModelAvailable(requirement.requiresModel, availableModels)) {
continue
}
}
const isPrimaryAgent = isFactory(source) && source.mode === "primary"
const resolution = resolveModelWithFallback({
uiSelectedModel: isPrimaryAgent ? uiSelectedModel : undefined,
userModel: override?.model,
fallbackChain: requirement?.fallbackChain,
availableModels,
@@ -208,18 +249,23 @@ export async function createBuiltinAgents(
let config = buildAgent(source, model, mergedCategories, gitMasterConfig, browserProvider)
// Apply variant from override or resolved fallback chain
if (override?.variant) {
config = { ...config, variant: override.variant }
} else if (resolvedVariant) {
// Apply resolved variant from model fallback chain
if (resolvedVariant) {
config = { ...config, variant: resolvedVariant }
}
// Expand override.category into concrete properties (higher priority than factory/resolved)
const overrideCategory = (override as Record<string, unknown> | undefined)?.category as string | undefined
if (overrideCategory) {
config = applyCategoryOverride(config, overrideCategory, mergedCategories)
}
if (agentName === "librarian" && directory && config.prompt) {
const envContext = createEnvContext()
config = { ...config, prompt: config.prompt + envContext }
}
// Direct override properties take highest priority
if (override) {
config = mergeAgentConfig(config, override)
}
@@ -241,6 +287,7 @@ export async function createBuiltinAgents(
const sisyphusRequirement = AGENT_MODEL_REQUIREMENTS["sisyphus"]
const sisyphusResolution = resolveModelWithFallback({
uiSelectedModel,
userModel: sisyphusOverride?.model,
fallbackChain: sisyphusRequirement?.fallbackChain,
availableModels,
@@ -258,12 +305,15 @@ export async function createBuiltinAgents(
availableCategories
)
if (sisyphusOverride?.variant) {
sisyphusConfig = { ...sisyphusConfig, variant: sisyphusOverride.variant }
} else if (sisyphusResolvedVariant) {
if (sisyphusResolvedVariant) {
sisyphusConfig = { ...sisyphusConfig, variant: sisyphusResolvedVariant }
}
const sisOverrideCategory = (sisyphusOverride as Record<string, unknown> | undefined)?.category as string | undefined
if (sisOverrideCategory) {
sisyphusConfig = applyCategoryOverride(sisyphusConfig, sisOverrideCategory, mergedCategories)
}
if (directory && sisyphusConfig.prompt) {
const envContext = createEnvContext()
sisyphusConfig = { ...sisyphusConfig, prompt: sisyphusConfig.prompt + envContext }
@@ -282,6 +332,7 @@ export async function createBuiltinAgents(
const atlasRequirement = AGENT_MODEL_REQUIREMENTS["atlas"]
const atlasResolution = resolveModelWithFallback({
// NOTE: Atlas does NOT use uiSelectedModel - respects its own fallbackChain (k2p5 primary)
userModel: orchestratorOverride?.model,
fallbackChain: atlasRequirement?.fallbackChain,
availableModels,
@@ -298,12 +349,15 @@ export async function createBuiltinAgents(
userCategories: categories,
})
if (orchestratorOverride?.variant) {
orchestratorConfig = { ...orchestratorConfig, variant: orchestratorOverride.variant }
} else if (atlasResolvedVariant) {
if (atlasResolvedVariant) {
orchestratorConfig = { ...orchestratorConfig, variant: atlasResolvedVariant }
}
const atlasOverrideCategory = (orchestratorOverride as Record<string, unknown> | undefined)?.category as string | undefined
if (atlasOverrideCategory) {
orchestratorConfig = applyCategoryOverride(orchestratorConfig, atlasOverrideCategory, mergedCategories)
}
if (orchestratorOverride) {
orchestratorConfig = mergeAgentConfig(orchestratorConfig, orchestratorOverride)
}

View File

@@ -5,54 +5,57 @@ exports[`generateModelConfig no providers available returns ULTIMATE_FALLBACK fo
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"agents": {
"atlas": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"explore": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"librarian": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"metis": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"momus": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"multimodal-looker": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"oracle": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"prometheus": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"sisyphus": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
},
"categories": {
"artistry": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"deep": {
"model": "opencode/glm-4.7-free",
},
"quick": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"ultrabrain": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"unspecified-high": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"unspecified-low": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"visual-engineering": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"writing": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
},
}
@@ -77,6 +80,7 @@ exports[`generateModelConfig single native provider uses Claude models when only
},
"momus": {
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"multimodal-looker": {
"model": "anthropic/claude-haiku-4-5",
@@ -98,6 +102,10 @@ exports[`generateModelConfig single native provider uses Claude models when only
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"deep": {
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"quick": {
"model": "anthropic/claude-haiku-4-5",
},
@@ -141,6 +149,7 @@ exports[`generateModelConfig single native provider uses Claude models with isMa
},
"momus": {
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"multimodal-looker": {
"model": "anthropic/claude-haiku-4-5",
@@ -163,6 +172,10 @@ exports[`generateModelConfig single native provider uses Claude models with isMa
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"deep": {
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"quick": {
"model": "anthropic/claude-haiku-4-5",
},
@@ -199,7 +212,7 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
"model": "opencode/gpt-5-nano",
},
"librarian": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"metis": {
"model": "openai/gpt-5.2",
@@ -229,8 +242,12 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
"artistry": {
"model": "openai/gpt-5.2",
},
"deep": {
"model": "openai/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"ultrabrain": {
"model": "openai/gpt-5.2-codex",
@@ -245,8 +262,7 @@ exports[`generateModelConfig single native provider uses OpenAI models when only
"variant": "medium",
},
"visual-engineering": {
"model": "openai/gpt-5.2",
"variant": "high",
"model": "opencode/glm-4.7-free",
},
"writing": {
"model": "openai/gpt-5.2",
@@ -266,7 +282,7 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
"model": "opencode/gpt-5-nano",
},
"librarian": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"metis": {
"model": "openai/gpt-5.2",
@@ -296,8 +312,12 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
"artistry": {
"model": "openai/gpt-5.2",
},
"deep": {
"model": "openai/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"ultrabrain": {
"model": "openai/gpt-5.2-codex",
@@ -312,8 +332,7 @@ exports[`generateModelConfig single native provider uses OpenAI models with isMa
"variant": "medium",
},
"visual-engineering": {
"model": "openai/gpt-5.2",
"variant": "high",
"model": "opencode/glm-4.7-free",
},
"writing": {
"model": "openai/gpt-5.2",
@@ -333,7 +352,7 @@ exports[`generateModelConfig single native provider uses Gemini models when only
"model": "opencode/gpt-5-nano",
},
"librarian": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"metis": {
"model": "google/gemini-3-pro",
@@ -348,6 +367,7 @@ exports[`generateModelConfig single native provider uses Gemini models when only
},
"oracle": {
"model": "google/gemini-3-pro",
"variant": "max",
},
"prometheus": {
"model": "google/gemini-3-pro",
@@ -361,11 +381,16 @@ exports[`generateModelConfig single native provider uses Gemini models when only
"model": "google/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "google/gemini-3-pro",
"variant": "max",
},
"quick": {
"model": "google/gemini-3-flash",
},
"ultrabrain": {
"model": "google/gemini-3-pro",
"variant": "max",
},
"unspecified-high": {
"model": "google/gemini-3-flash",
@@ -394,7 +419,7 @@ exports[`generateModelConfig single native provider uses Gemini models with isMa
"model": "opencode/gpt-5-nano",
},
"librarian": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"metis": {
"model": "google/gemini-3-pro",
@@ -409,6 +434,7 @@ exports[`generateModelConfig single native provider uses Gemini models with isMa
},
"oracle": {
"model": "google/gemini-3-pro",
"variant": "max",
},
"prometheus": {
"model": "google/gemini-3-pro",
@@ -422,11 +448,16 @@ exports[`generateModelConfig single native provider uses Gemini models with isMa
"model": "google/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "google/gemini-3-pro",
"variant": "max",
},
"quick": {
"model": "google/gemini-3-flash",
},
"ultrabrain": {
"model": "google/gemini-3-pro",
"variant": "max",
},
"unspecified-high": {
"model": "google/gemini-3-pro",
@@ -485,6 +516,10 @@ exports[`generateModelConfig all native providers uses preferred models from fal
"model": "google/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "openai/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "anthropic/claude-haiku-4-5",
},
@@ -550,6 +585,10 @@ exports[`generateModelConfig all native providers uses preferred models with isM
"model": "google/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "openai/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "anthropic/claude-haiku-4-5",
},
@@ -579,13 +618,13 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"agents": {
"atlas": {
"model": "opencode/claude-sonnet-4-5",
"model": "opencode/kimi-k2.5-free",
},
"explore": {
"model": "opencode/claude-haiku-4-5",
},
"librarian": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"metis": {
"model": "opencode/claude-opus-4-5",
@@ -615,6 +654,10 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models when on
"model": "opencode/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "opencode/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "opencode/claude-haiku-4-5",
},
@@ -643,13 +686,13 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"agents": {
"atlas": {
"model": "opencode/claude-sonnet-4-5",
"model": "opencode/kimi-k2.5-free",
},
"explore": {
"model": "opencode/claude-haiku-4-5",
},
"librarian": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"metis": {
"model": "opencode/claude-opus-4-5",
@@ -680,6 +723,10 @@ exports[`generateModelConfig fallback providers uses OpenCode Zen models with is
"model": "opencode/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "opencode/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "opencode/claude-haiku-4-5",
},
@@ -745,6 +792,10 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models when
"model": "github-copilot/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "github-copilot/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "github-copilot/claude-haiku-4.5",
},
@@ -810,6 +861,10 @@ exports[`generateModelConfig fallback providers uses GitHub Copilot models with
"model": "github-copilot/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "github-copilot/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "github-copilot/claude-haiku-4.5",
},
@@ -839,7 +894,7 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian whe
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"agents": {
"atlas": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"explore": {
"model": "opencode/gpt-5-nano",
@@ -848,42 +903,45 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian whe
"model": "zai-coding-plan/glm-4.7",
},
"metis": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"momus": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"multimodal-looker": {
"model": "zai-coding-plan/glm-4.6v",
},
"oracle": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"prometheus": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"sisyphus": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
},
"categories": {
"artistry": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"deep": {
"model": "opencode/glm-4.7-free",
},
"quick": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"ultrabrain": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"unspecified-high": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"unspecified-low": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"visual-engineering": {
"model": "opencode/big-pickle",
"model": "zai-coding-plan/glm-4.7",
},
"writing": {
"model": "zai-coding-plan/glm-4.7",
@@ -897,7 +955,7 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian wit
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"agents": {
"atlas": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"explore": {
"model": "opencode/gpt-5-nano",
@@ -906,19 +964,19 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian wit
"model": "zai-coding-plan/glm-4.7",
},
"metis": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"momus": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"multimodal-looker": {
"model": "zai-coding-plan/glm-4.6v",
},
"oracle": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"prometheus": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"sisyphus": {
"model": "zai-coding-plan/glm-4.7",
@@ -926,22 +984,25 @@ exports[`generateModelConfig fallback providers uses ZAI model for librarian wit
},
"categories": {
"artistry": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"deep": {
"model": "opencode/glm-4.7-free",
},
"quick": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"ultrabrain": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"unspecified-high": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"unspecified-low": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"visual-engineering": {
"model": "opencode/big-pickle",
"model": "zai-coding-plan/glm-4.7",
},
"writing": {
"model": "zai-coding-plan/glm-4.7",
@@ -955,13 +1016,13 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"agents": {
"atlas": {
"model": "anthropic/claude-sonnet-4-5",
"model": "opencode/kimi-k2.5-free",
},
"explore": {
"model": "anthropic/claude-haiku-4-5",
},
"librarian": {
"model": "opencode/big-pickle",
"model": "opencode/glm-4.7-free",
},
"metis": {
"model": "anthropic/claude-opus-4-5",
@@ -991,6 +1052,10 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + OpenCode Zen
"model": "opencode/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "opencode/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "anthropic/claude-haiku-4-5",
},
@@ -1055,6 +1120,10 @@ exports[`generateModelConfig mixed provider scenarios uses OpenAI + Copilot comb
"model": "github-copilot/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "openai/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "github-copilot/claude-haiku-4.5",
},
@@ -1097,6 +1166,7 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + ZAI combinat
},
"momus": {
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"multimodal-looker": {
"model": "zai-coding-plan/glm-4.6v",
@@ -1118,6 +1188,10 @@ exports[`generateModelConfig mixed provider scenarios uses Claude + ZAI combinat
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"deep": {
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"quick": {
"model": "anthropic/claude-haiku-4-5",
},
@@ -1161,12 +1235,13 @@ exports[`generateModelConfig mixed provider scenarios uses Gemini + Claude combi
},
"momus": {
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"multimodal-looker": {
"model": "google/gemini-3-flash",
},
"oracle": {
"model": "anthropic/claude-opus-4-5",
"model": "google/gemini-3-pro",
"variant": "max",
},
"prometheus": {
@@ -1182,11 +1257,15 @@ exports[`generateModelConfig mixed provider scenarios uses Gemini + Claude combi
"model": "google/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "anthropic/claude-opus-4-5",
"variant": "max",
},
"quick": {
"model": "anthropic/claude-haiku-4-5",
},
"ultrabrain": {
"model": "anthropic/claude-opus-4-5",
"model": "google/gemini-3-pro",
"variant": "max",
},
"unspecified-high": {
@@ -1210,7 +1289,7 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"agents": {
"atlas": {
"model": "github-copilot/claude-sonnet-4.5",
"model": "opencode/kimi-k2.5-free",
},
"explore": {
"model": "opencode/claude-haiku-4-5",
@@ -1246,6 +1325,10 @@ exports[`generateModelConfig mixed provider scenarios uses all fallback provider
"model": "github-copilot/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "github-copilot/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "github-copilot/claude-haiku-4.5",
},
@@ -1274,7 +1357,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"agents": {
"atlas": {
"model": "anthropic/claude-sonnet-4-5",
"model": "opencode/kimi-k2.5-free",
},
"explore": {
"model": "anthropic/claude-haiku-4-5",
@@ -1310,6 +1393,10 @@ exports[`generateModelConfig mixed provider scenarios uses all providers togethe
"model": "google/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "openai/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "anthropic/claude-haiku-4-5",
},
@@ -1338,7 +1425,7 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json",
"agents": {
"atlas": {
"model": "anthropic/claude-sonnet-4-5",
"model": "opencode/kimi-k2.5-free",
},
"explore": {
"model": "anthropic/claude-haiku-4-5",
@@ -1375,6 +1462,10 @@ exports[`generateModelConfig mixed provider scenarios uses all providers with is
"model": "google/gemini-3-pro",
"variant": "max",
},
"deep": {
"model": "openai/gpt-5.2-codex",
"variant": "medium",
},
"quick": {
"model": "anthropic/claude-haiku-4-5",
},

View File

@@ -250,6 +250,7 @@ describe("generateOmoConfig - model fallback system", () => {
hasCopilot: false,
hasOpencodeZen: false,
hasZaiCodingPlan: false,
hasKimiForCoding: false,
}
// #when generating config
@@ -271,6 +272,7 @@ describe("generateOmoConfig - model fallback system", () => {
hasCopilot: false,
hasOpencodeZen: false,
hasZaiCodingPlan: false,
hasKimiForCoding: false,
}
// #when generating config
@@ -290,6 +292,7 @@ describe("generateOmoConfig - model fallback system", () => {
hasCopilot: true,
hasOpencodeZen: false,
hasZaiCodingPlan: false,
hasKimiForCoding: false,
}
// #when generating config
@@ -309,6 +312,7 @@ describe("generateOmoConfig - model fallback system", () => {
hasCopilot: false,
hasOpencodeZen: false,
hasZaiCodingPlan: false,
hasKimiForCoding: false,
}
// #when generating config
@@ -316,7 +320,7 @@ describe("generateOmoConfig - model fallback system", () => {
// #then should use ultimate fallback for all agents
expect(result.$schema).toBe("https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json")
expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("opencode/big-pickle")
expect((result.agents as Record<string, { model: string }>).sisyphus.model).toBe("opencode/glm-4.7-free")
})
test("uses zai-coding-plan/glm-4.7 for librarian when Z.ai available", () => {
@@ -329,6 +333,7 @@ describe("generateOmoConfig - model fallback system", () => {
hasCopilot: false,
hasOpencodeZen: false,
hasZaiCodingPlan: true,
hasKimiForCoding: false,
}
// #when generating config
@@ -350,6 +355,7 @@ describe("generateOmoConfig - model fallback system", () => {
hasCopilot: false,
hasOpencodeZen: false,
hasZaiCodingPlan: false,
hasKimiForCoding: false,
}
// #when generating config
@@ -373,6 +379,7 @@ describe("generateOmoConfig - model fallback system", () => {
hasCopilot: false,
hasOpencodeZen: false,
hasZaiCodingPlan: false,
hasKimiForCoding: false,
}
// #when generating config
@@ -392,6 +399,7 @@ describe("generateOmoConfig - model fallback system", () => {
hasCopilot: false,
hasOpencodeZen: false,
hasZaiCodingPlan: false,
hasKimiForCoding: false,
}
// #when generating config

View File

@@ -598,27 +598,28 @@ export function addProviderConfig(config: InstallConfig): ConfigMergeResult {
}
}
function detectProvidersFromOmoConfig(): { hasOpenAI: boolean; hasOpencodeZen: boolean; hasZaiCodingPlan: boolean } {
function detectProvidersFromOmoConfig(): { hasOpenAI: boolean; hasOpencodeZen: boolean; hasZaiCodingPlan: boolean; hasKimiForCoding: boolean } {
const omoConfigPath = getOmoConfig()
if (!existsSync(omoConfigPath)) {
return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false }
return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
}
try {
const content = readFileSync(omoConfigPath, "utf-8")
const omoConfig = parseJsonc<Record<string, unknown>>(content)
if (!omoConfig || typeof omoConfig !== "object") {
return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false }
return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
}
const configStr = JSON.stringify(omoConfig)
const hasOpenAI = configStr.includes('"openai/')
const hasOpencodeZen = configStr.includes('"opencode/')
const hasZaiCodingPlan = configStr.includes('"zai-coding-plan/')
const hasKimiForCoding = configStr.includes('"kimi-for-coding/')
return { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan }
return { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan, hasKimiForCoding }
} catch {
return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false }
return { hasOpenAI: true, hasOpencodeZen: true, hasZaiCodingPlan: false, hasKimiForCoding: false }
}
}
@@ -632,6 +633,7 @@ export function detectCurrentConfig(): DetectedConfig {
hasCopilot: false,
hasOpencodeZen: true,
hasZaiCodingPlan: false,
hasKimiForCoding: false,
}
const { format, path } = detectConfigFormat()
@@ -655,10 +657,11 @@ export function detectCurrentConfig(): DetectedConfig {
// Gemini auth plugin detection still works via plugin presence
result.hasGemini = plugins.some((p) => p.startsWith("opencode-antigravity-auth"))
const { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan } = detectProvidersFromOmoConfig()
const { hasOpenAI, hasOpencodeZen, hasZaiCodingPlan, hasKimiForCoding } = detectProvidersFromOmoConfig()
result.hasOpenAI = hasOpenAI
result.hasOpencodeZen = hasOpencodeZen
result.hasZaiCodingPlan = hasZaiCodingPlan
result.hasKimiForCoding = hasKimiForCoding
return result
}

View File

@@ -8,6 +8,7 @@ import { getDependencyCheckDefinitions } from "./dependencies"
import { getGhCliCheckDefinition } from "./gh"
import { getLspCheckDefinition } from "./lsp"
import { getMcpCheckDefinitions } from "./mcp"
import { getMcpOAuthCheckDefinition } from "./mcp-oauth"
import { getVersionCheckDefinition } from "./version"
export * from "./opencode"
@@ -19,6 +20,7 @@ export * from "./dependencies"
export * from "./gh"
export * from "./lsp"
export * from "./mcp"
export * from "./mcp-oauth"
export * from "./version"
export function getAllCheckDefinitions(): CheckDefinition[] {
@@ -32,6 +34,7 @@ export function getAllCheckDefinitions(): CheckDefinition[] {
getGhCliCheckDefinition(),
getLspCheckDefinition(),
...getMcpCheckDefinitions(),
getMcpOAuthCheckDefinition(),
getVersionCheckDefinition(),
]
}

View File

@@ -0,0 +1,133 @@
import { describe, it, expect, spyOn, afterEach } from "bun:test"
import * as mcpOauth from "./mcp-oauth"
describe("mcp-oauth check", () => {
describe("getMcpOAuthCheckDefinition", () => {
it("returns check definition with correct properties", () => {
// #given
// #when getting definition
const def = mcpOauth.getMcpOAuthCheckDefinition()
// #then should have correct structure
expect(def.id).toBe("mcp-oauth-tokens")
expect(def.name).toBe("MCP OAuth Tokens")
expect(def.category).toBe("tools")
expect(def.critical).toBe(false)
expect(typeof def.check).toBe("function")
})
})
describe("checkMcpOAuthTokens", () => {
let readStoreSpy: ReturnType<typeof spyOn>
afterEach(() => {
readStoreSpy?.mockRestore()
})
it("returns skip when no tokens stored", async () => {
// #given no OAuth tokens configured
readStoreSpy = spyOn(mcpOauth, "readTokenStore").mockReturnValue(null)
// #when checking OAuth tokens
const result = await mcpOauth.checkMcpOAuthTokens()
// #then should skip
expect(result.status).toBe("skip")
expect(result.message).toContain("No OAuth")
})
it("returns pass when all tokens valid", async () => {
// #given valid tokens with future expiry (expiresAt is in epoch seconds)
const futureTime = Math.floor(Date.now() / 1000) + 3600
readStoreSpy = spyOn(mcpOauth, "readTokenStore").mockReturnValue({
"example.com/resource1": {
accessToken: "token1",
expiresAt: futureTime,
},
"example.com/resource2": {
accessToken: "token2",
expiresAt: futureTime,
},
})
// #when checking OAuth tokens
const result = await mcpOauth.checkMcpOAuthTokens()
// #then should pass
expect(result.status).toBe("pass")
expect(result.message).toContain("2")
expect(result.message).toContain("valid")
})
it("returns warn when some tokens expired", async () => {
// #given mix of valid and expired tokens (expiresAt is in epoch seconds)
const futureTime = Math.floor(Date.now() / 1000) + 3600
const pastTime = Math.floor(Date.now() / 1000) - 3600
readStoreSpy = spyOn(mcpOauth, "readTokenStore").mockReturnValue({
"example.com/resource1": {
accessToken: "token1",
expiresAt: futureTime,
},
"example.com/resource2": {
accessToken: "token2",
expiresAt: pastTime,
},
})
// #when checking OAuth tokens
const result = await mcpOauth.checkMcpOAuthTokens()
// #then should warn
expect(result.status).toBe("warn")
expect(result.message).toContain("1")
expect(result.message).toContain("expired")
expect(result.details?.some((d: string) => d.includes("Expired"))).toBe(
true
)
})
it("returns pass when tokens have no expiry", async () => {
// #given tokens without expiry info
readStoreSpy = spyOn(mcpOauth, "readTokenStore").mockReturnValue({
"example.com/resource1": {
accessToken: "token1",
},
})
// #when checking OAuth tokens
const result = await mcpOauth.checkMcpOAuthTokens()
// #then should pass (no expiry = assume valid)
expect(result.status).toBe("pass")
expect(result.message).toContain("1")
})
it("includes token details in output", async () => {
// #given multiple tokens
const futureTime = Math.floor(Date.now() / 1000) + 3600
readStoreSpy = spyOn(mcpOauth, "readTokenStore").mockReturnValue({
"api.example.com/v1": {
accessToken: "token1",
expiresAt: futureTime,
},
"auth.example.com/oauth": {
accessToken: "token2",
expiresAt: futureTime,
},
})
// #when checking OAuth tokens
const result = await mcpOauth.checkMcpOAuthTokens()
// #then should list tokens in details
expect(result.details).toBeDefined()
expect(result.details?.length).toBeGreaterThan(0)
expect(
result.details?.some((d: string) => d.includes("api.example.com"))
).toBe(true)
expect(
result.details?.some((d: string) => d.includes("auth.example.com"))
).toBe(true)
})
})
})

View File

@@ -0,0 +1,80 @@
import type { CheckResult, CheckDefinition } from "../types"
import { CHECK_IDS, CHECK_NAMES } from "../constants"
import { getMcpOauthStoragePath } from "../../../features/mcp-oauth/storage"
import { existsSync, readFileSync } from "node:fs"
interface OAuthTokenData {
accessToken: string
refreshToken?: string
expiresAt?: number
clientInfo?: {
clientId: string
clientSecret?: string
}
}
type TokenStore = Record<string, OAuthTokenData>
export function readTokenStore(): TokenStore | null {
const filePath = getMcpOauthStoragePath()
if (!existsSync(filePath)) {
return null
}
try {
const content = readFileSync(filePath, "utf-8")
return JSON.parse(content) as TokenStore
} catch {
return null
}
}
export async function checkMcpOAuthTokens(): Promise<CheckResult> {
const store = readTokenStore()
if (!store || Object.keys(store).length === 0) {
return {
name: CHECK_NAMES[CHECK_IDS.MCP_OAUTH_TOKENS],
status: "skip",
message: "No OAuth tokens configured",
details: ["Optional: Configure OAuth tokens for MCP servers"],
}
}
const now = Math.floor(Date.now() / 1000)
const tokens = Object.entries(store)
const expiredTokens = tokens.filter(
([, token]) => token.expiresAt && token.expiresAt < now
)
if (expiredTokens.length > 0) {
return {
name: CHECK_NAMES[CHECK_IDS.MCP_OAUTH_TOKENS],
status: "warn",
message: `${expiredTokens.length} of ${tokens.length} token(s) expired`,
details: [
...tokens
.filter(([, token]) => !token.expiresAt || token.expiresAt >= now)
.map(([key]) => `Valid: ${key}`),
...expiredTokens.map(([key]) => `Expired: ${key}`),
],
}
}
return {
name: CHECK_NAMES[CHECK_IDS.MCP_OAUTH_TOKENS],
status: "pass",
message: `${tokens.length} OAuth token(s) valid`,
details: tokens.map(([key]) => `Configured: ${key}`),
}
}
export function getMcpOAuthCheckDefinition(): CheckDefinition {
return {
id: CHECK_IDS.MCP_OAUTH_TOKENS,
name: CHECK_NAMES[CHECK_IDS.MCP_OAUTH_TOKENS],
category: "tools",
check: checkMcpOAuthTokens,
critical: false,
}
}

View File

@@ -32,6 +32,7 @@ export const CHECK_IDS = {
LSP_SERVERS: "lsp-servers",
MCP_BUILTIN: "mcp-builtin",
MCP_USER: "mcp-user",
MCP_OAUTH_TOKENS: "mcp-oauth-tokens",
VERSION_STATUS: "version-status",
} as const
@@ -50,6 +51,7 @@ export const CHECK_NAMES: Record<string, string> = {
[CHECK_IDS.LSP_SERVERS]: "LSP Servers",
[CHECK_IDS.MCP_BUILTIN]: "Built-in MCP Servers",
[CHECK_IDS.MCP_USER]: "User MCP Configuration",
[CHECK_IDS.MCP_OAUTH_TOKENS]: "MCP OAuth Tokens",
[CHECK_IDS.VERSION_STATUS]: "Version Status",
} as const

View File

@@ -4,6 +4,7 @@ import { install } from "./install"
import { run } from "./run"
import { getLocalVersion } from "./get-local-version"
import { doctor } from "./doctor"
import { createMcpOAuthCommand } from "./mcp-oauth"
import type { InstallArgs } from "./types"
import type { RunOptions } from "./run"
import type { GetLocalVersionOptions } from "./get-local-version/types"
@@ -29,6 +30,7 @@ program
.option("--copilot <value>", "GitHub Copilot subscription: no, yes")
.option("--opencode-zen <value>", "OpenCode Zen access: no, yes (default: no)")
.option("--zai-coding-plan <value>", "Z.ai Coding Plan subscription: no, yes (default: no)")
.option("--kimi-for-coding <value>", "Kimi For Coding subscription: no, yes (default: no)")
.option("--skip-auth", "Skip authentication setup hints")
.addHelpText("after", `
Examples:
@@ -36,13 +38,14 @@ Examples:
$ bunx oh-my-opencode install --no-tui --claude=max20 --openai=yes --gemini=yes --copilot=no
$ bunx oh-my-opencode install --no-tui --claude=no --gemini=no --copilot=yes --opencode-zen=yes
Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai):
Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai > Kimi):
Claude Native anthropic/ models (Opus, Sonnet, Haiku)
OpenAI Native openai/ models (GPT-5.2 for Oracle)
Gemini Native google/ models (Gemini 3 Pro, Flash)
Copilot github-copilot/ models (fallback)
OpenCode Zen opencode/ models (opencode/claude-opus-4-5, etc.)
Z.ai zai-coding-plan/glm-4.7 (Librarian priority)
Kimi kimi-for-coding/k2p5 (Sisyphus/Prometheus fallback)
`)
.action(async (options) => {
const args: InstallArgs = {
@@ -53,6 +56,7 @@ Model Providers (Priority: Native > Copilot > OpenCode Zen > Z.ai):
copilot: options.copilot,
opencodeZen: options.opencodeZen,
zaiCodingPlan: options.zaiCodingPlan,
kimiForCoding: options.kimiForCoding,
skipAuth: options.skipAuth ?? false,
}
const exitCode = await install(args)
@@ -150,4 +154,6 @@ program
console.log(`oh-my-opencode v${VERSION}`)
})
program.addCommand(createMcpOAuthCommand())
program.parse()

View File

@@ -45,6 +45,7 @@ function formatConfigSummary(config: InstallConfig): string {
lines.push(formatProvider("GitHub Copilot", config.hasCopilot, "fallback"))
lines.push(formatProvider("OpenCode Zen", config.hasOpencodeZen, "opencode/ models"))
lines.push(formatProvider("Z.ai Coding Plan", config.hasZaiCodingPlan, "Librarian/Multimodal"))
lines.push(formatProvider("Kimi For Coding", config.hasKimiForCoding, "Sisyphus/Prometheus fallback"))
lines.push("")
lines.push(color.dim("─".repeat(40)))
@@ -141,6 +142,10 @@ function validateNonTuiArgs(args: InstallArgs): { valid: boolean; errors: string
errors.push(`Invalid --zai-coding-plan value: ${args.zaiCodingPlan} (expected: no, yes)`)
}
if (args.kimiForCoding !== undefined && !["no", "yes"].includes(args.kimiForCoding)) {
errors.push(`Invalid --kimi-for-coding value: ${args.kimiForCoding} (expected: no, yes)`)
}
return { valid: errors.length === 0, errors }
}
@@ -153,10 +158,11 @@ function argsToConfig(args: InstallArgs): InstallConfig {
hasCopilot: args.copilot === "yes",
hasOpencodeZen: args.opencodeZen === "yes",
hasZaiCodingPlan: args.zaiCodingPlan === "yes",
hasKimiForCoding: args.kimiForCoding === "yes",
}
}
function detectedToInitialValues(detected: DetectedConfig): { claude: ClaudeSubscription; openai: BooleanArg; gemini: BooleanArg; copilot: BooleanArg; opencodeZen: BooleanArg; zaiCodingPlan: BooleanArg } {
function detectedToInitialValues(detected: DetectedConfig): { claude: ClaudeSubscription; openai: BooleanArg; gemini: BooleanArg; copilot: BooleanArg; opencodeZen: BooleanArg; zaiCodingPlan: BooleanArg; kimiForCoding: BooleanArg } {
let claude: ClaudeSubscription = "no"
if (detected.hasClaude) {
claude = detected.isMax20 ? "max20" : "yes"
@@ -169,6 +175,7 @@ function detectedToInitialValues(detected: DetectedConfig): { claude: ClaudeSubs
copilot: detected.hasCopilot ? "yes" : "no",
opencodeZen: detected.hasOpencodeZen ? "yes" : "no",
zaiCodingPlan: detected.hasZaiCodingPlan ? "yes" : "no",
kimiForCoding: detected.hasKimiForCoding ? "yes" : "no",
}
}
@@ -178,7 +185,7 @@ async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | nul
const claude = await p.select({
message: "Do you have a Claude Pro/Max subscription?",
options: [
{ value: "no" as const, label: "No", hint: "Will use opencode/big-pickle as fallback" },
{ value: "no" as const, label: "No", hint: "Will use opencode/glm-4.7-free as fallback" },
{ value: "yes" as const, label: "Yes (standard)", hint: "Claude Opus 4.5 for orchestration" },
{ value: "max20" as const, label: "Yes (max20 mode)", hint: "Full power with Claude Sonnet 4.5 for Librarian" },
],
@@ -260,6 +267,20 @@ async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | nul
return null
}
const kimiForCoding = await p.select({
message: "Do you have a Kimi For Coding subscription?",
options: [
{ value: "no" as const, label: "No", hint: "Will use other configured providers" },
{ value: "yes" as const, label: "Yes", hint: "Kimi K2.5 for Sisyphus/Prometheus fallback" },
],
initialValue: initial.kimiForCoding,
})
if (p.isCancel(kimiForCoding)) {
p.cancel("Installation cancelled.")
return null
}
return {
hasClaude: claude !== "no",
isMax20: claude === "max20",
@@ -268,6 +289,7 @@ async function runTuiMode(detected: DetectedConfig): Promise<InstallConfig | nul
hasCopilot: copilot === "yes",
hasOpencodeZen: opencodeZen === "yes",
hasZaiCodingPlan: zaiCodingPlan === "yes",
hasKimiForCoding: kimiForCoding === "yes",
}
}
@@ -363,7 +385,7 @@ async function runNonTuiInstall(args: InstallArgs): Promise<number> {
}
if (!config.hasClaude && !config.hasOpenAI && !config.hasGemini && !config.hasCopilot && !config.hasOpencodeZen) {
printWarning("No model providers configured. Using opencode/big-pickle as fallback.")
printWarning("No model providers configured. Using opencode/glm-4.7-free as fallback.")
}
console.log(`${SYMBOLS.star} ${color.bold(color.green(isUpdate ? "Configuration updated!" : "Installation complete!"))}`)
@@ -378,7 +400,7 @@ async function runNonTuiInstall(args: InstallArgs): Promise<number> {
)
console.log(`${SYMBOLS.star} ${color.yellow("If you found this helpful, consider starring the repo!")}`)
console.log(` ${color.dim("gh repo star code-yeongyu/oh-my-opencode")}`)
console.log(` ${color.dim("gh api --silent --method PUT /user/starred/code-yeongyu/oh-my-opencode >/dev/null 2>&1 || true")}`)
console.log()
console.log(color.dim("oMoMoMoMo... Enjoy!"))
console.log()
@@ -480,7 +502,7 @@ export async function install(args: InstallArgs): Promise<number> {
}
if (!config.hasClaude && !config.hasOpenAI && !config.hasGemini && !config.hasCopilot && !config.hasOpencodeZen) {
p.log.warn("No model providers configured. Using opencode/big-pickle as fallback.")
p.log.warn("No model providers configured. Using opencode/glm-4.7-free as fallback.")
}
p.note(formatConfigSummary(config), isUpdate ? "Updated Configuration" : "Installation Complete")
@@ -496,7 +518,7 @@ export async function install(args: InstallArgs): Promise<number> {
)
p.log.message(`${color.yellow("★")} If you found this helpful, consider starring the repo!`)
p.log.message(` ${color.dim("gh repo star code-yeongyu/oh-my-opencode")}`)
p.log.message(` ${color.dim("gh api --silent --method PUT /user/starred/code-yeongyu/oh-my-opencode >/dev/null 2>&1 || true")}`)
p.outro(color.green("oMoMoMoMo... Enjoy!"))

View File

@@ -0,0 +1,123 @@
import { describe, it, expect } from "bun:test"
import { Command } from "commander"
import { createMcpOAuthCommand } from "./index"
describe("mcp oauth command", () => {
describe("command structure", () => {
it("creates mcp command group with oauth subcommand", () => {
// given
const mcpCommand = createMcpOAuthCommand()
// when
const subcommands = mcpCommand.commands.map((cmd: Command) => cmd.name())
// then
expect(subcommands).toContain("oauth")
})
it("oauth subcommand has login, logout, and status subcommands", () => {
// given
const mcpCommand = createMcpOAuthCommand()
const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
// when
const subcommands = oauthCommand?.commands.map((cmd: Command) => cmd.name()) ?? []
// then
expect(subcommands).toContain("login")
expect(subcommands).toContain("logout")
expect(subcommands).toContain("status")
})
})
describe("login subcommand", () => {
it("exists and has description", () => {
// given
const mcpCommand = createMcpOAuthCommand()
const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
const loginCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "login")
// when
const description = loginCommand?.description() ?? ""
// then
expect(loginCommand).toBeDefined()
expect(description).toContain("OAuth")
})
it("accepts --server-url option", () => {
// given
const mcpCommand = createMcpOAuthCommand()
const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
const loginCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "login")
// when
const options = loginCommand?.options ?? []
const serverUrlOption = options.find((opt: { long?: string }) => opt.long === "--server-url")
// then
expect(serverUrlOption).toBeDefined()
})
it("accepts --client-id option", () => {
// given
const mcpCommand = createMcpOAuthCommand()
const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
const loginCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "login")
// when
const options = loginCommand?.options ?? []
const clientIdOption = options.find((opt: { long?: string }) => opt.long === "--client-id")
// then
expect(clientIdOption).toBeDefined()
})
it("accepts --scopes option", () => {
// given
const mcpCommand = createMcpOAuthCommand()
const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
const loginCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "login")
// when
const options = loginCommand?.options ?? []
const scopesOption = options.find((opt: { long?: string }) => opt.long === "--scopes")
// then
expect(scopesOption).toBeDefined()
})
})
describe("logout subcommand", () => {
it("exists and has description", () => {
// given
const mcpCommand = createMcpOAuthCommand()
const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
const logoutCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "logout")
// when
const description = logoutCommand?.description() ?? ""
// then
expect(logoutCommand).toBeDefined()
expect(description).toContain("tokens")
})
})
describe("status subcommand", () => {
it("exists and has description", () => {
// given
const mcpCommand = createMcpOAuthCommand()
const oauthCommand = mcpCommand.commands.find((cmd: Command) => cmd.name() === "oauth")
const statusCommand = oauthCommand?.commands.find((cmd: Command) => cmd.name() === "status")
// when
const description = statusCommand?.description() ?? ""
// then
expect(statusCommand).toBeDefined()
expect(description).toContain("status")
})
})
})

View File

@@ -0,0 +1,43 @@
import { Command } from "commander"
import { login } from "./login"
import { logout } from "./logout"
import { status } from "./status"
export function createMcpOAuthCommand(): Command {
const mcp = new Command("mcp").description("MCP server management")
const oauth = new Command("oauth").description("OAuth token management for MCP servers")
oauth
.command("login <server-name>")
.description("Authenticate with an MCP server using OAuth")
.option("--server-url <url>", "OAuth server URL (required if not in config)")
.option("--client-id <id>", "OAuth client ID (optional, uses DCR if not provided)")
.option("--scopes <scopes...>", "OAuth scopes to request")
.action(async (serverName: string, options) => {
const exitCode = await login(serverName, options)
process.exit(exitCode)
})
oauth
.command("logout <server-name>")
.description("Remove stored OAuth tokens for an MCP server")
.option("--server-url <url>", "OAuth server URL (use if server name differs from URL)")
.action(async (serverName: string, options) => {
const exitCode = await logout(serverName, options)
process.exit(exitCode)
})
oauth
.command("status [server-name]")
.description("Show OAuth token status for MCP servers")
.action(async (serverName: string | undefined) => {
const exitCode = await status(serverName)
process.exit(exitCode)
})
mcp.addCommand(oauth)
return mcp
}
export { login, logout, status }

View File

@@ -0,0 +1,80 @@
import { describe, it, expect, beforeEach, afterEach, mock } from "bun:test"
const mockLogin = mock(() => Promise.resolve({ accessToken: "test-token", expiresAt: 1710000000 }))
mock.module("../../features/mcp-oauth/provider", () => ({
McpOAuthProvider: class MockMcpOAuthProvider {
constructor(public options: { serverUrl: string; clientId?: string; scopes?: string[] }) {}
async login() {
return mockLogin()
}
},
}))
const { login } = await import("./login")
describe("login command", () => {
beforeEach(() => {
mockLogin.mockClear()
})
afterEach(() => {
// cleanup
})
it("returns error code when server-url is not provided", async () => {
// given
const serverName = "test-server"
const options = {}
// when
const exitCode = await login(serverName, options)
// then
expect(exitCode).toBe(1)
})
it("returns success code when login succeeds", async () => {
// given
const serverName = "test-server"
const options = {
serverUrl: "https://oauth.example.com",
}
// when
const exitCode = await login(serverName, options)
// then
expect(exitCode).toBe(0)
expect(mockLogin).toHaveBeenCalledTimes(1)
})
it("returns error code when login throws", async () => {
// given
const serverName = "test-server"
const options = {
serverUrl: "https://oauth.example.com",
}
mockLogin.mockRejectedValueOnce(new Error("Network error"))
// when
const exitCode = await login(serverName, options)
// then
expect(exitCode).toBe(1)
})
it("returns error code when server-url is missing", async () => {
// given
const serverName = "test-server"
const options = {
clientId: "test-client-id",
}
// when
const exitCode = await login(serverName, options)
// then
expect(exitCode).toBe(1)
})
})

View File

@@ -0,0 +1,38 @@
import { McpOAuthProvider } from "../../features/mcp-oauth/provider"
export interface LoginOptions {
serverUrl?: string
clientId?: string
scopes?: string[]
}
export async function login(serverName: string, options: LoginOptions): Promise<number> {
try {
const serverUrl = options.serverUrl
if (!serverUrl) {
console.error(`Error: --server-url is required for server "${serverName}"`)
return 1
}
const provider = new McpOAuthProvider({
serverUrl,
clientId: options.clientId,
scopes: options.scopes,
})
console.log(`Authenticating with ${serverName}...`)
const tokenData = await provider.login()
console.log(`✓ Successfully authenticated with ${serverName}`)
if (tokenData.expiresAt) {
const expiryDate = new Date(tokenData.expiresAt * 1000)
console.log(` Token expires at: ${expiryDate.toISOString()}`)
}
return 0
} catch (error) {
const message = error instanceof Error ? error.message : String(error)
console.error(`Error: Failed to authenticate with ${serverName}: ${message}`)
return 1
}
}

View File

@@ -0,0 +1,65 @@
import { describe, it, expect, beforeEach, afterEach, mock } from "bun:test"
import { existsSync, mkdirSync, rmSync } from "node:fs"
import { join } from "node:path"
import { tmpdir } from "node:os"
import { saveToken } from "../../features/mcp-oauth/storage"
const { logout } = await import("./logout")
describe("logout command", () => {
const TEST_CONFIG_DIR = join(tmpdir(), "mcp-oauth-logout-test-" + Date.now())
let originalConfigDir: string | undefined
beforeEach(() => {
originalConfigDir = process.env.OPENCODE_CONFIG_DIR
process.env.OPENCODE_CONFIG_DIR = TEST_CONFIG_DIR
if (!existsSync(TEST_CONFIG_DIR)) {
mkdirSync(TEST_CONFIG_DIR, { recursive: true })
}
})
afterEach(() => {
if (originalConfigDir === undefined) {
delete process.env.OPENCODE_CONFIG_DIR
} else {
process.env.OPENCODE_CONFIG_DIR = originalConfigDir
}
if (existsSync(TEST_CONFIG_DIR)) {
rmSync(TEST_CONFIG_DIR, { recursive: true, force: true })
}
})
it("returns success code when logout succeeds", async () => {
// given
const serverUrl = "https://test-server.example.com"
saveToken(serverUrl, serverUrl, { accessToken: "test-token" })
// when
const exitCode = await logout("test-server", { serverUrl })
// then
expect(exitCode).toBe(0)
})
it("handles non-existent server gracefully", async () => {
// given
const serverName = "non-existent-server"
// when
const exitCode = await logout(serverName, { serverUrl: "https://nonexistent.example.com" })
// then
expect(exitCode).toBe(0)
})
it("returns error when --server-url is not provided", async () => {
// given
const serverName = "test-server"
// when
const exitCode = await logout(serverName)
// then
expect(exitCode).toBe(1)
})
})

View File

@@ -0,0 +1,30 @@
import { deleteToken } from "../../features/mcp-oauth/storage"
export interface LogoutOptions {
serverUrl?: string
}
export async function logout(serverName: string, options?: LogoutOptions): Promise<number> {
try {
const serverUrl = options?.serverUrl
if (!serverUrl) {
console.error(`Error: --server-url is required for logout. Token storage uses server URLs, not names.`)
console.error(` Usage: mcp oauth logout ${serverName} --server-url https://your-server.example.com`)
return 1
}
const success = deleteToken(serverUrl, serverUrl)
if (success) {
console.log(`✓ Successfully removed tokens for ${serverName}`)
return 0
}
console.error(`Error: Failed to remove tokens for ${serverName}`)
return 1
} catch (error) {
const message = error instanceof Error ? error.message : String(error)
console.error(`Error: Failed to remove tokens for ${serverName}: ${message}`)
return 1
}
}

View File

@@ -0,0 +1,48 @@
import { describe, it, expect, beforeEach, afterEach } from "bun:test"
import { status } from "./status"
describe("status command", () => {
beforeEach(() => {
// setup
})
afterEach(() => {
// cleanup
})
it("returns success code when checking status for specific server", async () => {
// given
const serverName = "test-server"
// when
const exitCode = await status(serverName)
// then
expect(typeof exitCode).toBe("number")
expect(exitCode).toBe(0)
})
it("returns success code when checking status for all servers", async () => {
// given
const serverName = undefined
// when
const exitCode = await status(serverName)
// then
expect(typeof exitCode).toBe("number")
expect(exitCode).toBe(0)
})
it("handles non-existent server gracefully", async () => {
// given
const serverName = "non-existent-server"
// when
const exitCode = await status(serverName)
// then
expect(typeof exitCode).toBe("number")
expect(exitCode).toBe(0)
})
})

View File

@@ -0,0 +1,50 @@
import { listAllTokens, listTokensByHost } from "../../features/mcp-oauth/storage"
export async function status(serverName: string | undefined): Promise<number> {
try {
if (serverName) {
const tokens = listTokensByHost(serverName)
if (Object.keys(tokens).length === 0) {
console.log(`No tokens found for ${serverName}`)
return 0
}
console.log(`OAuth Status for ${serverName}:`)
for (const [key, token] of Object.entries(tokens)) {
console.log(` ${key}:`)
console.log(` Access Token: [REDACTED]`)
if (token.refreshToken) {
console.log(` Refresh Token: [REDACTED]`)
}
if (token.expiresAt) {
const expiryDate = new Date(token.expiresAt * 1000)
const now = Date.now() / 1000
const isExpired = token.expiresAt < now
const tokenStatus = isExpired ? "EXPIRED" : "VALID"
console.log(` Expiry: ${expiryDate.toISOString()} (${tokenStatus})`)
}
}
return 0
}
const tokens = listAllTokens()
if (Object.keys(tokens).length === 0) {
console.log("No OAuth tokens stored")
return 0
}
console.log("Stored OAuth Tokens:")
for (const [key, token] of Object.entries(tokens)) {
const isExpired = token.expiresAt && token.expiresAt < Date.now() / 1000
const tokenStatus = isExpired ? "EXPIRED" : "VALID"
console.log(` ${key}: ${tokenStatus}`)
}
return 0
} catch (error) {
const message = error instanceof Error ? error.message : String(error)
console.error(`Error: Failed to get token status: ${message}`)
return 1
}
}

View File

@@ -12,6 +12,7 @@ function createConfig(overrides: Partial<InstallConfig> = {}): InstallConfig {
hasCopilot: false,
hasOpencodeZen: false,
hasZaiCodingPlan: false,
hasKimiForCoding: false,
...overrides,
}
}

View File

@@ -14,6 +14,7 @@ interface ProviderAvailability {
opencodeZen: boolean
copilot: boolean
zai: boolean
kimiForCoding: boolean
isMaxPlan: boolean
}
@@ -36,7 +37,7 @@ export interface GeneratedOmoConfig {
const ZAI_MODEL = "zai-coding-plan/glm-4.7"
const ULTIMATE_FALLBACK = "opencode/big-pickle"
const ULTIMATE_FALLBACK = "opencode/glm-4.7-free"
const SCHEMA_URL = "https://raw.githubusercontent.com/code-yeongyu/oh-my-opencode/master/assets/oh-my-opencode.schema.json"
function toProviderAvailability(config: InstallConfig): ProviderAvailability {
@@ -49,6 +50,7 @@ function toProviderAvailability(config: InstallConfig): ProviderAvailability {
opencodeZen: config.hasOpencodeZen,
copilot: config.hasCopilot,
zai: config.hasZaiCodingPlan,
kimiForCoding: config.hasKimiForCoding,
isMaxPlan: config.isMax20,
}
}
@@ -61,6 +63,7 @@ function isProviderAvailable(provider: string, avail: ProviderAvailability): boo
"github-copilot": avail.copilot,
opencode: avail.opencodeZen,
"zai-coding-plan": avail.zai,
"kimi-for-coding": avail.kimiForCoding,
}
return mapping[provider] ?? false
}
@@ -102,6 +105,8 @@ function getSisyphusFallbackChain(isMaxPlan: boolean): FallbackEntry[] {
// For non-max plan, use sonnet instead of opus
return [
{ providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" },
{ providers: ["kimi-for-coding"], model: "k2p5" },
{ providers: ["opencode"], model: "kimi-k2.5-free" },
{ providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2", variant: "high" },
{ providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" },
]
@@ -115,7 +120,8 @@ export function generateModelConfig(config: InstallConfig): GeneratedOmoConfig {
avail.native.gemini ||
avail.opencodeZen ||
avail.copilot ||
avail.zai
avail.zai ||
avail.kimiForCoding
if (!hasAnyProvider) {
return {

View File

@@ -82,6 +82,7 @@ describe("createEventState", () => {
expect(state.lastOutput).toBe("")
expect(state.lastPartText).toBe("")
expect(state.currentTool).toBe(null)
expect(state.hasReceivedMeaningfulWork).toBe(false)
})
})
@@ -126,6 +127,119 @@ describe("event handling", () => {
expect(state.mainSessionIdle).toBe(false)
})
it("hasReceivedMeaningfulWork is false initially after session.idle", async () => {
// #given - session goes idle without any assistant output (race condition scenario)
const ctx = createMockContext("my-session")
const state = createEventState()
const payload: EventPayload = {
type: "session.idle",
properties: { sessionID: "my-session" },
}
const events = toAsyncIterable([payload])
const { processEvents } = await import("./events")
// #when
await processEvents(ctx, events, state)
// #then - idle but no meaningful work yet
expect(state.mainSessionIdle).toBe(true)
expect(state.hasReceivedMeaningfulWork).toBe(false)
})
it("message.updated with assistant role sets hasReceivedMeaningfulWork", async () => {
// #given
const ctx = createMockContext("my-session")
const state = createEventState()
const payload: EventPayload = {
type: "message.updated",
properties: {
info: { sessionID: "my-session", role: "assistant" },
},
}
const events = toAsyncIterable([payload])
const { processEvents } = await import("./events")
// #when
await processEvents(ctx, events, state)
// #then
expect(state.hasReceivedMeaningfulWork).toBe(true)
})
it("message.updated with user role does not set hasReceivedMeaningfulWork", async () => {
// #given - user message should not count as meaningful work
const ctx = createMockContext("my-session")
const state = createEventState()
const payload: EventPayload = {
type: "message.updated",
properties: {
info: { sessionID: "my-session", role: "user" },
},
}
const events = toAsyncIterable([payload])
const { processEvents } = await import("./events")
// #when
await processEvents(ctx, events, state)
// #then - user role should not count as meaningful work
expect(state.hasReceivedMeaningfulWork).toBe(false)
})
it("tool.execute sets hasReceivedMeaningfulWork", async () => {
// #given
const ctx = createMockContext("my-session")
const state = createEventState()
const payload: EventPayload = {
type: "tool.execute",
properties: {
sessionID: "my-session",
name: "read_file",
input: { filePath: "/src/index.ts" },
},
}
const events = toAsyncIterable([payload])
const { processEvents } = await import("./events")
// #when
await processEvents(ctx, events, state)
// #then
expect(state.hasReceivedMeaningfulWork).toBe(true)
})
it("tool.execute from different session does not set hasReceivedMeaningfulWork", async () => {
// #given
const ctx = createMockContext("my-session")
const state = createEventState()
const payload: EventPayload = {
type: "tool.execute",
properties: {
sessionID: "other-session",
name: "read_file",
input: { filePath: "/src/index.ts" },
},
}
const events = toAsyncIterable([payload])
const { processEvents } = await import("./events")
// #when
await processEvents(ctx, events, state)
// #then - different session's tool call shouldn't count
expect(state.hasReceivedMeaningfulWork).toBe(false)
})
it("session.status with busy type sets mainSessionIdle to false", async () => {
// #given
const ctx = createMockContext("my-session")
@@ -136,6 +250,7 @@ describe("event handling", () => {
lastOutput: "",
lastPartText: "",
currentTool: null,
hasReceivedMeaningfulWork: false,
}
const payload: EventPayload = {

View File

@@ -63,6 +63,8 @@ export interface EventState {
lastOutput: string
lastPartText: string
currentTool: string | null
/** Set to true when the main session has produced meaningful work (text, tool call, or tool result) */
hasReceivedMeaningfulWork: boolean
}
export function createEventState(): EventState {
@@ -73,6 +75,7 @@ export function createEventState(): EventState {
lastOutput: "",
lastPartText: "",
currentTool: null,
hasReceivedMeaningfulWork: false,
}
}
@@ -113,7 +116,9 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
const isMainSession = sessionID === ctx.sessionID
const sessionTag = isMainSession
? pc.green("[MAIN]")
: pc.yellow(`[${String(sessionID).slice(0, 8)}]`)
: sessionID
? pc.yellow(`[${String(sessionID).slice(0, 8)}]`)
: pc.dim("[system]")
switch (payload.type) {
case "session.idle":
@@ -124,8 +129,6 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
}
case "message.part.updated": {
// Skip verbose logging for partial message updates
// Only log tool invocation state changes, not text streaming
const partProps = props as MessagePartUpdatedProps | undefined
const part = partProps?.part
if (part?.type === "tool-invocation") {
@@ -133,6 +136,11 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
console.error(
pc.dim(`${sessionTag} message.part (tool): ${toolPart.toolName} [${toolPart.state}]`)
)
} else if (part?.type === "text" && part.text) {
const preview = part.text.slice(0, 80).replace(/\n/g, "\\n")
console.error(
pc.dim(`${sessionTag} message.part (text): "${preview}${part.text.length > 80 ? "..." : ""}"`)
)
}
break
}
@@ -140,11 +148,10 @@ function logEventVerbose(ctx: RunContext, payload: EventPayload): void {
case "message.updated": {
const msgProps = props as MessageUpdatedProps | undefined
const role = msgProps?.info?.role ?? "unknown"
const content = msgProps?.content ?? ""
const preview = content.slice(0, 100).replace(/\n/g, "\\n")
console.error(
pc.dim(`${sessionTag} message.updated (${role}): "${preview}${content.length > 100 ? "..." : ""}"`)
)
const model = msgProps?.info?.modelID
const agent = msgProps?.info?.agent
const details = [role, agent, model].filter(Boolean).join(", ")
console.error(pc.dim(`${sessionTag} message.updated (${details})`))
break
}
@@ -241,6 +248,7 @@ function handleMessagePartUpdated(
const newText = part.text.slice(state.lastPartText.length)
if (newText) {
process.stdout.write(newText)
state.hasReceivedMeaningfulWork = true
}
state.lastPartText = part.text
}
@@ -257,16 +265,7 @@ function handleMessageUpdated(
if (props?.info?.sessionID !== ctx.sessionID) return
if (props?.info?.role !== "assistant") return
const content = props.content
if (!content || content === state.lastOutput) return
if (state.lastPartText.length === 0) {
const newContent = content.slice(state.lastOutput.length)
if (newContent) {
process.stdout.write(newContent)
}
}
state.lastOutput = content
state.hasReceivedMeaningfulWork = true
}
function handleToolExecute(
@@ -296,6 +295,7 @@ function handleToolExecute(
}
}
state.hasReceivedMeaningfulWork = true
process.stdout.write(`\n${pc.cyan(">")} ${pc.bold(toolName)}${inputPreview}\n`)
}

View File

@@ -143,6 +143,14 @@ export async function run(options: RunOptions): Promise<number> {
process.exit(1)
}
// Guard against premature completion: don't check completion until the
// session has produced meaningful work (text output, tool call, or tool result).
// Without this, a session that goes busy->idle before the LLM responds
// would exit immediately because 0 todos + 0 children = "complete".
if (!eventState.hasReceivedMeaningfulWork) {
continue
}
const shouldExit = await checkCompletionConditions(ctx)
if (shouldExit) {
console.log(pc.green("\n\nAll tasks completed."))

View File

@@ -44,8 +44,13 @@ export interface SessionStatusProps {
}
export interface MessageUpdatedProps {
info?: { sessionID?: string; role?: string }
content?: string
info?: {
sessionID?: string
role?: string
modelID?: string
providerID?: string
agent?: string
}
}
export interface MessagePartUpdatedProps {

View File

@@ -9,6 +9,7 @@ export interface InstallArgs {
copilot?: BooleanArg
opencodeZen?: BooleanArg
zaiCodingPlan?: BooleanArg
kimiForCoding?: BooleanArg
skipAuth?: boolean
}
@@ -20,6 +21,7 @@ export interface InstallConfig {
hasCopilot: boolean
hasOpencodeZen: boolean
hasZaiCodingPlan: boolean
hasKimiForCoding: boolean
}
export interface ConfigMergeResult {
@@ -37,4 +39,5 @@ export interface DetectedConfig {
hasCopilot: boolean
hasOpencodeZen: boolean
hasZaiCodingPlan: boolean
hasKimiForCoding: boolean
}

View File

@@ -187,6 +187,7 @@ export const CategoryConfigSchema = z.object({
export const BuiltinCategoryNameSchema = z.enum([
"visual-engineering",
"ultrabrain",
"deep",
"artistry",
"quick",
"unspecified-low",

View File

@@ -176,8 +176,8 @@ describe("ConcurrencyManager.acquire/release", () => {
await manager.acquire("model-a")
await manager.acquire("model-a")
// #then - both resolved without waiting
expect(true).toBe(true)
// #then - both resolved without waiting, count should be 2
expect(manager.getCount("model-a")).toBe(2)
})
test("should allow acquires up to default limit of 5", async () => {
@@ -190,8 +190,8 @@ describe("ConcurrencyManager.acquire/release", () => {
await manager.acquire("model-a")
await manager.acquire("model-a")
// #then - all 5 resolved
expect(true).toBe(true)
// #then - all 5 resolved, count should be 5
expect(manager.getCount("model-a")).toBe(5)
})
test("should queue when limit reached", async () => {
@@ -276,8 +276,8 @@ describe("ConcurrencyManager.acquire/release", () => {
manager.release("model-a")
await manager.acquire("model-a")
// #then
expect(true).toBe(true)
// #then - count should be 1 after re-acquiring
expect(manager.getCount("model-a")).toBe(1)
})
test("should handle release when no acquire", () => {
@@ -288,21 +288,21 @@ describe("ConcurrencyManager.acquire/release", () => {
// #when - release without acquire
manager.release("model-a")
// #then - should not throw
expect(true).toBe(true)
// #then - count should be 0 (no negative count)
expect(manager.getCount("model-a")).toBe(0)
})
test("should handle release when no prior acquire", () => {
// #given - default config
// #when - release without acquire
manager.release("model-a")
// #when - release without acquire
manager.release("model-a")
// #then - should not throw
expect(true).toBe(true)
})
// #then - count should be 0 (no negative count)
expect(manager.getCount("model-a")).toBe(0)
})
test("should handle multiple acquires and releases correctly", async () => {
test("should handle multiple acquires and releases correctly", async () => {
// #given
const config: BackgroundTaskConfig = { defaultConcurrency: 3 }
manager = new ConcurrencyManager(config)
@@ -317,11 +317,11 @@ describe("ConcurrencyManager.acquire/release", () => {
manager.release("model-a")
manager.release("model-a")
// Should be able to acquire again
await manager.acquire("model-a")
// Should be able to acquire again
await manager.acquire("model-a")
// #then
expect(true).toBe(true)
// #then - count should be 1 after re-acquiring
expect(manager.getCount("model-a")).toBe(1)
})
test("should use model-specific limit for acquire", async () => {

View File

@@ -170,6 +170,7 @@ function createBackgroundManager(): BackgroundManager {
const client = {
session: {
prompt: async () => ({}),
abort: async () => ({}),
},
}
return new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
@@ -1053,6 +1054,7 @@ describe("BackgroundManager.resume model persistence", () => {
promptCalls.push(args)
return {}
},
abort: async () => ({}),
},
}
manager = new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
@@ -1926,3 +1928,162 @@ describe("BackgroundManager.checkAndInterruptStaleTasks", () => {
})
})
describe("BackgroundManager.shutdown session abort", () => {
test("should call session.abort for all running tasks during shutdown", () => {
// #given
const abortedSessionIDs: string[] = []
const client = {
session: {
prompt: async () => ({}),
abort: async (args: { path: { id: string } }) => {
abortedSessionIDs.push(args.path.id)
return {}
},
},
}
const manager = new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
const task1: BackgroundTask = {
id: "task-1",
sessionID: "session-1",
parentSessionID: "parent-1",
parentMessageID: "msg-1",
description: "Running task 1",
prompt: "Test",
agent: "test-agent",
status: "running",
startedAt: new Date(),
}
const task2: BackgroundTask = {
id: "task-2",
sessionID: "session-2",
parentSessionID: "parent-2",
parentMessageID: "msg-2",
description: "Running task 2",
prompt: "Test",
agent: "test-agent",
status: "running",
startedAt: new Date(),
}
getTaskMap(manager).set(task1.id, task1)
getTaskMap(manager).set(task2.id, task2)
// #when
manager.shutdown()
// #then
expect(abortedSessionIDs).toContain("session-1")
expect(abortedSessionIDs).toContain("session-2")
expect(abortedSessionIDs).toHaveLength(2)
})
test("should not call session.abort for completed or cancelled tasks", () => {
// #given
const abortedSessionIDs: string[] = []
const client = {
session: {
prompt: async () => ({}),
abort: async (args: { path: { id: string } }) => {
abortedSessionIDs.push(args.path.id)
return {}
},
},
}
const manager = new BackgroundManager({ client, directory: tmpdir() } as unknown as PluginInput)
const completedTask: BackgroundTask = {
id: "task-completed",
sessionID: "session-completed",
parentSessionID: "parent-1",
parentMessageID: "msg-1",
description: "Completed task",
prompt: "Test",
agent: "test-agent",
status: "completed",
startedAt: new Date(),
completedAt: new Date(),
}
const cancelledTask: BackgroundTask = {
id: "task-cancelled",
sessionID: "session-cancelled",
parentSessionID: "parent-2",
parentMessageID: "msg-2",
description: "Cancelled task",
prompt: "Test",
agent: "test-agent",
status: "cancelled",
startedAt: new Date(),
completedAt: new Date(),
}
const pendingTask: BackgroundTask = {
id: "task-pending",
parentSessionID: "parent-3",
parentMessageID: "msg-3",
description: "Pending task",
prompt: "Test",
agent: "test-agent",
status: "pending",
queuedAt: new Date(),
}
getTaskMap(manager).set(completedTask.id, completedTask)
getTaskMap(manager).set(cancelledTask.id, cancelledTask)
getTaskMap(manager).set(pendingTask.id, pendingTask)
// #when
manager.shutdown()
// #then
expect(abortedSessionIDs).toHaveLength(0)
})
test("should call onShutdown callback during shutdown", () => {
// #given
let shutdownCalled = false
const client = {
session: {
prompt: async () => ({}),
abort: async () => ({}),
},
}
const manager = new BackgroundManager(
{ client, directory: tmpdir() } as unknown as PluginInput,
undefined,
{
onShutdown: () => {
shutdownCalled = true
},
}
)
// #when
manager.shutdown()
// #then
expect(shutdownCalled).toBe(true)
})
test("should not throw when onShutdown callback throws", () => {
// #given
const client = {
session: {
prompt: async () => ({}),
abort: async () => ({}),
},
}
const manager = new BackgroundManager(
{ client, directory: tmpdir() } as unknown as PluginInput,
undefined,
{
onShutdown: () => {
throw new Error("cleanup failed")
},
}
)
// #when / #then
expect(() => manager.shutdown()).not.toThrow()
})
})

View File

@@ -5,7 +5,7 @@ import type {
LaunchInput,
ResumeInput,
} from "./types"
import { log, getAgentToolRestrictions } from "../../shared"
import { log, getAgentToolRestrictions, promptWithModelSuggestionRetry } from "../../shared"
import { ConcurrencyManager } from "./concurrency"
import type { BackgroundTaskConfig, TmuxConfig } from "../../config/schema"
import { isInsideTmux } from "../../shared/tmux"
@@ -79,6 +79,7 @@ export class BackgroundManager {
private config?: BackgroundTaskConfig
private tmuxEnabled: boolean
private onSubagentSessionCreated?: OnSubagentSessionCreated
private onShutdown?: () => void
private queuesByKey: Map<string, QueueItem[]> = new Map()
private processingKeys: Set<string> = new Set()
@@ -89,6 +90,7 @@ export class BackgroundManager {
options?: {
tmuxConfig?: TmuxConfig
onSubagentSessionCreated?: OnSubagentSessionCreated
onShutdown?: () => void
}
) {
this.tasks = new Map()
@@ -100,6 +102,7 @@ export class BackgroundManager {
this.config = config
this.tmuxEnabled = options?.tmuxConfig?.enabled ?? false
this.onSubagentSessionCreated = options?.onSubagentSessionCreated
this.onShutdown = options?.onShutdown
this.registerProcessCleanup()
}
@@ -304,7 +307,7 @@ export class BackgroundManager {
: undefined
const launchVariant = input.model?.variant
this.client.session.prompt({
promptWithModelSuggestionRetry(this.client, {
path: { id: sessionID },
body: {
agent: input.agent,
@@ -1346,7 +1349,25 @@ Use \`background_output(task_id="${task.id}")\` to retrieve this result when rea
log("[background-agent] Shutting down BackgroundManager")
this.stopPolling()
// Release concurrency for all running tasks first
// Abort all running sessions to prevent zombie processes (#1240)
for (const task of this.tasks.values()) {
if (task.status === "running" && task.sessionID) {
this.client.session.abort({
path: { id: task.sessionID },
}).catch(() => {})
}
}
// Notify shutdown listeners (e.g., tmux cleanup)
if (this.onShutdown) {
try {
this.onShutdown()
} catch (error) {
log("[background-agent] Error in onShutdown callback:", error)
}
}
// Release concurrency for all running tasks
for (const task of this.tasks.values()) {
if (task.concurrencyKey) {
this.concurrencyManager.release(task.concurrencyKey)

View File

@@ -7,6 +7,10 @@ export interface ClaudeCodeMcpServer {
args?: string[]
env?: Record<string, string>
headers?: Record<string, string>
oauth?: {
clientId?: string
scopes?: string[]
}
disabled?: boolean
}

View File

@@ -2,10 +2,11 @@ import { existsSync, mkdirSync, readFileSync, readdirSync, writeFileSync } from
import { join } from "node:path"
import { MESSAGE_STORAGE, PART_STORAGE } from "./constants"
import type { MessageMeta, OriginalMessageContext, TextPart, ToolPermission } from "./types"
import { log } from "../../shared/logger"
export interface StoredMessage {
agent?: string
model?: { providerID?: string; modelID?: string }
model?: { providerID?: string; modelID?: string; variant?: string }
tools?: Record<string, ToolPermission>
}
@@ -117,7 +118,7 @@ export function injectHookMessage(
): boolean {
// Validate hook content to prevent empty message injection
if (!hookContent || hookContent.trim().length === 0) {
console.warn("[hook-message-injector] Attempted to inject empty hook content, skipping injection", {
log("[hook-message-injector] Attempted to inject empty hook content, skipping injection", {
sessionID,
hasAgent: !!originalMessage.agent,
hasModel: !!(originalMessage.model?.providerID && originalMessage.model?.modelID)
@@ -141,9 +142,17 @@ export function injectHookMessage(
const resolvedAgent = originalMessage.agent ?? fallback?.agent ?? "general"
const resolvedModel =
originalMessage.model?.providerID && originalMessage.model?.modelID
? { providerID: originalMessage.model.providerID, modelID: originalMessage.model.modelID }
? {
providerID: originalMessage.model.providerID,
modelID: originalMessage.model.modelID,
...(originalMessage.model.variant ? { variant: originalMessage.model.variant } : {})
}
: fallback?.model?.providerID && fallback?.model?.modelID
? { providerID: fallback.model.providerID, modelID: fallback.model.modelID }
? {
providerID: fallback.model.providerID,
modelID: fallback.model.modelID,
...(fallback.model.variant ? { variant: fallback.model.variant } : {})
}
: undefined
const resolvedTools = originalMessage.tools ?? fallback?.tools

View File

@@ -12,6 +12,7 @@ export interface MessageMeta {
model?: {
providerID: string
modelID: string
variant?: string
}
path?: {
cwd: string
@@ -25,6 +26,7 @@ export interface OriginalMessageContext {
model?: {
providerID?: string
modelID?: string
variant?: string
}
path?: {
cwd?: string

View File

@@ -0,0 +1,136 @@
import { afterEach, describe, expect, it } from "bun:test"
import { findAvailablePort, startCallbackServer, type CallbackServer } from "./callback-server"
const nativeFetch = Bun.fetch.bind(Bun)
describe("findAvailablePort", () => {
it("returns the start port when it is available", async () => {
//#given
const startPort = 19877
//#when
const port = await findAvailablePort(startPort)
//#then
expect(port).toBeGreaterThanOrEqual(startPort)
expect(port).toBeLessThan(startPort + 20)
})
it("skips busy ports and returns next available", async () => {
//#given
const blocker = Bun.serve({
port: 19877,
hostname: "127.0.0.1",
fetch: () => new Response(),
})
//#when
const port = await findAvailablePort(19877)
//#then
expect(port).toBeGreaterThan(19877)
blocker.stop(true)
})
})
describe("startCallbackServer", () => {
let server: CallbackServer | null = null
afterEach(async () => {
server?.close()
server = null
// Allow time for port to be released before next test
await Bun.sleep(10)
})
it("starts server and returns port", async () => {
//#given - no preconditions
//#when
server = await startCallbackServer()
//#then
expect(server.port).toBeGreaterThanOrEqual(19877)
expect(typeof server.waitForCallback).toBe("function")
expect(typeof server.close).toBe("function")
})
it("resolves callback with code and state from query params", async () => {
//#given
server = await startCallbackServer()
const callbackUrl = `http://127.0.0.1:${server.port}/oauth/callback?code=test-code&state=test-state`
//#when
// Use Promise.all to ensure fetch and waitForCallback run concurrently
// This prevents race condition where waitForCallback blocks before fetch starts
const [result, response] = await Promise.all([
server.waitForCallback(),
nativeFetch(callbackUrl)
])
//#then
expect(result).toEqual({ code: "test-code", state: "test-state" })
expect(response.status).toBe(200)
const html = await response.text()
expect(html).toContain("Authorization successful")
})
it("returns 404 for non-callback routes", async () => {
//#given
server = await startCallbackServer()
//#when
const response = await nativeFetch(`http://127.0.0.1:${server.port}/other`)
//#then
expect(response.status).toBe(404)
})
it("returns 400 and rejects when code is missing", async () => {
//#given
server = await startCallbackServer()
const callbackRejection = server.waitForCallback().catch((e: Error) => e)
//#when
const response = await nativeFetch(`http://127.0.0.1:${server.port}/oauth/callback?state=s`)
//#then
expect(response.status).toBe(400)
const error = await callbackRejection
expect(error).toBeInstanceOf(Error)
expect((error as Error).message).toContain("missing code or state")
})
it("returns 400 and rejects when state is missing", async () => {
//#given
server = await startCallbackServer()
const callbackRejection = server.waitForCallback().catch((e: Error) => e)
//#when
const response = await nativeFetch(`http://127.0.0.1:${server.port}/oauth/callback?code=c`)
//#then
expect(response.status).toBe(400)
const error = await callbackRejection
expect(error).toBeInstanceOf(Error)
expect((error as Error).message).toContain("missing code or state")
})
it("close stops the server immediately", async () => {
//#given
server = await startCallbackServer()
const port = server.port
//#when
server.close()
server = null
//#then
try {
await nativeFetch(`http://127.0.0.1:${port}/oauth/callback?code=c&state=s`)
expect(true).toBe(false)
} catch (error) {
expect(error).toBeDefined()
}
})
})

View File

@@ -0,0 +1,124 @@
const DEFAULT_PORT = 19877
const MAX_PORT_ATTEMPTS = 20
const TIMEOUT_MS = 5 * 60 * 1000
export type OAuthCallbackResult = {
code: string
state: string
}
export type CallbackServer = {
port: number
waitForCallback: () => Promise<OAuthCallbackResult>
close: () => void
}
const SUCCESS_HTML = `<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>OAuth Authorized</title>
<style>
body { font-family: -apple-system, BlinkMacSystemFont, sans-serif; display: flex; justify-content: center; align-items: center; height: 100vh; margin: 0; background: #0a0a0a; color: #fafafa; }
.container { text-align: center; }
h1 { font-size: 1.5rem; margin-bottom: 0.5rem; }
p { color: #888; }
</style>
</head>
<body>
<div class="container">
<h1>Authorization successful</h1>
<p>You can close this window and return to your terminal.</p>
</div>
</body>
</html>`
async function isPortAvailable(port: number): Promise<boolean> {
try {
const server = Bun.serve({
port,
hostname: "127.0.0.1",
fetch: () => new Response(),
})
server.stop(true)
return true
} catch {
return false
}
}
export async function findAvailablePort(startPort: number = DEFAULT_PORT): Promise<number> {
for (let attempt = 0; attempt < MAX_PORT_ATTEMPTS; attempt++) {
const port = startPort + attempt
if (await isPortAvailable(port)) {
return port
}
}
throw new Error(`No available port found in range ${startPort}-${startPort + MAX_PORT_ATTEMPTS - 1}`)
}
export async function startCallbackServer(startPort: number = DEFAULT_PORT): Promise<CallbackServer> {
const port = await findAvailablePort(startPort)
let resolveCallback: ((result: OAuthCallbackResult) => void) | null = null
let rejectCallback: ((error: Error) => void) | null = null
const callbackPromise = new Promise<OAuthCallbackResult>((resolve, reject) => {
resolveCallback = resolve
rejectCallback = reject
})
const timeoutId = setTimeout(() => {
rejectCallback?.(new Error("OAuth callback timed out after 5 minutes"))
server.stop(true)
}, TIMEOUT_MS)
const server = Bun.serve({
port,
hostname: "127.0.0.1",
fetch(request: Request): Response {
const url = new URL(request.url)
if (url.pathname !== "/oauth/callback") {
return new Response("Not Found", { status: 404 })
}
const oauthError = url.searchParams.get("error")
if (oauthError) {
const description = url.searchParams.get("error_description") ?? oauthError
clearTimeout(timeoutId)
rejectCallback?.(new Error(`OAuth authorization failed: ${description}`))
setTimeout(() => server.stop(true), 100)
return new Response(`Authorization failed: ${description}`, { status: 400 })
}
const code = url.searchParams.get("code")
const state = url.searchParams.get("state")
if (!code || !state) {
clearTimeout(timeoutId)
rejectCallback?.(new Error("OAuth callback missing code or state parameter"))
setTimeout(() => server.stop(true), 100)
return new Response("Missing code or state parameter", { status: 400 })
}
resolveCallback?.({ code, state })
clearTimeout(timeoutId)
setTimeout(() => server.stop(true), 100)
return new Response(SUCCESS_HTML, {
headers: { "content-type": "text/html; charset=utf-8" },
})
},
})
return {
port,
waitForCallback: () => callbackPromise,
close: () => {
clearTimeout(timeoutId)
server.stop(true)
},
}
}

View File

@@ -0,0 +1,164 @@
import { describe, expect, it } from "bun:test"
import {
getOrRegisterClient,
type ClientCredentials,
type ClientRegistrationStorage,
type DcrFetch,
} from "./dcr"
function createStorage(initial: ClientCredentials | null):
& ClientRegistrationStorage
& { getLastKey: () => string | null; getLastSet: () => ClientCredentials | null } {
let stored = initial
let lastKey: string | null = null
let lastSet: ClientCredentials | null = null
return {
getClientRegistration: () => stored,
setClientRegistration: (serverIdentifier: string, credentials: ClientCredentials) => {
lastKey = serverIdentifier
lastSet = credentials
stored = credentials
},
getLastKey: () => lastKey,
getLastSet: () => lastSet,
}
}
describe("getOrRegisterClient", () => {
it("returns cached registration when available", async () => {
// #given
const storage = createStorage({
clientId: "cached-client",
clientSecret: "cached-secret",
})
const fetchMock: DcrFetch = async () => {
throw new Error("fetch should not be called")
}
// #when
const result = await getOrRegisterClient({
registrationEndpoint: "https://server.example.com/register",
serverIdentifier: "server-1",
clientName: "Test Client",
redirectUris: ["https://app.example.com/callback"],
tokenEndpointAuthMethod: "client_secret_post",
storage,
fetch: fetchMock,
})
// #then
expect(result).toEqual({
clientId: "cached-client",
clientSecret: "cached-secret",
})
})
it("registers client and stores credentials when endpoint available", async () => {
// #given
const storage = createStorage(null)
let fetchCalled = false
const fetchMock: DcrFetch = async (
input: string,
init?: { method?: string; headers?: Record<string, string>; body?: string }
) => {
fetchCalled = true
expect(input).toBe("https://server.example.com/register")
if (typeof init?.body !== "string") {
throw new Error("Expected request body string")
}
const payload = JSON.parse(init.body)
expect(payload).toEqual({
redirect_uris: ["https://app.example.com/callback"],
client_name: "Test Client",
grant_types: ["authorization_code", "refresh_token"],
response_types: ["code"],
token_endpoint_auth_method: "client_secret_post",
})
return {
ok: true,
json: async () => ({
client_id: "registered-client",
client_secret: "registered-secret",
}),
}
}
// #when
const result = await getOrRegisterClient({
registrationEndpoint: "https://server.example.com/register",
serverIdentifier: "server-2",
clientName: "Test Client",
redirectUris: ["https://app.example.com/callback"],
tokenEndpointAuthMethod: "client_secret_post",
storage,
fetch: fetchMock,
})
// #then
expect(fetchCalled).toBe(true)
expect(result).toEqual({
clientId: "registered-client",
clientSecret: "registered-secret",
})
expect(storage.getLastKey()).toBe("server-2")
expect(storage.getLastSet()).toEqual({
clientId: "registered-client",
clientSecret: "registered-secret",
})
})
it("uses config client id when registration endpoint missing", async () => {
// #given
const storage = createStorage(null)
let fetchCalled = false
const fetchMock: DcrFetch = async () => {
fetchCalled = true
return {
ok: false,
json: async () => ({}),
}
}
// #when
const result = await getOrRegisterClient({
registrationEndpoint: undefined,
serverIdentifier: "server-3",
clientName: "Test Client",
redirectUris: ["https://app.example.com/callback"],
tokenEndpointAuthMethod: "client_secret_post",
clientId: "config-client",
storage,
fetch: fetchMock,
})
// #then
expect(fetchCalled).toBe(false)
expect(result).toEqual({ clientId: "config-client" })
})
it("falls back to config client id when registration fails", async () => {
// #given
const storage = createStorage(null)
const fetchMock: DcrFetch = async () => {
throw new Error("network error")
}
// #when
const result = await getOrRegisterClient({
registrationEndpoint: "https://server.example.com/register",
serverIdentifier: "server-4",
clientName: "Test Client",
redirectUris: ["https://app.example.com/callback"],
tokenEndpointAuthMethod: "client_secret_post",
clientId: "fallback-client",
storage,
fetch: fetchMock,
})
// #then
expect(result).toEqual({ clientId: "fallback-client" })
expect(storage.getLastSet()).toBeNull()
})
})

View File

@@ -0,0 +1,98 @@
export type ClientRegistrationRequest = {
redirect_uris: string[]
client_name: string
grant_types: ["authorization_code", "refresh_token"]
response_types: ["code"]
token_endpoint_auth_method: "none" | "client_secret_post"
}
export type ClientCredentials = {
clientId: string
clientSecret?: string
}
export type ClientRegistrationStorage = {
getClientRegistration: (serverIdentifier: string) => ClientCredentials | null
setClientRegistration: (
serverIdentifier: string,
credentials: ClientCredentials
) => void
}
export type DynamicClientRegistrationOptions = {
registrationEndpoint?: string | null
serverIdentifier?: string
clientName: string
redirectUris: string[]
tokenEndpointAuthMethod: "none" | "client_secret_post"
clientId?: string | null
storage: ClientRegistrationStorage
fetch?: DcrFetch
}
export type DcrFetch = (
input: string,
init?: { method?: string; headers?: Record<string, string>; body?: string }
) => Promise<{ ok: boolean; json: () => Promise<unknown> }>
export async function getOrRegisterClient(
options: DynamicClientRegistrationOptions
): Promise<ClientCredentials | null> {
const serverIdentifier =
options.serverIdentifier ?? options.registrationEndpoint ?? "default"
const existing = options.storage.getClientRegistration(serverIdentifier)
if (existing) return existing
if (!options.registrationEndpoint) {
return options.clientId ? { clientId: options.clientId } : null
}
const fetchImpl = options.fetch ?? globalThis.fetch
const request: ClientRegistrationRequest = {
redirect_uris: options.redirectUris,
client_name: options.clientName,
grant_types: ["authorization_code", "refresh_token"],
response_types: ["code"],
token_endpoint_auth_method: options.tokenEndpointAuthMethod,
}
try {
const response = await fetchImpl(options.registrationEndpoint, {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify(request),
})
if (!response.ok) {
return options.clientId ? { clientId: options.clientId } : null
}
const data: unknown = await response.json()
const parsed = parseRegistrationResponse(data)
if (!parsed) {
return options.clientId ? { clientId: options.clientId } : null
}
options.storage.setClientRegistration(serverIdentifier, parsed)
return parsed
} catch {
return options.clientId ? { clientId: options.clientId } : null
}
}
function parseRegistrationResponse(data: unknown): ClientCredentials | null {
if (!isRecord(data)) return null
const clientId = data.client_id
if (typeof clientId !== "string" || clientId.length === 0) return null
const clientSecret = data.client_secret
if (typeof clientSecret === "string" && clientSecret.length > 0) {
return { clientId, clientSecret }
}
return { clientId }
}
function isRecord(value: unknown): value is Record<string, unknown> {
return typeof value === "object" && value !== null
}

View File

@@ -0,0 +1,175 @@
import { describe, test, expect, beforeEach, afterEach } from "bun:test"
import { discoverOAuthServerMetadata, resetDiscoveryCache } from "./discovery"
describe("discoverOAuthServerMetadata", () => {
const originalFetch = globalThis.fetch
beforeEach(() => {
resetDiscoveryCache()
})
afterEach(() => {
Object.defineProperty(globalThis, "fetch", { value: originalFetch, configurable: true })
})
test("returns endpoints from PRM + AS discovery", () => {
// #given
const resource = "https://mcp.example.com"
const prmUrl = new URL("/.well-known/oauth-protected-resource", resource).toString()
const authServer = "https://auth.example.com"
const asUrl = new URL("/.well-known/oauth-authorization-server", authServer).toString()
const calls: string[] = []
const fetchMock = async (input: string | URL) => {
const url = typeof input === "string" ? input : input.toString()
calls.push(url)
if (url === prmUrl) {
return new Response(JSON.stringify({ authorization_servers: [authServer] }), { status: 200 })
}
if (url === asUrl) {
return new Response(
JSON.stringify({
authorization_endpoint: "https://auth.example.com/authorize",
token_endpoint: "https://auth.example.com/token",
registration_endpoint: "https://auth.example.com/register",
}),
{ status: 200 }
)
}
return new Response("not found", { status: 404 })
}
Object.defineProperty(globalThis, "fetch", { value: fetchMock, configurable: true })
// #when
return discoverOAuthServerMetadata(resource).then((result) => {
// #then
expect(result).toEqual({
authorizationEndpoint: "https://auth.example.com/authorize",
tokenEndpoint: "https://auth.example.com/token",
registrationEndpoint: "https://auth.example.com/register",
resource,
})
expect(calls).toEqual([prmUrl, asUrl])
})
})
test("falls back to RFC 8414 when PRM returns 404", () => {
// #given
const resource = "https://mcp.example.com"
const prmUrl = new URL("/.well-known/oauth-protected-resource", resource).toString()
const asUrl = new URL("/.well-known/oauth-authorization-server", resource).toString()
const calls: string[] = []
const fetchMock = async (input: string | URL) => {
const url = typeof input === "string" ? input : input.toString()
calls.push(url)
if (url === prmUrl) {
return new Response("not found", { status: 404 })
}
if (url === asUrl) {
return new Response(
JSON.stringify({
authorization_endpoint: "https://mcp.example.com/authorize",
token_endpoint: "https://mcp.example.com/token",
}),
{ status: 200 }
)
}
return new Response("not found", { status: 404 })
}
Object.defineProperty(globalThis, "fetch", { value: fetchMock, configurable: true })
// #when
return discoverOAuthServerMetadata(resource).then((result) => {
// #then
expect(result).toEqual({
authorizationEndpoint: "https://mcp.example.com/authorize",
tokenEndpoint: "https://mcp.example.com/token",
registrationEndpoint: undefined,
resource,
})
expect(calls).toEqual([prmUrl, asUrl])
})
})
test("throws when both PRM and AS discovery return 404", () => {
// #given
const resource = "https://mcp.example.com"
const prmUrl = new URL("/.well-known/oauth-protected-resource", resource).toString()
const asUrl = new URL("/.well-known/oauth-authorization-server", resource).toString()
const fetchMock = async (input: string | URL) => {
const url = typeof input === "string" ? input : input.toString()
if (url === prmUrl || url === asUrl) {
return new Response("not found", { status: 404 })
}
return new Response("not found", { status: 404 })
}
Object.defineProperty(globalThis, "fetch", { value: fetchMock, configurable: true })
// #when
const result = discoverOAuthServerMetadata(resource)
// #then
return expect(result).rejects.toThrow("OAuth authorization server metadata not found")
})
test("throws when AS metadata is malformed", () => {
// #given
const resource = "https://mcp.example.com"
const prmUrl = new URL("/.well-known/oauth-protected-resource", resource).toString()
const authServer = "https://auth.example.com"
const asUrl = new URL("/.well-known/oauth-authorization-server", authServer).toString()
const fetchMock = async (input: string | URL) => {
const url = typeof input === "string" ? input : input.toString()
if (url === prmUrl) {
return new Response(JSON.stringify({ authorization_servers: [authServer] }), { status: 200 })
}
if (url === asUrl) {
return new Response(JSON.stringify({ authorization_endpoint: "https://auth.example.com/authorize" }), {
status: 200,
})
}
return new Response("not found", { status: 404 })
}
Object.defineProperty(globalThis, "fetch", { value: fetchMock, configurable: true })
// #when
const result = discoverOAuthServerMetadata(resource)
// #then
return expect(result).rejects.toThrow("token_endpoint")
})
test("caches discovery results per resource URL", () => {
// #given
const resource = "https://mcp.example.com"
const prmUrl = new URL("/.well-known/oauth-protected-resource", resource).toString()
const authServer = "https://auth.example.com"
const asUrl = new URL("/.well-known/oauth-authorization-server", authServer).toString()
const calls: string[] = []
const fetchMock = async (input: string | URL) => {
const url = typeof input === "string" ? input : input.toString()
calls.push(url)
if (url === prmUrl) {
return new Response(JSON.stringify({ authorization_servers: [authServer] }), { status: 200 })
}
if (url === asUrl) {
return new Response(
JSON.stringify({
authorization_endpoint: "https://auth.example.com/authorize",
token_endpoint: "https://auth.example.com/token",
}),
{ status: 200 }
)
}
return new Response("not found", { status: 404 })
}
Object.defineProperty(globalThis, "fetch", { value: fetchMock, configurable: true })
// #when
return discoverOAuthServerMetadata(resource)
.then(() => discoverOAuthServerMetadata(resource))
.then(() => {
// #then
expect(calls).toEqual([prmUrl, asUrl])
})
})
})

View File

@@ -0,0 +1,123 @@
export interface OAuthServerMetadata {
authorizationEndpoint: string
tokenEndpoint: string
registrationEndpoint?: string
resource: string
}
const discoveryCache = new Map<string, OAuthServerMetadata>()
const pendingDiscovery = new Map<string, Promise<OAuthServerMetadata>>()
function parseHttpsUrl(value: string, label: string): URL {
const parsed = new URL(value)
if (parsed.protocol !== "https:") {
throw new Error(`${label} must use https`)
}
return parsed
}
function readStringField(source: Record<string, unknown>, field: string): string {
const value = source[field]
if (typeof value !== "string" || value.length === 0) {
throw new Error(`OAuth metadata missing ${field}`)
}
return value
}
async function fetchMetadata(url: string): Promise<{ ok: true; json: Record<string, unknown> } | { ok: false; status: number }> {
const response = await fetch(url, { headers: { accept: "application/json" } })
if (!response.ok) {
return { ok: false, status: response.status }
}
const json = (await response.json().catch(() => null)) as Record<string, unknown> | null
if (!json || typeof json !== "object") {
throw new Error("OAuth metadata response is not valid JSON")
}
return { ok: true, json }
}
async function fetchAuthorizationServerMetadata(issuer: string, resource: string): Promise<OAuthServerMetadata> {
const issuerUrl = parseHttpsUrl(issuer, "Authorization server URL")
const issuerPath = issuerUrl.pathname.replace(/\/+$/, "")
const metadataUrl = new URL(`/.well-known/oauth-authorization-server${issuerPath}`, issuerUrl).toString()
const metadata = await fetchMetadata(metadataUrl)
if (!metadata.ok) {
if (metadata.status === 404) {
throw new Error("OAuth authorization server metadata not found")
}
throw new Error(`OAuth authorization server metadata fetch failed (${metadata.status})`)
}
const authorizationEndpoint = parseHttpsUrl(
readStringField(metadata.json, "authorization_endpoint"),
"authorization_endpoint"
).toString()
const tokenEndpoint = parseHttpsUrl(
readStringField(metadata.json, "token_endpoint"),
"token_endpoint"
).toString()
const registrationEndpointValue = metadata.json.registration_endpoint
const registrationEndpoint =
typeof registrationEndpointValue === "string" && registrationEndpointValue.length > 0
? parseHttpsUrl(registrationEndpointValue, "registration_endpoint").toString()
: undefined
return {
authorizationEndpoint,
tokenEndpoint,
registrationEndpoint,
resource,
}
}
function parseAuthorizationServers(metadata: Record<string, unknown>): string[] {
const servers = metadata.authorization_servers
if (!Array.isArray(servers)) return []
return servers.filter((server): server is string => typeof server === "string" && server.length > 0)
}
export async function discoverOAuthServerMetadata(resource: string): Promise<OAuthServerMetadata> {
const resourceUrl = parseHttpsUrl(resource, "Resource server URL")
const resourceKey = resourceUrl.toString()
const cached = discoveryCache.get(resourceKey)
if (cached) return cached
const pending = pendingDiscovery.get(resourceKey)
if (pending) return pending
const discoveryPromise = (async () => {
const prmUrl = new URL("/.well-known/oauth-protected-resource", resourceUrl).toString()
const prmResponse = await fetchMetadata(prmUrl)
if (prmResponse.ok) {
const authServers = parseAuthorizationServers(prmResponse.json)
if (authServers.length === 0) {
throw new Error("OAuth protected resource metadata missing authorization_servers")
}
return fetchAuthorizationServerMetadata(authServers[0], resource)
}
if (prmResponse.status !== 404) {
throw new Error(`OAuth protected resource metadata fetch failed (${prmResponse.status})`)
}
return fetchAuthorizationServerMetadata(resourceKey, resource)
})()
pendingDiscovery.set(resourceKey, discoveryPromise)
try {
const result = await discoveryPromise
discoveryCache.set(resourceKey, result)
return result
} finally {
pendingDiscovery.delete(resourceKey)
}
}
export function resetDiscoveryCache(): void {
discoveryCache.clear()
pendingDiscovery.clear()
}

View File

@@ -0,0 +1 @@
export * from "./schema"

View File

@@ -0,0 +1,223 @@
import { describe, expect, it, beforeEach, afterEach, mock } from "bun:test"
import { createHash, randomBytes } from "node:crypto"
import { McpOAuthProvider, generateCodeVerifier, generateCodeChallenge, buildAuthorizationUrl } from "./provider"
import type { OAuthTokenData } from "./storage"
describe("McpOAuthProvider", () => {
describe("generateCodeVerifier", () => {
it("returns a base64url-encoded 32-byte random string", () => {
//#given
const verifier = generateCodeVerifier()
//#when
const decoded = Buffer.from(verifier, "base64url")
//#then
expect(decoded.length).toBe(32)
expect(verifier).toMatch(/^[A-Za-z0-9_-]+$/)
})
it("produces unique values on each call", () => {
//#given
const first = generateCodeVerifier()
//#when
const second = generateCodeVerifier()
//#then
expect(first).not.toBe(second)
})
})
describe("generateCodeChallenge", () => {
it("returns SHA256 base64url digest of the verifier", () => {
//#given
const verifier = "test-verifier-value"
const expected = createHash("sha256").update(verifier).digest("base64url")
//#when
const challenge = generateCodeChallenge(verifier)
//#then
expect(challenge).toBe(expected)
})
})
describe("buildAuthorizationUrl", () => {
it("builds URL with all required PKCE parameters", () => {
//#given
const endpoint = "https://auth.example.com/authorize"
//#when
const url = buildAuthorizationUrl(endpoint, {
clientId: "my-client",
redirectUri: "http://127.0.0.1:8912/callback",
codeChallenge: "challenge-value",
state: "state-value",
scopes: ["openid", "profile"],
resource: "https://mcp.example.com",
})
//#then
const parsed = new URL(url)
expect(parsed.origin + parsed.pathname).toBe("https://auth.example.com/authorize")
expect(parsed.searchParams.get("response_type")).toBe("code")
expect(parsed.searchParams.get("client_id")).toBe("my-client")
expect(parsed.searchParams.get("redirect_uri")).toBe("http://127.0.0.1:8912/callback")
expect(parsed.searchParams.get("code_challenge")).toBe("challenge-value")
expect(parsed.searchParams.get("code_challenge_method")).toBe("S256")
expect(parsed.searchParams.get("state")).toBe("state-value")
expect(parsed.searchParams.get("scope")).toBe("openid profile")
expect(parsed.searchParams.get("resource")).toBe("https://mcp.example.com")
})
it("omits scope when empty", () => {
//#given
const endpoint = "https://auth.example.com/authorize"
//#when
const url = buildAuthorizationUrl(endpoint, {
clientId: "my-client",
redirectUri: "http://127.0.0.1:8912/callback",
codeChallenge: "challenge-value",
state: "state-value",
scopes: [],
})
//#then
const parsed = new URL(url)
expect(parsed.searchParams.has("scope")).toBe(false)
})
it("omits resource when undefined", () => {
//#given
const endpoint = "https://auth.example.com/authorize"
//#when
const url = buildAuthorizationUrl(endpoint, {
clientId: "my-client",
redirectUri: "http://127.0.0.1:8912/callback",
codeChallenge: "challenge-value",
state: "state-value",
})
//#then
const parsed = new URL(url)
expect(parsed.searchParams.has("resource")).toBe(false)
})
})
describe("constructor and basic methods", () => {
it("stores serverUrl and optional clientId and scopes", () => {
//#given
const options = {
serverUrl: "https://mcp.example.com",
clientId: "my-client",
scopes: ["openid"],
}
//#when
const provider = new McpOAuthProvider(options)
//#then
expect(provider.tokens()).toBeNull()
expect(provider.clientInformation()).toBeNull()
expect(provider.codeVerifier()).toBeNull()
})
it("defaults scopes to empty array", () => {
//#given
const options = { serverUrl: "https://mcp.example.com" }
//#when
const provider = new McpOAuthProvider(options)
//#then
expect(provider.redirectUrl()).toBe("http://127.0.0.1:19877/callback")
})
})
describe("saveCodeVerifier / codeVerifier", () => {
it("stores and retrieves code verifier", () => {
//#given
const provider = new McpOAuthProvider({ serverUrl: "https://mcp.example.com" })
//#when
provider.saveCodeVerifier("my-verifier")
//#then
expect(provider.codeVerifier()).toBe("my-verifier")
})
})
describe("saveTokens / tokens", () => {
let originalEnv: string | undefined
beforeEach(() => {
originalEnv = process.env.OPENCODE_CONFIG_DIR
const { mkdirSync } = require("node:fs")
const { tmpdir } = require("node:os")
const { join } = require("node:path")
const testDir = join(tmpdir(), "mcp-oauth-provider-test-" + Date.now())
mkdirSync(testDir, { recursive: true })
process.env.OPENCODE_CONFIG_DIR = testDir
})
afterEach(() => {
if (originalEnv === undefined) {
delete process.env.OPENCODE_CONFIG_DIR
} else {
process.env.OPENCODE_CONFIG_DIR = originalEnv
}
})
it("persists and loads token data via storage", () => {
//#given
const provider = new McpOAuthProvider({ serverUrl: "https://mcp.example.com" })
const tokenData: OAuthTokenData = {
accessToken: "access-token-123",
refreshToken: "refresh-token-456",
expiresAt: 1710000000,
}
//#when
const saved = provider.saveTokens(tokenData)
const loaded = provider.tokens()
//#then
expect(saved).toBe(true)
expect(loaded).toEqual(tokenData)
})
})
describe("redirectToAuthorization", () => {
it("throws when no client information is set", async () => {
//#given
const provider = new McpOAuthProvider({ serverUrl: "https://mcp.example.com" })
const metadata = {
authorizationEndpoint: "https://auth.example.com/authorize",
tokenEndpoint: "https://auth.example.com/token",
resource: "https://mcp.example.com",
}
//#when
const result = provider.redirectToAuthorization(metadata)
//#then
await expect(result).rejects.toThrow("No client information available")
})
})
describe("redirectUrl", () => {
it("returns localhost callback URL with default port", () => {
//#given
const provider = new McpOAuthProvider({ serverUrl: "https://mcp.example.com" })
//#when
const url = provider.redirectUrl()
//#then
expect(url).toBe("http://127.0.0.1:19877/callback")
})
})
})

View File

@@ -0,0 +1,295 @@
import { createHash, randomBytes } from "node:crypto"
import { createServer } from "node:http"
import { spawn } from "node:child_process"
import type { OAuthTokenData } from "./storage"
import { loadToken, saveToken } from "./storage"
import { discoverOAuthServerMetadata } from "./discovery"
import type { OAuthServerMetadata } from "./discovery"
import { getOrRegisterClient } from "./dcr"
import type { ClientCredentials, ClientRegistrationStorage } from "./dcr"
import { findAvailablePort } from "./callback-server"
export type McpOAuthProviderOptions = {
serverUrl: string
clientId?: string
scopes?: string[]
}
type CallbackResult = {
code: string
state: string
}
function generateCodeVerifier(): string {
return randomBytes(32).toString("base64url")
}
function generateCodeChallenge(verifier: string): string {
return createHash("sha256").update(verifier).digest("base64url")
}
function buildAuthorizationUrl(
authorizationEndpoint: string,
options: {
clientId: string
redirectUri: string
codeChallenge: string
state: string
scopes?: string[]
resource?: string
}
): string {
const url = new URL(authorizationEndpoint)
url.searchParams.set("response_type", "code")
url.searchParams.set("client_id", options.clientId)
url.searchParams.set("redirect_uri", options.redirectUri)
url.searchParams.set("code_challenge", options.codeChallenge)
url.searchParams.set("code_challenge_method", "S256")
url.searchParams.set("state", options.state)
if (options.scopes && options.scopes.length > 0) {
url.searchParams.set("scope", options.scopes.join(" "))
}
if (options.resource) {
url.searchParams.set("resource", options.resource)
}
return url.toString()
}
const CALLBACK_TIMEOUT_MS = 5 * 60 * 1000
function startCallbackServer(port: number): Promise<CallbackResult> {
return new Promise((resolve, reject) => {
let timeoutId: ReturnType<typeof setTimeout>
const server = createServer((request, response) => {
clearTimeout(timeoutId)
const requestUrl = new URL(request.url ?? "/", `http://localhost:${port}`)
const code = requestUrl.searchParams.get("code")
const state = requestUrl.searchParams.get("state")
const error = requestUrl.searchParams.get("error")
if (error) {
const errorDescription = requestUrl.searchParams.get("error_description") ?? error
response.writeHead(400, { "content-type": "text/html" })
response.end("<html><body><h1>Authorization failed</h1></body></html>")
server.close()
reject(new Error(`OAuth authorization error: ${errorDescription}`))
return
}
if (!code || !state) {
response.writeHead(400, { "content-type": "text/html" })
response.end("<html><body><h1>Missing code or state</h1></body></html>")
server.close()
reject(new Error("OAuth callback missing code or state parameter"))
return
}
response.writeHead(200, { "content-type": "text/html" })
response.end("<html><body><h1>Authorization successful. You can close this tab.</h1></body></html>")
server.close()
resolve({ code, state })
})
timeoutId = setTimeout(() => {
server.close()
reject(new Error("OAuth callback timed out after 5 minutes"))
}, CALLBACK_TIMEOUT_MS)
server.listen(port, "127.0.0.1")
server.on("error", (err) => {
clearTimeout(timeoutId)
reject(err)
})
})
}
function openBrowser(url: string): void {
const platform = process.platform
let cmd: string
let args: string[]
if (platform === "darwin") {
cmd = "open"
args = [url]
} else if (platform === "win32") {
cmd = "explorer"
args = [url]
} else {
cmd = "xdg-open"
args = [url]
}
try {
const child = spawn(cmd, args, { stdio: "ignore", detached: true })
child.on("error", () => {})
child.unref()
} catch {
// Browser open failed — user must navigate manually
}
}
export class McpOAuthProvider {
private readonly serverUrl: string
private readonly configClientId: string | undefined
private readonly scopes: string[]
private storedCodeVerifier: string | null = null
private storedClientInfo: ClientCredentials | null = null
private callbackPort: number | null = null
constructor(options: McpOAuthProviderOptions) {
this.serverUrl = options.serverUrl
this.configClientId = options.clientId
this.scopes = options.scopes ?? []
}
tokens(): OAuthTokenData | null {
return loadToken(this.serverUrl, this.serverUrl)
}
saveTokens(tokenData: OAuthTokenData): boolean {
return saveToken(this.serverUrl, this.serverUrl, tokenData)
}
clientInformation(): ClientCredentials | null {
if (this.storedClientInfo) return this.storedClientInfo
const tokenData = this.tokens()
if (tokenData?.clientInfo) {
this.storedClientInfo = tokenData.clientInfo
return this.storedClientInfo
}
return null
}
redirectUrl(): string {
return `http://127.0.0.1:${this.callbackPort ?? 19877}/callback`
}
saveCodeVerifier(verifier: string): void {
this.storedCodeVerifier = verifier
}
codeVerifier(): string | null {
return this.storedCodeVerifier
}
async redirectToAuthorization(metadata: OAuthServerMetadata): Promise<CallbackResult> {
const verifier = generateCodeVerifier()
this.saveCodeVerifier(verifier)
const challenge = generateCodeChallenge(verifier)
const state = randomBytes(16).toString("hex")
const clientInfo = this.clientInformation()
if (!clientInfo) {
throw new Error("No client information available. Run login() or register a client first.")
}
if (this.callbackPort === null) {
this.callbackPort = await findAvailablePort()
}
const authUrl = buildAuthorizationUrl(metadata.authorizationEndpoint, {
clientId: clientInfo.clientId,
redirectUri: this.redirectUrl(),
codeChallenge: challenge,
state,
scopes: this.scopes,
resource: metadata.resource,
})
const callbackPromise = startCallbackServer(this.callbackPort)
openBrowser(authUrl)
const result = await callbackPromise
if (result.state !== state) {
throw new Error("OAuth state mismatch")
}
return result
}
async login(): Promise<OAuthTokenData> {
const metadata = await discoverOAuthServerMetadata(this.serverUrl)
const clientRegistrationStorage: ClientRegistrationStorage = {
getClientRegistration: () => this.storedClientInfo,
setClientRegistration: (_serverIdentifier: string, credentials: ClientCredentials) => {
this.storedClientInfo = credentials
},
}
const clientInfo = await getOrRegisterClient({
registrationEndpoint: metadata.registrationEndpoint,
serverIdentifier: this.serverUrl,
clientName: "oh-my-opencode",
redirectUris: [this.redirectUrl()],
tokenEndpointAuthMethod: "none",
clientId: this.configClientId,
storage: clientRegistrationStorage,
})
if (!clientInfo) {
throw new Error("Failed to obtain client credentials. Provide a clientId or ensure the server supports DCR.")
}
this.storedClientInfo = clientInfo
const { code } = await this.redirectToAuthorization(metadata)
const verifier = this.codeVerifier()
if (!verifier) {
throw new Error("Code verifier not found")
}
const tokenResponse = await fetch(metadata.tokenEndpoint, {
method: "POST",
headers: { "content-type": "application/x-www-form-urlencoded" },
body: new URLSearchParams({
grant_type: "authorization_code",
code,
redirect_uri: this.redirectUrl(),
client_id: clientInfo.clientId,
code_verifier: verifier,
...(metadata.resource ? { resource: metadata.resource } : {}),
}).toString(),
})
if (!tokenResponse.ok) {
let errorDetail = `${tokenResponse.status}`
try {
const body = (await tokenResponse.json()) as Record<string, unknown>
if (body.error) {
errorDetail = `${tokenResponse.status} ${body.error}`
if (body.error_description) {
errorDetail += `: ${body.error_description}`
}
}
} catch {
// Response body not JSON
}
throw new Error(`Token exchange failed: ${errorDetail}`)
}
const tokenData = (await tokenResponse.json()) as Record<string, unknown>
const accessToken = tokenData.access_token
if (typeof accessToken !== "string") {
throw new Error("Token response missing access_token")
}
const oauthTokenData: OAuthTokenData = {
accessToken,
refreshToken: typeof tokenData.refresh_token === "string" ? tokenData.refresh_token : undefined,
expiresAt:
typeof tokenData.expires_in === "number" ? Math.floor(Date.now() / 1000) + tokenData.expires_in : undefined,
clientInfo: {
clientId: clientInfo.clientId,
clientSecret: clientInfo.clientSecret,
},
}
this.saveTokens(oauthTokenData)
return oauthTokenData
}
}
export { generateCodeVerifier, generateCodeChallenge, buildAuthorizationUrl, startCallbackServer }

View File

@@ -0,0 +1,121 @@
import { describe, expect, it } from "bun:test"
import { addResourceToParams, getResourceIndicator } from "./resource-indicator"
describe("getResourceIndicator", () => {
it("returns URL unchanged when already normalized", () => {
// #given
const url = "https://mcp.example.com"
// #when
const result = getResourceIndicator(url)
// #then
expect(result).toBe("https://mcp.example.com")
})
it("strips trailing slash", () => {
// #given
const url = "https://mcp.example.com/"
// #when
const result = getResourceIndicator(url)
// #then
expect(result).toBe("https://mcp.example.com")
})
it("strips query parameters", () => {
// #given
const url = "https://mcp.example.com/v1?token=abc&debug=true"
// #when
const result = getResourceIndicator(url)
// #then
expect(result).toBe("https://mcp.example.com/v1")
})
it("strips fragment", () => {
// #given
const url = "https://mcp.example.com/v1#section"
// #when
const result = getResourceIndicator(url)
// #then
expect(result).toBe("https://mcp.example.com/v1")
})
it("strips query and trailing slash together", () => {
// #given
const url = "https://mcp.example.com/api/?key=val"
// #when
const result = getResourceIndicator(url)
// #then
expect(result).toBe("https://mcp.example.com/api")
})
it("preserves path segments", () => {
// #given
const url = "https://mcp.example.com/org/project/v2"
// #when
const result = getResourceIndicator(url)
// #then
expect(result).toBe("https://mcp.example.com/org/project/v2")
})
it("preserves port number", () => {
// #given
const url = "https://mcp.example.com:8443/api/"
// #when
const result = getResourceIndicator(url)
// #then
expect(result).toBe("https://mcp.example.com:8443/api")
})
})
describe("addResourceToParams", () => {
it("sets resource parameter on empty params", () => {
// #given
const params = new URLSearchParams()
const resource = "https://mcp.example.com"
// #when
addResourceToParams(params, resource)
// #then
expect(params.get("resource")).toBe("https://mcp.example.com")
})
it("adds resource alongside existing parameters", () => {
// #given
const params = new URLSearchParams({ grant_type: "authorization_code" })
const resource = "https://mcp.example.com/v1"
// #when
addResourceToParams(params, resource)
// #then
expect(params.get("grant_type")).toBe("authorization_code")
expect(params.get("resource")).toBe("https://mcp.example.com/v1")
})
it("overwrites existing resource parameter", () => {
// #given
const params = new URLSearchParams({ resource: "https://old.example.com" })
const resource = "https://new.example.com"
// #when
addResourceToParams(params, resource)
// #then
expect(params.get("resource")).toBe("https://new.example.com")
expect(params.getAll("resource")).toHaveLength(1)
})
})

View File

@@ -0,0 +1,16 @@
export function getResourceIndicator(url: string): string {
const parsed = new URL(url)
parsed.search = ""
parsed.hash = ""
let normalized = parsed.toString()
if (normalized.endsWith("/")) {
normalized = normalized.slice(0, -1)
}
return normalized
}
export function addResourceToParams(params: URLSearchParams, resource: string): void {
params.set("resource", resource)
}

View File

@@ -0,0 +1,60 @@
/// <reference types="bun-types" />
import { describe, expect, test } from "bun:test"
import { McpOauthSchema } from "./schema"
describe("McpOauthSchema", () => {
test("parses empty oauth config", () => {
//#given
const input = {}
//#when
const result = McpOauthSchema.parse(input)
//#then
expect(result).toEqual({})
})
test("parses oauth config with clientId", () => {
//#given
const input = { clientId: "client-123" }
//#when
const result = McpOauthSchema.parse(input)
//#then
expect(result).toEqual({ clientId: "client-123" })
})
test("parses oauth config with scopes", () => {
//#given
const input = { scopes: ["openid", "profile"] }
//#when
const result = McpOauthSchema.parse(input)
//#then
expect(result).toEqual({ scopes: ["openid", "profile"] })
})
test("rejects non-string clientId", () => {
//#given
const input = { clientId: 123 }
//#when
const result = McpOauthSchema.safeParse(input)
//#then
expect(result.success).toBe(false)
})
test("rejects non-string scopes", () => {
//#given
const input = { scopes: ["openid", 42] }
//#when
const result = McpOauthSchema.safeParse(input)
//#then
expect(result.success).toBe(false)
})
})

View File

@@ -0,0 +1,8 @@
import { z } from "zod"
export const McpOauthSchema = z.object({
clientId: z.string().optional(),
scopes: z.array(z.string()).optional(),
})
export type McpOauth = z.infer<typeof McpOauthSchema>

View File

@@ -0,0 +1,223 @@
import { describe, expect, it } from "bun:test"
import { isStepUpRequired, mergeScopes, parseWwwAuthenticate } from "./step-up"
describe("parseWwwAuthenticate", () => {
it("parses scope from simple Bearer header", () => {
// #given
const header = 'Bearer scope="read write"'
// #when
const result = parseWwwAuthenticate(header)
// #then
expect(result).toEqual({ requiredScopes: ["read", "write"] })
})
it("parses scope with error fields", () => {
// #given
const header = 'Bearer error="insufficient_scope", scope="admin"'
// #when
const result = parseWwwAuthenticate(header)
// #then
expect(result).toEqual({
requiredScopes: ["admin"],
error: "insufficient_scope",
})
})
it("parses all fields including error_description", () => {
// #given
const header =
'Bearer realm="example", error="insufficient_scope", error_description="Need admin access", scope="admin write"'
// #when
const result = parseWwwAuthenticate(header)
// #then
expect(result).toEqual({
requiredScopes: ["admin", "write"],
error: "insufficient_scope",
errorDescription: "Need admin access",
})
})
it("returns null for non-Bearer scheme", () => {
// #given
const header = 'Basic realm="example"'
// #when
const result = parseWwwAuthenticate(header)
// #then
expect(result).toBeNull()
})
it("returns null when no scope parameter present", () => {
// #given
const header = 'Bearer error="invalid_token"'
// #when
const result = parseWwwAuthenticate(header)
// #then
expect(result).toBeNull()
})
it("returns null for empty scope value", () => {
// #given
const header = 'Bearer scope=""'
// #when
const result = parseWwwAuthenticate(header)
// #then
expect(result).toBeNull()
})
it("returns null for bare Bearer with no params", () => {
// #given
const header = "Bearer"
// #when
const result = parseWwwAuthenticate(header)
// #then
expect(result).toBeNull()
})
it("handles case-insensitive Bearer prefix", () => {
// #given
const header = 'bearer scope="read"'
// #when
const result = parseWwwAuthenticate(header)
// #then
expect(result).toEqual({ requiredScopes: ["read"] })
})
it("parses single scope value", () => {
// #given
const header = 'Bearer scope="admin"'
// #when
const result = parseWwwAuthenticate(header)
// #then
expect(result).toEqual({ requiredScopes: ["admin"] })
})
})
describe("mergeScopes", () => {
it("merges new scopes into existing", () => {
// #given
const existing = ["read", "write"]
const required = ["admin", "write"]
// #when
const result = mergeScopes(existing, required)
// #then
expect(result).toEqual(["read", "write", "admin"])
})
it("returns required when existing is empty", () => {
// #given
const existing: string[] = []
const required = ["read", "write"]
// #when
const result = mergeScopes(existing, required)
// #then
expect(result).toEqual(["read", "write"])
})
it("returns existing when required is empty", () => {
// #given
const existing = ["read"]
const required: string[] = []
// #when
const result = mergeScopes(existing, required)
// #then
expect(result).toEqual(["read"])
})
it("deduplicates identical scopes", () => {
// #given
const existing = ["read", "write"]
const required = ["read", "write"]
// #when
const result = mergeScopes(existing, required)
// #then
expect(result).toEqual(["read", "write"])
})
})
describe("isStepUpRequired", () => {
it("returns step-up info for 403 with WWW-Authenticate", () => {
// #given
const statusCode = 403
const headers = { "www-authenticate": 'Bearer scope="admin"' }
// #when
const result = isStepUpRequired(statusCode, headers)
// #then
expect(result).toEqual({ requiredScopes: ["admin"] })
})
it("returns null for non-403 status", () => {
// #given
const statusCode = 401
const headers = { "www-authenticate": 'Bearer scope="admin"' }
// #when
const result = isStepUpRequired(statusCode, headers)
// #then
expect(result).toBeNull()
})
it("returns null when no WWW-Authenticate header", () => {
// #given
const statusCode = 403
const headers = { "content-type": "application/json" }
// #when
const result = isStepUpRequired(statusCode, headers)
// #then
expect(result).toBeNull()
})
it("handles capitalized WWW-Authenticate header", () => {
// #given
const statusCode = 403
const headers = { "WWW-Authenticate": 'Bearer scope="read write"' }
// #when
const result = isStepUpRequired(statusCode, headers)
// #then
expect(result).toEqual({ requiredScopes: ["read", "write"] })
})
it("returns null for 403 with unparseable WWW-Authenticate", () => {
// #given
const statusCode = 403
const headers = { "www-authenticate": 'Basic realm="example"' }
// #when
const result = isStepUpRequired(statusCode, headers)
// #then
expect(result).toBeNull()
})
})

View File

@@ -0,0 +1,79 @@
export interface StepUpInfo {
requiredScopes: string[]
error?: string
errorDescription?: string
}
export function parseWwwAuthenticate(header: string): StepUpInfo | null {
const trimmed = header.trim()
const lowerHeader = trimmed.toLowerCase()
const bearerIndex = lowerHeader.indexOf("bearer")
if (bearerIndex === -1) {
return null
}
const params = trimmed.slice(bearerIndex + "bearer".length).trim()
if (params.length === 0) {
return null
}
const scope = extractParam(params, "scope")
if (scope === null) {
return null
}
const requiredScopes = scope
.split(/\s+/)
.filter((s) => s.length > 0)
if (requiredScopes.length === 0) {
return null
}
const info: StepUpInfo = { requiredScopes }
const error = extractParam(params, "error")
if (error !== null) {
info.error = error
}
const errorDescription = extractParam(params, "error_description")
if (errorDescription !== null) {
info.errorDescription = errorDescription
}
return info
}
function extractParam(params: string, name: string): string | null {
const quotedPattern = new RegExp(`${name}="([^"]*)"`)
const quotedMatch = quotedPattern.exec(params)
if (quotedMatch) {
return quotedMatch[1]
}
const unquotedPattern = new RegExp(`${name}=([^\\s,]+)`)
const unquotedMatch = unquotedPattern.exec(params)
return unquotedMatch?.[1] ?? null
}
export function mergeScopes(existing: string[], required: string[]): string[] {
const set = new Set(existing)
for (const scope of required) {
set.add(scope)
}
return [...set]
}
export function isStepUpRequired(statusCode: number, headers: Record<string, string>): StepUpInfo | null {
if (statusCode !== 403) {
return null
}
const wwwAuth = headers["www-authenticate"] ?? headers["WWW-Authenticate"]
if (!wwwAuth) {
return null
}
return parseWwwAuthenticate(wwwAuth)
}

View File

@@ -0,0 +1,136 @@
import { describe, expect, test, beforeEach, afterEach } from "bun:test"
import { existsSync, mkdirSync, rmSync, readFileSync, statSync, writeFileSync } from "node:fs"
import { join } from "node:path"
import { tmpdir } from "node:os"
import {
deleteToken,
getMcpOauthStoragePath,
listAllTokens,
listTokensByHost,
loadToken,
saveToken,
} from "./storage"
import type { OAuthTokenData } from "./storage"
describe("mcp-oauth storage", () => {
const TEST_CONFIG_DIR = join(tmpdir(), "mcp-oauth-test-" + Date.now())
let originalConfigDir: string | undefined
beforeEach(() => {
originalConfigDir = process.env.OPENCODE_CONFIG_DIR
process.env.OPENCODE_CONFIG_DIR = TEST_CONFIG_DIR
if (!existsSync(TEST_CONFIG_DIR)) {
mkdirSync(TEST_CONFIG_DIR, { recursive: true })
}
})
afterEach(() => {
if (originalConfigDir === undefined) {
delete process.env.OPENCODE_CONFIG_DIR
} else {
process.env.OPENCODE_CONFIG_DIR = originalConfigDir
}
if (existsSync(TEST_CONFIG_DIR)) {
rmSync(TEST_CONFIG_DIR, { recursive: true, force: true })
}
})
test("should save tokens with {host}/{resource} key and set 0600 permissions", () => {
// #given
const token: OAuthTokenData = {
accessToken: "access-1",
refreshToken: "refresh-1",
expiresAt: 1710000000,
clientInfo: { clientId: "client-1", clientSecret: "secret-1" },
}
// #when
const success = saveToken("https://example.com:443", "mcp/v1", token)
const storagePath = getMcpOauthStoragePath()
const parsed = JSON.parse(readFileSync(storagePath, "utf-8")) as Record<string, OAuthTokenData>
const mode = statSync(storagePath).mode & 0o777
// #then
expect(success).toBe(true)
expect(Object.keys(parsed)).toEqual(["example.com/mcp/v1"])
expect(parsed["example.com/mcp/v1"].accessToken).toBe("access-1")
expect(mode).toBe(0o600)
})
test("should load a saved token", () => {
// #given
const token: OAuthTokenData = { accessToken: "access-2", refreshToken: "refresh-2" }
saveToken("api.example.com", "resource-a", token)
// #when
const loaded = loadToken("api.example.com:8443", "resource-a")
// #then
expect(loaded).toEqual(token)
})
test("should delete a token", () => {
// #given
const token: OAuthTokenData = { accessToken: "access-3" }
saveToken("api.example.com", "resource-b", token)
// #when
const success = deleteToken("api.example.com", "resource-b")
const loaded = loadToken("api.example.com", "resource-b")
// #then
expect(success).toBe(true)
expect(loaded).toBeNull()
})
test("should list tokens by host", () => {
// #given
saveToken("api.example.com", "resource-a", { accessToken: "access-a" })
saveToken("api.example.com", "resource-b", { accessToken: "access-b" })
saveToken("other.example.com", "resource-c", { accessToken: "access-c" })
// #when
const entries = listTokensByHost("api.example.com:5555")
// #then
expect(Object.keys(entries).sort()).toEqual([
"api.example.com/resource-a",
"api.example.com/resource-b",
])
expect(entries["api.example.com/resource-a"].accessToken).toBe("access-a")
})
test("should handle missing storage file", () => {
// #given
const storagePath = getMcpOauthStoragePath()
if (existsSync(storagePath)) {
rmSync(storagePath, { force: true })
}
// #when
const loaded = loadToken("api.example.com", "resource-a")
const entries = listTokensByHost("api.example.com")
// #then
expect(loaded).toBeNull()
expect(entries).toEqual({})
})
test("should handle invalid JSON", () => {
// #given
const storagePath = getMcpOauthStoragePath()
const dir = join(storagePath, "..")
if (!existsSync(dir)) {
mkdirSync(dir, { recursive: true })
}
writeFileSync(storagePath, "{not-valid-json", "utf-8")
// #when
const loaded = loadToken("api.example.com", "resource-a")
const entries = listTokensByHost("api.example.com")
// #then
expect(loaded).toBeNull()
expect(entries).toEqual({})
})
})

View File

@@ -0,0 +1,153 @@
import { chmodSync, existsSync, mkdirSync, readFileSync, unlinkSync, writeFileSync } from "node:fs"
import { dirname, join } from "node:path"
import { getOpenCodeConfigDir } from "../../shared"
export interface OAuthTokenData {
accessToken: string
refreshToken?: string
expiresAt?: number
clientInfo?: {
clientId: string
clientSecret?: string
}
}
type TokenStore = Record<string, OAuthTokenData>
const STORAGE_FILE_NAME = "mcp-oauth.json"
export function getMcpOauthStoragePath(): string {
return join(getOpenCodeConfigDir({ binary: "opencode" }), STORAGE_FILE_NAME)
}
function normalizeHost(serverHost: string): string {
let host = serverHost.trim()
if (!host) return host
if (host.includes("://")) {
try {
host = new URL(host).hostname
} catch {
host = host.split("/")[0]
}
} else {
host = host.split("/")[0]
}
if (host.startsWith("[")) {
const closing = host.indexOf("]")
if (closing !== -1) {
host = host.slice(0, closing + 1)
}
return host
}
if (host.includes(":")) {
host = host.split(":")[0]
}
return host
}
function normalizeResource(resource: string): string {
return resource.replace(/^\/+/, "")
}
function buildKey(serverHost: string, resource: string): string {
const host = normalizeHost(serverHost)
const normalizedResource = normalizeResource(resource)
return `${host}/${normalizedResource}`
}
function readStore(): TokenStore | null {
const filePath = getMcpOauthStoragePath()
if (!existsSync(filePath)) {
return null
}
try {
const content = readFileSync(filePath, "utf-8")
return JSON.parse(content) as TokenStore
} catch {
return null
}
}
function writeStore(store: TokenStore): boolean {
const filePath = getMcpOauthStoragePath()
try {
const dir = dirname(filePath)
if (!existsSync(dir)) {
mkdirSync(dir, { recursive: true })
}
writeFileSync(filePath, JSON.stringify(store, null, 2), { encoding: "utf-8", mode: 0o600 })
chmodSync(filePath, 0o600)
return true
} catch {
return false
}
}
export function loadToken(serverHost: string, resource: string): OAuthTokenData | null {
const store = readStore()
if (!store) return null
const key = buildKey(serverHost, resource)
return store[key] ?? null
}
export function saveToken(serverHost: string, resource: string, token: OAuthTokenData): boolean {
const store = readStore() ?? {}
const key = buildKey(serverHost, resource)
store[key] = token
return writeStore(store)
}
export function deleteToken(serverHost: string, resource: string): boolean {
const store = readStore()
if (!store) return true
const key = buildKey(serverHost, resource)
if (!(key in store)) {
return true
}
delete store[key]
if (Object.keys(store).length === 0) {
try {
const filePath = getMcpOauthStoragePath()
if (existsSync(filePath)) {
unlinkSync(filePath)
}
return true
} catch {
return false
}
}
return writeStore(store)
}
export function listTokensByHost(serverHost: string): TokenStore {
const store = readStore()
if (!store) return {}
const host = normalizeHost(serverHost)
const prefix = `${host}/`
const result: TokenStore = {}
for (const [key, value] of Object.entries(store)) {
if (key.startsWith(prefix)) {
result[key] = value
}
}
return result
}
export function listAllTokens(): TokenStore {
return readStore() ?? {}
}

View File

@@ -3,8 +3,6 @@ import { SkillMcpManager } from "./manager"
import type { SkillMcpClientInfo, SkillMcpServerContext } from "./types"
import type { ClaudeCodeMcpServer } from "../claude-code-mcp-loader/types"
// Mock the MCP SDK transports to avoid network calls
const mockHttpConnect = mock(() => Promise.reject(new Error("Mocked HTTP connection failure")))
const mockHttpClose = mock(() => Promise.resolve())
@@ -24,6 +22,21 @@ mock.module("@modelcontextprotocol/sdk/client/streamableHttp.js", () => ({
},
}))
const mockTokens = mock(() => null as { accessToken: string; refreshToken?: string; expiresAt?: number } | null)
const mockLogin = mock(() => Promise.resolve({ accessToken: "new-token" }))
mock.module("../mcp-oauth/provider", () => ({
McpOAuthProvider: class MockMcpOAuthProvider {
constructor(public options: { serverUrl: string; clientId?: string; scopes?: string[] }) {}
tokens() {
return mockTokens()
}
async login() {
return mockLogin()
}
},
}))
@@ -518,7 +531,6 @@ describe("SkillMcpManager", () => {
skillName: "retry-skill",
}
// Mock client that fails first time with "Not connected", then succeeds
let callCount = 0
const mockClient = {
callTool: mock(async () => {
@@ -531,7 +543,6 @@ describe("SkillMcpManager", () => {
close: mock(() => Promise.resolve()),
}
// Spy on getOrCreateClientWithRetry to inject mock client
const getOrCreateSpy = spyOn(manager as any, "getOrCreateClientWithRetry")
getOrCreateSpy.mockResolvedValue(mockClient)
@@ -539,9 +550,9 @@ describe("SkillMcpManager", () => {
const result = await manager.callTool(info, context, "test-tool", {})
// #then
expect(callCount).toBe(2) // First call fails, second succeeds
expect(callCount).toBe(2)
expect(result).toEqual([{ type: "text", text: "success" }])
expect(getOrCreateSpy).toHaveBeenCalledTimes(2) // Called twice due to retry
expect(getOrCreateSpy).toHaveBeenCalledTimes(2)
})
it("should fail after 3 retry attempts", async () => {
@@ -558,7 +569,6 @@ describe("SkillMcpManager", () => {
skillName: "fail-skill",
}
// Mock client that always fails with "Not connected"
const mockClient = {
callTool: mock(async () => {
throw new Error("Not connected")
@@ -573,7 +583,7 @@ describe("SkillMcpManager", () => {
await expect(manager.callTool(info, context, "test-tool", {})).rejects.toThrow(
/Failed after 3 reconnection attempts/
)
expect(getOrCreateSpy).toHaveBeenCalledTimes(3) // Initial + 2 retries
expect(getOrCreateSpy).toHaveBeenCalledTimes(3)
})
it("should not retry on non-connection errors", async () => {
@@ -590,7 +600,6 @@ describe("SkillMcpManager", () => {
skillName: "error-skill",
}
// Mock client that fails with non-connection error
const mockClient = {
callTool: mock(async () => {
throw new Error("Tool not found")
@@ -605,7 +614,194 @@ describe("SkillMcpManager", () => {
await expect(manager.callTool(info, context, "test-tool", {})).rejects.toThrow(
"Tool not found"
)
expect(getOrCreateSpy).toHaveBeenCalledTimes(1) // No retry
expect(getOrCreateSpy).toHaveBeenCalledTimes(1)
})
})
describe("OAuth integration", () => {
beforeEach(() => {
mockTokens.mockClear()
mockLogin.mockClear()
})
it("injects Authorization header when oauth config has stored tokens", async () => {
// #given
const info: SkillMcpClientInfo = {
serverName: "oauth-server",
skillName: "oauth-skill",
sessionID: "session-oauth-1",
}
const config: ClaudeCodeMcpServer = {
url: "https://mcp.example.com/mcp",
oauth: {
clientId: "my-client",
scopes: ["read", "write"],
},
}
mockTokens.mockReturnValue({ accessToken: "stored-access-token" })
// #when
try {
await manager.getOrCreateClient(info, config)
} catch { /* connection fails in test */ }
// #then
const headers = lastTransportInstance.options?.requestInit?.headers as Record<string, string> | undefined
expect(headers?.Authorization).toBe("Bearer stored-access-token")
})
it("does not inject Authorization header when no stored tokens exist and login fails", async () => {
// #given
const info: SkillMcpClientInfo = {
serverName: "oauth-no-token",
skillName: "oauth-skill",
sessionID: "session-oauth-2",
}
const config: ClaudeCodeMcpServer = {
url: "https://mcp.example.com/mcp",
oauth: {
clientId: "my-client",
},
}
mockTokens.mockReturnValue(null)
mockLogin.mockRejectedValue(new Error("Login failed"))
// #when
try {
await manager.getOrCreateClient(info, config)
} catch { /* connection fails in test */ }
// #then
const headers = lastTransportInstance.options?.requestInit?.headers as Record<string, string> | undefined
expect(headers?.Authorization).toBeUndefined()
})
it("preserves existing static headers alongside OAuth token", async () => {
// #given
const info: SkillMcpClientInfo = {
serverName: "oauth-with-headers",
skillName: "oauth-skill",
sessionID: "session-oauth-3",
}
const config: ClaudeCodeMcpServer = {
url: "https://mcp.example.com/mcp",
headers: {
"X-Custom": "custom-value",
},
oauth: {
clientId: "my-client",
},
}
mockTokens.mockReturnValue({ accessToken: "oauth-token" })
// #when
try {
await manager.getOrCreateClient(info, config)
} catch { /* connection fails in test */ }
// #then
const headers = lastTransportInstance.options?.requestInit?.headers as Record<string, string> | undefined
expect(headers?.["X-Custom"]).toBe("custom-value")
expect(headers?.Authorization).toBe("Bearer oauth-token")
})
it("does not create auth provider when oauth config is absent", async () => {
// #given
const info: SkillMcpClientInfo = {
serverName: "no-oauth-server",
skillName: "test-skill",
sessionID: "session-no-oauth",
}
const config: ClaudeCodeMcpServer = {
url: "https://mcp.example.com/mcp",
headers: {
Authorization: "Bearer static-token",
},
}
// #when
try {
await manager.getOrCreateClient(info, config)
} catch { /* connection fails in test */ }
// #then
const headers = lastTransportInstance.options?.requestInit?.headers as Record<string, string> | undefined
expect(headers?.Authorization).toBe("Bearer static-token")
expect(mockTokens).not.toHaveBeenCalled()
})
it("handles step-up auth by triggering re-login on 403 with scope", async () => {
// #given
const info: SkillMcpClientInfo = {
serverName: "stepup-server",
skillName: "stepup-skill",
sessionID: "session-stepup-1",
}
const config: ClaudeCodeMcpServer = {
url: "https://mcp.example.com/mcp",
oauth: {
clientId: "my-client",
scopes: ["read"],
},
}
const context: SkillMcpServerContext = {
config,
skillName: "stepup-skill",
}
mockTokens.mockReturnValue({ accessToken: "initial-token" })
mockLogin.mockResolvedValue({ accessToken: "upgraded-token" })
let callCount = 0
const mockClient = {
callTool: mock(async () => {
callCount++
if (callCount === 1) {
throw new Error('403 WWW-Authenticate: Bearer scope="admin write"')
}
return { content: [{ type: "text", text: "success" }] }
}),
close: mock(() => Promise.resolve()),
}
const getOrCreateSpy = spyOn(manager as any, "getOrCreateClientWithRetry")
getOrCreateSpy.mockResolvedValue(mockClient)
// #when
const result = await manager.callTool(info, context, "test-tool", {})
// #then
expect(result).toEqual([{ type: "text", text: "success" }])
expect(mockLogin).toHaveBeenCalled()
})
it("does not attempt step-up when oauth config is absent", async () => {
// #given
const info: SkillMcpClientInfo = {
serverName: "no-stepup-server",
skillName: "no-stepup-skill",
sessionID: "session-no-stepup",
}
const context: SkillMcpServerContext = {
config: {
url: "https://mcp.example.com/mcp",
},
skillName: "no-stepup-skill",
}
const mockClient = {
callTool: mock(async () => {
throw new Error('403 WWW-Authenticate: Bearer scope="admin"')
}),
close: mock(() => Promise.resolve()),
}
const getOrCreateSpy = spyOn(manager as any, "getOrCreateClientWithRetry")
getOrCreateSpy.mockResolvedValue(mockClient)
// #when / #then
await expect(manager.callTool(info, context, "test-tool", {})).rejects.toThrow(/403/)
expect(mockLogin).not.toHaveBeenCalled()
})
})
})

View File

@@ -4,6 +4,8 @@ import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/
import type { Tool, Resource, Prompt } from "@modelcontextprotocol/sdk/types.js"
import type { ClaudeCodeMcpServer } from "../claude-code-mcp-loader/types"
import { expandEnvVarsInObject } from "../claude-code-mcp-loader/env-expander"
import { McpOAuthProvider } from "../mcp-oauth/provider"
import { isStepUpRequired, mergeScopes } from "../mcp-oauth/step-up"
import { createCleanMcpEnvironment } from "./env-cleaner"
import type { SkillMcpClientInfo, SkillMcpServerContext } from "./types"
@@ -60,6 +62,7 @@ function getConnectionType(config: ClaudeCodeMcpServer): ConnectionType | null {
export class SkillMcpManager {
private clients: Map<string, ManagedClient> = new Map()
private pendingConnections: Map<string, Promise<Client>> = new Map()
private authProviders: Map<string, McpOAuthProvider> = new Map()
private cleanupRegistered = false
private cleanupInterval: ReturnType<typeof setInterval> | null = null
private readonly IDLE_TIMEOUT = 5 * 60 * 1000
@@ -68,6 +71,28 @@ export class SkillMcpManager {
return `${info.sessionID}:${info.skillName}:${info.serverName}`
}
/**
* Get or create an McpOAuthProvider for a given server URL + oauth config.
* Providers are cached by server URL to reuse tokens across reconnections.
*/
private getOrCreateAuthProvider(
serverUrl: string,
oauth: NonNullable<ClaudeCodeMcpServer["oauth"]>
): McpOAuthProvider {
const existing = this.authProviders.get(serverUrl)
if (existing) {
return existing
}
const provider = new McpOAuthProvider({
serverUrl,
clientId: oauth.clientId,
scopes: oauth.scopes,
})
this.authProviders.set(serverUrl, provider)
return provider
}
private registerProcessCleanup(): void {
if (this.cleanupRegistered) return
this.cleanupRegistered = true
@@ -204,7 +229,30 @@ export class SkillMcpManager {
// Build request init with headers if provided
const requestInit: RequestInit = {}
if (config.headers && Object.keys(config.headers).length > 0) {
requestInit.headers = config.headers
requestInit.headers = { ...config.headers }
}
let authProvider: McpOAuthProvider | undefined
if (config.oauth) {
authProvider = this.getOrCreateAuthProvider(config.url, config.oauth)
let tokenData = authProvider.tokens()
const isExpired = tokenData?.expiresAt != null && tokenData.expiresAt < Math.floor(Date.now() / 1000)
if (!tokenData || isExpired) {
try {
tokenData = await authProvider.login()
} catch {
// Login failed — proceed without auth header
}
}
if (tokenData) {
const existingHeaders = (requestInit.headers ?? {}) as Record<string, string>
requestInit.headers = {
...existingHeaders,
Authorization: `Bearer ${tokenData.accessToken}`,
}
}
}
const transport = new StreamableHTTPClientTransport(url, {
@@ -460,6 +508,12 @@ export class SkillMcpManager {
lastError = error instanceof Error ? error : new Error(String(error))
const errorMessage = lastError.message.toLowerCase()
const stepUpHandled = await this.handleStepUpIfNeeded(lastError, config)
if (stepUpHandled) {
await this.forceReconnect(info)
continue
}
if (!errorMessage.includes("not connected")) {
throw lastError
}
@@ -470,23 +524,66 @@ export class SkillMcpManager {
)
}
const key = this.getClientKey(info)
const existing = this.clients.get(key)
if (existing) {
this.clients.delete(key)
try {
await existing.client.close()
} catch { /* process may already be terminated */ }
try {
await existing.transport.close()
} catch { /* transport may already be terminated */ }
}
await this.forceReconnect(info)
}
}
throw lastError || new Error("Operation failed with unknown error")
}
private async handleStepUpIfNeeded(
error: Error,
config: ClaudeCodeMcpServer
): Promise<boolean> {
if (!config.oauth || !config.url) {
return false
}
const statusMatch = /\b403\b/.exec(error.message)
if (!statusMatch) {
return false
}
const headers: Record<string, string> = {}
const wwwAuthMatch = /WWW-Authenticate:\s*(.+)/i.exec(error.message)
if (wwwAuthMatch?.[1]) {
headers["www-authenticate"] = wwwAuthMatch[1]
}
const stepUp = isStepUpRequired(403, headers)
if (!stepUp) {
return false
}
const currentScopes = config.oauth.scopes ?? []
const merged = mergeScopes(currentScopes, stepUp.requiredScopes)
config.oauth.scopes = merged
this.authProviders.delete(config.url)
const provider = this.getOrCreateAuthProvider(config.url, config.oauth)
try {
await provider.login()
return true
} catch {
return false
}
}
private async forceReconnect(info: SkillMcpClientInfo): Promise<void> {
const key = this.getClientKey(info)
const existing = this.clients.get(key)
if (existing) {
this.clients.delete(key)
try {
await existing.client.close()
} catch { /* process may already be terminated */ }
try {
await existing.transport.close()
} catch { /* transport may already be terminated */ }
}
}
private async getOrCreateClientWithRetry(
info: SkillMcpClientInfo,
config: ClaudeCodeMcpServer

View File

@@ -2,6 +2,7 @@ import { describe, test, expect, mock, beforeEach } from 'bun:test'
import type { TmuxConfig } from '../../config/schema'
import type { WindowState, PaneAction } from './types'
import type { ActionResult, ExecuteContext } from './action-executor'
import type { TmuxUtilDeps } from './manager'
type ExecuteActionsResult = {
success: boolean
@@ -33,6 +34,11 @@ const mockExecuteAction = mock<(
const mockIsInsideTmux = mock<() => boolean>(() => true)
const mockGetCurrentPaneId = mock<() => string | undefined>(() => '%0')
const mockTmuxDeps: TmuxUtilDeps = {
isInsideTmux: mockIsInsideTmux,
getCurrentPaneId: mockGetCurrentPaneId,
}
mock.module('./pane-state-querier', () => ({
queryWindowState: mockQueryWindowState,
paneExists: mockPaneExists,
@@ -51,15 +57,19 @@ mock.module('./action-executor', () => ({
executeAction: mockExecuteAction,
}))
mock.module('../../shared/tmux', () => ({
isInsideTmux: mockIsInsideTmux,
getCurrentPaneId: mockGetCurrentPaneId,
POLL_INTERVAL_BACKGROUND_MS: 2000,
SESSION_TIMEOUT_MS: 600000,
SESSION_MISSING_GRACE_MS: 6000,
SESSION_READY_POLL_INTERVAL_MS: 100,
SESSION_READY_TIMEOUT_MS: 500,
}))
mock.module('../../shared/tmux', () => {
const { isInsideTmux, getCurrentPaneId } = require('../../shared/tmux/tmux-utils')
const { POLL_INTERVAL_BACKGROUND_MS, SESSION_TIMEOUT_MS, SESSION_MISSING_GRACE_MS } = require('../../shared/tmux/constants')
return {
isInsideTmux,
getCurrentPaneId,
POLL_INTERVAL_BACKGROUND_MS,
SESSION_TIMEOUT_MS,
SESSION_MISSING_GRACE_MS,
SESSION_READY_POLL_INTERVAL_MS: 100,
SESSION_READY_TIMEOUT_MS: 500,
}
})
const trackedSessions = new Set<string>()
@@ -148,7 +158,7 @@ describe('TmuxSessionManager', () => {
}
//#when
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
//#then
expect(manager).toBeDefined()
@@ -168,7 +178,7 @@ describe('TmuxSessionManager', () => {
}
//#when
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
//#then
expect(manager).toBeDefined()
@@ -188,7 +198,7 @@ describe('TmuxSessionManager', () => {
}
//#when
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
//#then
expect(manager).toBeDefined()
@@ -210,7 +220,7 @@ describe('TmuxSessionManager', () => {
main_pane_min_width: 80,
agent_pane_min_width: 40,
}
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
const event = createSessionCreatedEvent(
'ses_child',
'ses_parent',
@@ -271,7 +281,7 @@ describe('TmuxSessionManager', () => {
main_pane_min_width: 80,
agent_pane_min_width: 40,
}
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
//#when - first agent
await manager.onSessionCreated(
@@ -305,7 +315,7 @@ describe('TmuxSessionManager', () => {
main_pane_min_width: 80,
agent_pane_min_width: 40,
}
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
const event = createSessionCreatedEvent('ses_root', undefined, 'Root Session')
//#when
@@ -327,7 +337,7 @@ describe('TmuxSessionManager', () => {
main_pane_min_width: 80,
agent_pane_min_width: 40,
}
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
const event = createSessionCreatedEvent(
'ses_child',
'ses_parent',
@@ -353,7 +363,7 @@ describe('TmuxSessionManager', () => {
main_pane_min_width: 80,
agent_pane_min_width: 40,
}
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
const event = {
type: 'session.deleted',
properties: {
@@ -398,7 +408,7 @@ describe('TmuxSessionManager', () => {
main_pane_min_width: 120,
agent_pane_min_width: 40,
}
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
//#when
await manager.onSessionCreated(
@@ -450,7 +460,7 @@ describe('TmuxSessionManager', () => {
main_pane_min_width: 80,
agent_pane_min_width: 40,
}
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
await manager.onSessionCreated(
createSessionCreatedEvent(
@@ -487,7 +497,7 @@ describe('TmuxSessionManager', () => {
main_pane_min_width: 80,
agent_pane_min_width: 40,
}
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
//#when
await manager.onSessionDeleted({ sessionID: 'ses_unknown' })
@@ -521,7 +531,7 @@ describe('TmuxSessionManager', () => {
main_pane_min_width: 80,
agent_pane_min_width: 40,
}
const manager = new TmuxSessionManager(ctx, config)
const manager = new TmuxSessionManager(ctx, config, mockTmuxDeps)
await manager.onSessionCreated(
createSessionCreatedEvent('ses_1', 'ses_parent', 'Task 1')

View File

@@ -2,8 +2,8 @@ import type { PluginInput } from "@opencode-ai/plugin"
import type { TmuxConfig } from "../../config/schema"
import type { TrackedSession, CapacityConfig } from "./types"
import {
isInsideTmux,
getCurrentPaneId,
isInsideTmux as defaultIsInsideTmux,
getCurrentPaneId as defaultGetCurrentPaneId,
POLL_INTERVAL_BACKGROUND_MS,
SESSION_MISSING_GRACE_MS,
SESSION_READY_POLL_INTERVAL_MS,
@@ -21,6 +21,16 @@ interface SessionCreatedEvent {
properties?: { info?: { id?: string; parentID?: string; title?: string } }
}
export interface TmuxUtilDeps {
isInsideTmux: () => boolean
getCurrentPaneId: () => string | undefined
}
const defaultTmuxDeps: TmuxUtilDeps = {
isInsideTmux: defaultIsInsideTmux,
getCurrentPaneId: defaultGetCurrentPaneId,
}
const SESSION_TIMEOUT_MS = 10 * 60 * 1000
/**
@@ -43,13 +53,15 @@ export class TmuxSessionManager {
private sessions = new Map<string, TrackedSession>()
private pendingSessions = new Set<string>()
private pollInterval?: ReturnType<typeof setInterval>
private deps: TmuxUtilDeps
constructor(ctx: PluginInput, tmuxConfig: TmuxConfig) {
constructor(ctx: PluginInput, tmuxConfig: TmuxConfig, deps: TmuxUtilDeps = defaultTmuxDeps) {
this.client = ctx.client
this.tmuxConfig = tmuxConfig
this.deps = deps
const defaultPort = process.env.OPENCODE_PORT ?? "4096"
this.serverUrl = ctx.serverUrl?.toString() ?? `http://localhost:${defaultPort}`
this.sourcePaneId = getCurrentPaneId()
this.sourcePaneId = deps.getCurrentPaneId()
log("[tmux-session-manager] initialized", {
configEnabled: this.tmuxConfig.enabled,
@@ -60,7 +72,7 @@ export class TmuxSessionManager {
}
private isEnabled(): boolean {
return this.tmuxConfig.enabled && isInsideTmux()
return this.tmuxConfig.enabled && this.deps.isInsideTmux()
}
private getCapacityConfig(): CapacityConfig {
@@ -113,7 +125,7 @@ export class TmuxSessionManager {
log("[tmux-session-manager] onSessionCreated called", {
enabled,
tmuxConfigEnabled: this.tmuxConfig.enabled,
isInsideTmux: isInsideTmux(),
isInsideTmux: this.deps.isInsideTmux(),
eventType: event.type,
infoId: event.properties?.info?.id,
infoParentID: event.properties?.info?.parentID,

View File

@@ -1,11 +1,83 @@
import { describe, test, expect, mock, beforeEach, spyOn } from "bun:test"
import { afterEach, beforeEach, describe, expect, mock, spyOn, test } from "bun:test"
import { executeCompact } from "./executor"
import type { AutoCompactState } from "./types"
import * as storage from "./storage"
type TimerCallback = (...args: any[]) => void
interface FakeTimeouts {
advanceBy: (ms: number) => Promise<void>
restore: () => void
}
function createFakeTimeouts(): FakeTimeouts {
let now = 0
let nextId = 1
const timers = new Map<number, { id: number; time: number; callback: TimerCallback; args: any[] }>()
const cleared = new Set<number>()
const original = {
setTimeout: globalThis.setTimeout,
clearTimeout: globalThis.clearTimeout,
}
const normalizeDelay = (delay?: number) => {
if (typeof delay !== "number" || !Number.isFinite(delay)) return 0
return delay < 0 ? 0 : delay
}
globalThis.setTimeout = ((callback: TimerCallback, delay?: number, ...args: any[]) => {
const id = nextId++
timers.set(id, {
id,
time: now + normalizeDelay(delay),
callback,
args,
})
return id as unknown as ReturnType<typeof setTimeout>
}) as typeof setTimeout
globalThis.clearTimeout = ((id?: number) => {
if (typeof id !== "number") return
cleared.add(id)
timers.delete(id)
}) as typeof clearTimeout
const advanceBy = async (ms: number) => {
const target = now + Math.max(0, ms)
while (true) {
let next: { id: number; time: number; callback: TimerCallback; args: any[] } | undefined
for (const timer of timers.values()) {
if (timer.time <= target && (!next || timer.time < next.time)) {
next = timer
}
}
if (!next) break
now = next.time
timers.delete(next.id)
if (!cleared.has(next.id)) {
next.callback(...next.args)
}
cleared.delete(next.id)
await Promise.resolve()
}
now = target
await Promise.resolve()
}
const restore = () => {
globalThis.setTimeout = original.setTimeout
globalThis.clearTimeout = original.clearTimeout
}
return { advanceBy, restore }
}
describe("executeCompact lock management", () => {
let autoCompactState: AutoCompactState
let mockClient: any
let fakeTimeouts: FakeTimeouts
const sessionID = "test-session-123"
const directory = "/test/dir"
const msg = { providerID: "anthropic", modelID: "claude-opus-4-5" }
@@ -32,6 +104,12 @@ describe("executeCompact lock management", () => {
showToast: mock(() => Promise.resolve()),
},
}
fakeTimeouts = createFakeTimeouts()
})
afterEach(() => {
fakeTimeouts.restore()
})
test("clears lock on successful summarize completion", async () => {
@@ -216,7 +294,7 @@ describe("executeCompact lock management", () => {
await executeCompact(sessionID, msg, autoCompactState, mockClient, directory)
// Wait for setTimeout callback
await new Promise((resolve) => setTimeout(resolve, 600))
await fakeTimeouts.advanceBy(600)
// #then: Lock should be cleared
// The continuation happens in setTimeout, but lock is cleared in finally before that
@@ -288,7 +366,7 @@ describe("executeCompact lock management", () => {
await executeCompact(sessionID, msg, autoCompactState, mockClient, directory)
// Wait for setTimeout callback
await new Promise((resolve) => setTimeout(resolve, 600))
await fakeTimeouts.advanceBy(600)
// #then: Truncation was attempted
expect(truncateSpy).toHaveBeenCalled()

View File

@@ -4,6 +4,7 @@ import { join } from "path"
import { homedir, tmpdir } from "os"
import { createRequire } from "module"
import { extractZip } from "../../shared"
import { log } from "../../shared/logger"
const DEBUG = process.env.COMMENT_CHECKER_DEBUG === "1"
const DEBUG_FILE = join(tmpdir(), "comment-checker-debug.log")
@@ -127,7 +128,7 @@ export async function downloadCommentChecker(): Promise<string | null> {
const downloadUrl = `https://github.com/${REPO}/releases/download/v${version}/${assetName}`
debugLog(`Downloading from: ${downloadUrl}`)
console.log(`[oh-my-opencode] Downloading comment-checker binary...`)
log(`[oh-my-opencode] Downloading comment-checker binary...`)
try {
// Ensure cache directory exists
@@ -166,14 +167,14 @@ export async function downloadCommentChecker(): Promise<string | null> {
}
debugLog(`Successfully downloaded binary to: ${binaryPath}`)
console.log(`[oh-my-opencode] comment-checker binary ready.`)
log(`[oh-my-opencode] comment-checker binary ready.`)
return binaryPath
} catch (err) {
debugLog(`Failed to download: ${err}`)
console.error(`[oh-my-opencode] Failed to download comment-checker: ${err instanceof Error ? err.message : err}`)
console.error(`[oh-my-opencode] Comment checking disabled.`)
log(`[oh-my-opencode] Failed to download comment-checker: ${err instanceof Error ? err.message : err}`)
log(`[oh-my-opencode] Comment checking disabled.`)
return null
}
}

View File

@@ -6,6 +6,7 @@ import {
} from "./storage";
import { OMO_SESSION_PREFIX, buildSessionReminderMessage } from "./constants";
import type { InteractiveBashSessionState } from "./types";
import { subagentSessions } from "../../features/claude-code-session-state";
interface ToolExecuteInput {
tool: string;
@@ -146,7 +147,7 @@ function findSubcommand(tokens: string[]): string {
return ""
}
export function createInteractiveBashSessionHook(_ctx: PluginInput) {
export function createInteractiveBashSessionHook(ctx: PluginInput) {
const sessionStates = new Map<string, InteractiveBashSessionState>();
function getOrCreateState(sessionID: string): InteractiveBashSessionState {
@@ -178,6 +179,10 @@ export function createInteractiveBashSessionHook(_ctx: PluginInput) {
await proc.exited;
} catch {}
}
for (const sessionId of subagentSessions) {
ctx.client.session.abort({ path: { id: sessionId } }).catch(() => {})
}
}
const toolExecuteAfter = async (

View File

@@ -180,7 +180,9 @@ ${ULTRAWORK_PLANNER_SECTION}
1. **THINK DEEPLY** - What is the user's TRUE intent? What problem are they REALLY trying to solve?
2. **EXPLORE THOROUGHLY** - Fire explore/librarian agents to gather ALL relevant context
3. **CONSULT ORACLE** - For architecture decisions, complex logic, or when you're stuck
3. **CONSULT SPECIALISTS** - For hard/complex tasks, DO NOT struggle alone. Delegate:
- **Oracle**: Conventional problems - architecture, debugging, complex logic
- **Artistry**: Non-conventional problems - different approach needed, unusual constraints
4. **ASK THE USER** - If ambiguity remains after exploration, ASK. Don't guess.
**SIGNS YOU ARE NOT READY TO IMPLEMENT:**
@@ -194,7 +196,10 @@ ${ULTRAWORK_PLANNER_SECTION}
\`\`\`
delegate_task(agent="explore", prompt="Find [X] patterns in codebase", background=true)
delegate_task(agent="librarian", prompt="Find docs/examples for [Y]", background=true)
delegate_task(agent="oracle", prompt="Review my approach: [describe plan]")
// Hard problem? DON'T struggle alone:
delegate_task(agent="oracle", prompt="...") // conventional: architecture, debugging
delegate_task(category="artistry", prompt="...") // non-conventional: needs different approach
\`\`\`
**ONLY AFTER YOU HAVE:**
@@ -229,7 +234,7 @@ delegate_task(agent="oracle", prompt="Review my approach: [describe plan]")
**IF YOU ENCOUNTER A BLOCKER:**
1. **DO NOT** give up
2. **DO NOT** deliver a compromised version
3. **DO** consult oracle for solutions
3. **DO** consult specialists (oracle for conventional, artistry for non-conventional)
4. **DO** ask the user for guidance
5. **DO** explore alternative approaches
@@ -298,7 +303,8 @@ delegate_task(session_id="ses_abc123", prompt="Here's my answer to your question
| Codebase exploration | delegate_task(subagent_type="explore", run_in_background=true) | Parallel, context-efficient |
| Documentation lookup | delegate_task(subagent_type="librarian", run_in_background=true) | Specialized knowledge |
| Planning | delegate_task(subagent_type="plan") | Parallel task graph + structured TODO list |
| Architecture/Debugging | delegate_task(subagent_type="oracle") | High-IQ reasoning |
| Hard problem (conventional) | delegate_task(subagent_type="oracle") | Architecture, debugging, complex logic |
| Hard problem (non-conventional) | delegate_task(category="artistry", load_skills=[...]) | Different approach needed |
| Implementation | delegate_task(category="...", load_skills=[...]) | Domain-optimized models |
**CATEGORY + SKILL DELEGATION:**
@@ -490,8 +496,9 @@ CONTEXT GATHERING (parallel):
- 1-2 librarian agents (if external library involved)
- Direct tools: Grep, AST-grep, LSP for targeted searches
IF COMPLEX (architecture, multi-system, debugging after 2+ failures):
- Consult oracle for strategic guidance
IF COMPLEX - DO NOT STRUGGLE ALONE. Consult specialists:
- **Oracle**: Conventional problems (architecture, debugging, complex logic)
- **Artistry**: Non-conventional problems (different approach needed)
SYNTHESIZE findings before proceeding.`,
},

View File

@@ -16,6 +16,7 @@ import {
stripThinkingParts,
} from "./storage"
import type { MessageData, ResumeConfig } from "./types"
import { log } from "../../shared/logger"
export interface SessionRecoveryOptions {
experimental?: ExperimentalConfig
@@ -414,7 +415,7 @@ export function createSessionRecoveryHook(ctx: PluginInput, options?: SessionRec
return success
} catch (err) {
console.error("[session-recovery] Recovery failed:", err)
log("[session-recovery] Recovery failed:", err)
return false
} finally {
processingErrors.delete(assistantMsgID)

View File

@@ -10,7 +10,7 @@ import {
clearBoulderState,
} from "../../features/boulder-state"
import { log } from "../../shared/logger"
import { updateSessionAgent } from "../../features/claude-code-session-state"
import { getSessionAgent, updateSessionAgent } from "../../features/claude-code-session-state"
export const HOOK_NAME = "start-work"
@@ -71,7 +71,10 @@ export function createStartWorkHook(ctx: PluginInput) {
sessionID: input.sessionID,
})
updateSessionAgent(input.sessionID, "atlas")
const currentAgent = getSessionAgent(input.sessionID)
if (!currentAgent) {
updateSessionAgent(input.sessionID, "atlas")
}
const existingState = readBoulderState(ctx.directory)
const sessionId = input.sessionID

View File

@@ -4,9 +4,123 @@ import type { BackgroundManager } from "../features/background-agent"
import { setMainSession, subagentSessions, _resetForTesting } from "../features/claude-code-session-state"
import { createTodoContinuationEnforcer } from "./todo-continuation-enforcer"
type TimerCallback = (...args: any[]) => void
interface FakeTimers {
advanceBy: (ms: number, advanceClock?: boolean) => Promise<void>
restore: () => void
}
function createFakeTimers(): FakeTimers {
const originalNow = Date.now()
let clockNow = originalNow
let timerNow = 0
let nextId = 1
const timers = new Map<number, { id: number; time: number; interval: number | null; callback: TimerCallback; args: any[] }>()
const cleared = new Set<number>()
const original = {
setTimeout: globalThis.setTimeout,
clearTimeout: globalThis.clearTimeout,
setInterval: globalThis.setInterval,
clearInterval: globalThis.clearInterval,
dateNow: Date.now,
}
const normalizeDelay = (delay?: number) => {
if (typeof delay !== "number" || !Number.isFinite(delay)) return 0
return delay < 0 ? 0 : delay
}
const schedule = (callback: TimerCallback, delay: number | undefined, interval: number | null, args: any[]) => {
const id = nextId++
timers.set(id, {
id,
time: timerNow + normalizeDelay(delay),
interval,
callback,
args,
})
return id
}
const clear = (id: number | undefined) => {
if (typeof id !== "number") return
cleared.add(id)
timers.delete(id)
}
globalThis.setTimeout = ((callback: TimerCallback, delay?: number, ...args: any[]) => {
return schedule(callback, delay, null, args) as unknown as ReturnType<typeof setTimeout>
}) as typeof setTimeout
globalThis.setInterval = ((callback: TimerCallback, delay?: number, ...args: any[]) => {
const interval = normalizeDelay(delay)
return schedule(callback, delay, interval, args) as unknown as ReturnType<typeof setInterval>
}) as typeof setInterval
globalThis.clearTimeout = ((id?: number) => {
clear(id)
}) as typeof clearTimeout
globalThis.clearInterval = ((id?: number) => {
clear(id)
}) as typeof clearInterval
Date.now = () => clockNow
const advanceBy = async (ms: number, advanceClock: boolean = false) => {
const clamped = Math.max(0, ms)
const target = timerNow + clamped
if (advanceClock) {
clockNow += clamped
}
while (true) {
let next: { id: number; time: number; interval: number | null; callback: TimerCallback; args: any[] } | undefined
for (const timer of timers.values()) {
if (timer.time <= target && (!next || timer.time < next.time)) {
next = timer
}
}
if (!next) break
timerNow = next.time
timers.delete(next.id)
next.callback(...next.args)
if (next.interval !== null && !cleared.has(next.id)) {
timers.set(next.id, {
id: next.id,
time: timerNow + next.interval,
interval: next.interval,
callback: next.callback,
args: next.args,
})
} else {
cleared.delete(next.id)
}
await Promise.resolve()
}
timerNow = target
await Promise.resolve()
}
const restore = () => {
globalThis.setTimeout = original.setTimeout
globalThis.clearTimeout = original.clearTimeout
globalThis.setInterval = original.setInterval
globalThis.clearInterval = original.clearInterval
Date.now = original.dateNow
}
return { advanceBy, restore }
}
describe("todo-continuation-enforcer", () => {
let promptCalls: Array<{ sessionID: string; agent?: string; model?: { providerID?: string; modelID?: string }; text: string }>
let toastCalls: Array<{ title: string; message: string }>
let fakeTimers: FakeTimers
interface MockMessage {
info: {
@@ -60,6 +174,7 @@ describe("todo-continuation-enforcer", () => {
}
beforeEach(() => {
fakeTimers = createFakeTimers()
_resetForTesting()
promptCalls = []
toastCalls = []
@@ -67,6 +182,7 @@ describe("todo-continuation-enforcer", () => {
})
afterEach(() => {
fakeTimers.restore()
_resetForTesting()
})
@@ -85,12 +201,12 @@ describe("todo-continuation-enforcer", () => {
})
// #then - countdown toast shown
await new Promise(r => setTimeout(r, 100))
await fakeTimers.advanceBy(100)
expect(toastCalls.length).toBeGreaterThanOrEqual(1)
expect(toastCalls[0].title).toBe("Todo Continuation")
// #then - after countdown, continuation injected
await new Promise(r => setTimeout(r, 2500))
await fakeTimers.advanceBy(2500)
expect(promptCalls.length).toBe(1)
expect(promptCalls[0].text).toContain("TODO CONTINUATION")
})
@@ -112,7 +228,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation injected
expect(promptCalls).toHaveLength(0)
@@ -132,7 +248,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation injected
expect(promptCalls).toHaveLength(0)
@@ -150,7 +266,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID: otherSession } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation injected
expect(promptCalls).toHaveLength(0)
@@ -170,7 +286,7 @@ describe("todo-continuation-enforcer", () => {
})
// #then - continuation injected for background task session
await new Promise(r => setTimeout(r, 2500))
await fakeTimers.advanceBy(2500)
expect(promptCalls.length).toBe(1)
expect(promptCalls[0].sessionID).toBe(bgTaskSession)
})
@@ -190,7 +306,7 @@ describe("todo-continuation-enforcer", () => {
})
// #when - wait past grace period (500ms), then user sends message
await new Promise(r => setTimeout(r, 600))
await fakeTimers.advanceBy(600, true)
await hook.handler({
event: {
type: "message.updated",
@@ -199,7 +315,7 @@ describe("todo-continuation-enforcer", () => {
})
// #then - wait past countdown time and verify no injection (countdown was cancelled)
await new Promise(r => setTimeout(r, 2500))
await fakeTimers.advanceBy(2500)
expect(promptCalls).toHaveLength(0)
})
@@ -223,9 +339,9 @@ describe("todo-continuation-enforcer", () => {
},
})
// #then - countdown should continue (message was ignored)
// #then - countdown should continue (message was ignored)
// wait past 2s countdown and verify injection happens
await new Promise(r => setTimeout(r, 2500))
await fakeTimers.advanceBy(2500)
expect(promptCalls).toHaveLength(1)
})
@@ -242,7 +358,7 @@ describe("todo-continuation-enforcer", () => {
})
// #when - assistant starts responding
await new Promise(r => setTimeout(r, 500))
await fakeTimers.advanceBy(500)
await hook.handler({
event: {
type: "message.part.updated",
@@ -250,7 +366,7 @@ describe("todo-continuation-enforcer", () => {
},
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation injected (cancelled)
expect(promptCalls).toHaveLength(0)
@@ -269,12 +385,12 @@ describe("todo-continuation-enforcer", () => {
})
// #when - tool starts executing
await new Promise(r => setTimeout(r, 500))
await fakeTimers.advanceBy(500)
await hook.handler({
event: { type: "tool.execute.before", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation injected (cancelled)
expect(promptCalls).toHaveLength(0)
@@ -295,7 +411,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation injected
expect(promptCalls).toHaveLength(0)
@@ -317,7 +433,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - continuation injected
expect(promptCalls.length).toBe(1)
@@ -336,12 +452,12 @@ describe("todo-continuation-enforcer", () => {
})
// #when - session is deleted during countdown
await new Promise(r => setTimeout(r, 500))
await fakeTimers.advanceBy(500)
await hook.handler({
event: { type: "session.deleted", properties: { info: { id: sessionID } } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation injected (cleaned up)
expect(promptCalls).toHaveLength(0)
@@ -362,7 +478,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 100))
await fakeTimers.advanceBy(100)
expect(toastCalls.length).toBeGreaterThanOrEqual(1)
})
@@ -379,7 +495,7 @@ describe("todo-continuation-enforcer", () => {
})
// #then - multiple toast updates during countdown (2s countdown = 2 toasts: "2s" and "1s")
await new Promise(r => setTimeout(r, 2500))
await fakeTimers.advanceBy(2500)
expect(toastCalls.length).toBeGreaterThanOrEqual(2)
expect(toastCalls[0].message).toContain("2s")
})
@@ -395,7 +511,7 @@ describe("todo-continuation-enforcer", () => {
await hook.handler({
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3500))
await fakeTimers.advanceBy(3500)
// #then - first injection happened
expect(promptCalls.length).toBe(1)
@@ -404,7 +520,7 @@ describe("todo-continuation-enforcer", () => {
await hook.handler({
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3500))
await fakeTimers.advanceBy(3500)
// #then - second injection also happened (no throttle blocking)
expect(promptCalls.length).toBe(2)
@@ -439,7 +555,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 2500))
await fakeTimers.advanceBy(2500)
// #then - continuation injected (non-abort errors don't block)
expect(promptCalls.length).toBe(1)
@@ -472,7 +588,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation (last message was aborted)
expect(promptCalls).toHaveLength(0)
@@ -490,12 +606,12 @@ describe("todo-continuation-enforcer", () => {
const hook = createTodoContinuationEnforcer(createMockPluginInput(), {})
// #when - session goes idle
// #when - session goes idle
await hook.handler({
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - continuation injected (no abort)
expect(promptCalls.length).toBe(1)
@@ -518,7 +634,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - continuation injected (last message is user, not aborted assistant)
expect(promptCalls.length).toBe(1)
@@ -541,7 +657,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation (abort error detected)
expect(promptCalls).toHaveLength(0)
@@ -566,12 +682,12 @@ describe("todo-continuation-enforcer", () => {
},
})
// #when - session goes idle immediately after
// #when - session goes idle immediately after
await hook.handler({
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation (abort detected via event)
expect(promptCalls).toHaveLength(0)
@@ -601,7 +717,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation (abort detected via event)
expect(promptCalls).toHaveLength(0)
@@ -627,13 +743,13 @@ describe("todo-continuation-enforcer", () => {
})
// #when - wait >3s then idle fires
await new Promise(r => setTimeout(r, 3100))
await fakeTimers.advanceBy(3100, true)
await hook.handler({
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - continuation injected (abort flag is stale)
expect(promptCalls.length).toBeGreaterThan(0)
@@ -659,7 +775,7 @@ describe("todo-continuation-enforcer", () => {
})
// #when - user sends new message (clears abort flag)
await new Promise(r => setTimeout(r, 600))
await fakeTimers.advanceBy(600)
await hook.handler({
event: {
type: "message.updated",
@@ -672,7 +788,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - continuation injected (abort flag was cleared by user activity)
expect(promptCalls.length).toBeGreaterThan(0)
@@ -710,7 +826,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - continuation injected (abort flag was cleared by assistant activity)
expect(promptCalls.length).toBeGreaterThan(0)
@@ -748,7 +864,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - continuation injected (abort flag was cleared by tool execution)
expect(promptCalls.length).toBeGreaterThan(0)
@@ -778,7 +894,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation (event-based detection wins over API)
expect(promptCalls).toHaveLength(0)
@@ -800,7 +916,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation (API fallback detected the abort)
expect(promptCalls).toHaveLength(0)
@@ -820,7 +936,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 2500))
await fakeTimers.advanceBy(2500)
// #then - prompt call made, model is undefined when no context (expected behavior)
expect(promptCalls.length).toBe(1)
@@ -867,7 +983,7 @@ describe("todo-continuation-enforcer", () => {
// #when - session goes idle
await hook.handler({ event: { type: "session.idle", properties: { sessionID } } })
await new Promise(r => setTimeout(r, 2500))
await fakeTimers.advanceBy(2500)
// #then - model should be extracted from assistant message's flat modelID/providerID
expect(promptCalls.length).toBe(1)
@@ -919,7 +1035,7 @@ describe("todo-continuation-enforcer", () => {
// #when - session goes idle
await hook.handler({ event: { type: "session.idle", properties: { sessionID } } })
await new Promise(r => setTimeout(r, 2500))
await fakeTimers.advanceBy(2500)
// #then - continuation uses Sisyphus (skipped compaction agent)
expect(promptCalls.length).toBe(1)
@@ -964,7 +1080,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation (compaction is in default skipAgents)
expect(promptCalls).toHaveLength(0)
@@ -1010,7 +1126,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - no continuation (prometheus found after filtering compaction, prometheus is in skipAgents)
expect(promptCalls).toHaveLength(0)
@@ -1057,7 +1173,7 @@ describe("todo-continuation-enforcer", () => {
event: { type: "session.idle", properties: { sessionID } },
})
await new Promise(r => setTimeout(r, 3000))
await fakeTimers.advanceBy(3000)
// #then - continuation injected (no agents to skip)
expect(promptCalls.length).toBe(1)

View File

@@ -205,7 +205,11 @@ export function createTodoContinuationEnforcer(
const prevMessage = messageDir ? findNearestMessageWithFields(messageDir) : null
agentName = agentName ?? prevMessage?.agent
model = model ?? (prevMessage?.model?.providerID && prevMessage?.model?.modelID
? { providerID: prevMessage.model.providerID, modelID: prevMessage.model.modelID }
? {
providerID: prevMessage.model.providerID,
modelID: prevMessage.model.modelID,
...(prevMessage.model.variant ? { variant: prevMessage.model.variant } : {})
}
: undefined)
tools = tools ?? prevMessage?.tools
}

View File

@@ -118,7 +118,7 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
if (externalNotifier.detected && !forceEnable) {
// External notification plugin detected - skip our notification to avoid conflicts
console.warn(getNotificationConflictWarning(externalNotifier.pluginName!));
log(getNotificationConflictWarning(externalNotifier.pluginName!));
log("session-notification disabled due to external notifier conflict", {
detected: externalNotifier.pluginName,
allPlugins: externalNotifier.allPlugins,
@@ -144,10 +144,6 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
isOpenCodeVersionAtLeast(OPENCODE_NATIVE_AGENTS_INJECTION_VERSION);
if (hasNativeSupport) {
console.warn(
`[oh-my-opencode] directory-agents-injector hook auto-disabled: ` +
`OpenCode ${currentVersion} has native AGENTS.md support (>= ${OPENCODE_NATIVE_AGENTS_INJECTION_VERSION})`
);
log("directory-agents-injector auto-disabled due to native OpenCode support", {
currentVersion,
nativeVersion: OPENCODE_NATIVE_AGENTS_INJECTION_VERSION,
@@ -268,6 +264,11 @@ const OhMyOpenCodePlugin: Plugin = async (ctx) => {
});
log("[index] onSubagentSessionCreated callback completed");
},
onShutdown: () => {
tmuxSessionManager.cleanup().catch((error) => {
log("[index] tmux cleanup error during shutdown:", error)
})
},
});
const atlasHook = isHookEnabled("atlas")

View File

@@ -1,56 +1,56 @@
import { describe, test, expect, mock, beforeEach } from "bun:test"
import { describe, test, expect, spyOn, beforeEach, afterEach } from "bun:test"
import { resolveCategoryConfig, createConfigHandler } from "./config-handler"
import type { CategoryConfig } from "../config/schema"
import type { OhMyOpenCodeConfig } from "../config"
mock.module("../agents", () => ({
createBuiltinAgents: async () => ({
import * as agents from "../agents"
import * as sisyphusJunior from "../agents/sisyphus-junior"
import * as commandLoader from "../features/claude-code-command-loader"
import * as builtinCommands from "../features/builtin-commands"
import * as skillLoader from "../features/opencode-skill-loader"
import * as agentLoader from "../features/claude-code-agent-loader"
import * as mcpLoader from "../features/claude-code-mcp-loader"
import * as pluginLoader from "../features/claude-code-plugin-loader"
import * as mcpModule from "../mcp"
import * as shared from "../shared"
import * as configDir from "../shared/opencode-config-dir"
import * as permissionCompat from "../shared/permission-compat"
import * as modelResolver from "../shared/model-resolver"
beforeEach(() => {
spyOn(agents, "createBuiltinAgents" as any).mockResolvedValue({
sisyphus: { name: "sisyphus", prompt: "test", mode: "primary" },
oracle: { name: "oracle", prompt: "test", mode: "subagent" },
}),
}))
})
mock.module("../agents/sisyphus-junior", () => ({
createSisyphusJuniorAgentWithOverrides: () => ({
spyOn(sisyphusJunior, "createSisyphusJuniorAgentWithOverrides" as any).mockReturnValue({
name: "sisyphus-junior",
prompt: "test",
mode: "subagent",
}),
}))
})
mock.module("../features/claude-code-command-loader", () => ({
loadUserCommands: async () => ({}),
loadProjectCommands: async () => ({}),
loadOpencodeGlobalCommands: async () => ({}),
loadOpencodeProjectCommands: async () => ({}),
}))
spyOn(commandLoader, "loadUserCommands" as any).mockResolvedValue({})
spyOn(commandLoader, "loadProjectCommands" as any).mockResolvedValue({})
spyOn(commandLoader, "loadOpencodeGlobalCommands" as any).mockResolvedValue({})
spyOn(commandLoader, "loadOpencodeProjectCommands" as any).mockResolvedValue({})
mock.module("../features/builtin-commands", () => ({
loadBuiltinCommands: () => ({}),
}))
spyOn(builtinCommands, "loadBuiltinCommands" as any).mockReturnValue({})
mock.module("../features/opencode-skill-loader", () => ({
loadUserSkills: async () => ({}),
loadProjectSkills: async () => ({}),
loadOpencodeGlobalSkills: async () => ({}),
loadOpencodeProjectSkills: async () => ({}),
discoverUserClaudeSkills: async () => [],
discoverProjectClaudeSkills: async () => [],
discoverOpencodeGlobalSkills: async () => [],
discoverOpencodeProjectSkills: async () => [],
}))
spyOn(skillLoader, "loadUserSkills" as any).mockResolvedValue({})
spyOn(skillLoader, "loadProjectSkills" as any).mockResolvedValue({})
spyOn(skillLoader, "loadOpencodeGlobalSkills" as any).mockResolvedValue({})
spyOn(skillLoader, "loadOpencodeProjectSkills" as any).mockResolvedValue({})
spyOn(skillLoader, "discoverUserClaudeSkills" as any).mockResolvedValue([])
spyOn(skillLoader, "discoverProjectClaudeSkills" as any).mockResolvedValue([])
spyOn(skillLoader, "discoverOpencodeGlobalSkills" as any).mockResolvedValue([])
spyOn(skillLoader, "discoverOpencodeProjectSkills" as any).mockResolvedValue([])
mock.module("../features/claude-code-agent-loader", () => ({
loadUserAgents: () => ({}),
loadProjectAgents: () => ({}),
}))
spyOn(agentLoader, "loadUserAgents" as any).mockReturnValue({})
spyOn(agentLoader, "loadProjectAgents" as any).mockReturnValue({})
mock.module("../features/claude-code-mcp-loader", () => ({
loadMcpConfigs: async () => ({ servers: {} }),
}))
spyOn(mcpLoader, "loadMcpConfigs" as any).mockResolvedValue({ servers: {} })
mock.module("../features/claude-code-plugin-loader", () => ({
loadAllPluginComponents: async () => ({
spyOn(pluginLoader, "loadAllPluginComponents" as any).mockResolvedValue({
commands: {},
skills: {},
agents: {},
@@ -58,60 +58,52 @@ mock.module("../features/claude-code-plugin-loader", () => ({
hooksConfigs: [],
plugins: [],
errors: [],
}),
}))
})
mock.module("../mcp", () => ({
createBuiltinMcps: () => ({}),
}))
spyOn(mcpModule, "createBuiltinMcps" as any).mockReturnValue({})
mock.module("../shared", () => ({
log: () => {},
fetchAvailableModels: async () => new Set(["anthropic/claude-opus-4-5"]),
readConnectedProvidersCache: () => null,
}))
spyOn(shared, "log" as any).mockImplementation(() => {})
spyOn(shared, "fetchAvailableModels" as any).mockResolvedValue(new Set(["anthropic/claude-opus-4-5"]))
spyOn(shared, "readConnectedProvidersCache" as any).mockReturnValue(null)
mock.module("../shared/opencode-config-dir", () => ({
getOpenCodeConfigPaths: () => ({
spyOn(configDir, "getOpenCodeConfigPaths" as any).mockReturnValue({
global: "/tmp/.config/opencode",
project: "/tmp/.opencode",
}),
}))
})
mock.module("../shared/permission-compat", () => ({
migrateAgentConfig: (config: Record<string, unknown>) => config,
}))
spyOn(permissionCompat, "migrateAgentConfig" as any).mockImplementation((config: Record<string, unknown>) => config)
mock.module("../shared/migration", () => ({
AGENT_NAME_MAP: {},
}))
spyOn(modelResolver, "resolveModelWithFallback" as any).mockReturnValue({ model: "anthropic/claude-opus-4-5" })
})
mock.module("../shared/model-resolver", () => ({
resolveModelWithFallback: () => ({ model: "anthropic/claude-opus-4-5" }),
}))
mock.module("../shared/model-requirements", () => ({
AGENT_MODEL_REQUIREMENTS: {
sisyphus: { fallbackChain: [{ providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5" }] },
oracle: { fallbackChain: [{ providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" }] },
librarian: { fallbackChain: [{ providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" }] },
explore: { fallbackChain: [{ providers: ["anthropic", "opencode"], model: "claude-haiku-4-5" }] },
"multimodal-looker": { fallbackChain: [{ providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" }] },
prometheus: { fallbackChain: [{ providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5" }] },
metis: { fallbackChain: [{ providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5" }] },
momus: { fallbackChain: [{ providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2" }] },
atlas: { fallbackChain: [{ providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" }] },
},
CATEGORY_MODEL_REQUIREMENTS: {
"visual-engineering": { fallbackChain: [{ providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" }] },
ultrabrain: { fallbackChain: [{ providers: ["openai", "github-copilot", "opencode"], model: "gpt-5.2-codex" }] },
artistry: { fallbackChain: [{ providers: ["google", "github-copilot", "opencode"], model: "gemini-3-pro" }] },
quick: { fallbackChain: [{ providers: ["anthropic", "github-copilot", "opencode"], model: "claude-haiku-4-5" }] },
"unspecified-low": { fallbackChain: [{ providers: ["anthropic", "github-copilot", "opencode"], model: "claude-sonnet-4-5" }] },
"unspecified-high": { fallbackChain: [{ providers: ["anthropic", "github-copilot", "opencode"], model: "claude-opus-4-5" }] },
writing: { fallbackChain: [{ providers: ["google", "github-copilot", "opencode"], model: "gemini-3-flash" }] },
},
}))
afterEach(() => {
(agents.createBuiltinAgents as any)?.mockRestore?.()
;(sisyphusJunior.createSisyphusJuniorAgentWithOverrides as any)?.mockRestore?.()
;(commandLoader.loadUserCommands as any)?.mockRestore?.()
;(commandLoader.loadProjectCommands as any)?.mockRestore?.()
;(commandLoader.loadOpencodeGlobalCommands as any)?.mockRestore?.()
;(commandLoader.loadOpencodeProjectCommands as any)?.mockRestore?.()
;(builtinCommands.loadBuiltinCommands as any)?.mockRestore?.()
;(skillLoader.loadUserSkills as any)?.mockRestore?.()
;(skillLoader.loadProjectSkills as any)?.mockRestore?.()
;(skillLoader.loadOpencodeGlobalSkills as any)?.mockRestore?.()
;(skillLoader.loadOpencodeProjectSkills as any)?.mockRestore?.()
;(skillLoader.discoverUserClaudeSkills as any)?.mockRestore?.()
;(skillLoader.discoverProjectClaudeSkills as any)?.mockRestore?.()
;(skillLoader.discoverOpencodeGlobalSkills as any)?.mockRestore?.()
;(skillLoader.discoverOpencodeProjectSkills as any)?.mockRestore?.()
;(agentLoader.loadUserAgents as any)?.mockRestore?.()
;(agentLoader.loadProjectAgents as any)?.mockRestore?.()
;(mcpLoader.loadMcpConfigs as any)?.mockRestore?.()
;(pluginLoader.loadAllPluginComponents as any)?.mockRestore?.()
;(mcpModule.createBuiltinMcps as any)?.mockRestore?.()
;(shared.log as any)?.mockRestore?.()
;(shared.fetchAvailableModels as any)?.mockRestore?.()
;(shared.readConnectedProvidersCache as any)?.mockRestore?.()
;(configDir.getOpenCodeConfigPaths as any)?.mockRestore?.()
;(permissionCompat.migrateAgentConfig as any)?.mockRestore?.()
;(modelResolver.resolveModelWithFallback as any)?.mockRestore?.()
})
describe("Plan agent demote behavior", () => {
test("plan agent should be demoted to subagent mode when replacePlan is true", async () => {
@@ -280,3 +272,170 @@ describe("Prometheus category config resolution", () => {
expect(config?.tools).toEqual({ tool1: true, tool2: false })
})
})
describe("Prometheus direct override priority over category", () => {
test("direct reasoningEffort takes priority over category reasoningEffort", async () => {
// #given - category has reasoningEffort=xhigh, direct override says "low"
const pluginConfig: OhMyOpenCodeConfig = {
sisyphus_agent: {
planner_enabled: true,
},
categories: {
"test-planning": {
model: "openai/gpt-5.2",
reasoningEffort: "xhigh",
},
},
agents: {
prometheus: {
category: "test-planning",
reasoningEffort: "low",
},
},
}
const config: Record<string, unknown> = {
model: "anthropic/claude-opus-4-5",
agent: {},
}
const handler = createConfigHandler({
ctx: { directory: "/tmp" },
pluginConfig,
modelCacheState: {
anthropicContext1MEnabled: false,
modelContextLimitsCache: new Map(),
},
})
// #when
await handler(config)
// #then - direct override's reasoningEffort wins
const agents = config.agent as Record<string, { reasoningEffort?: string }>
expect(agents.prometheus).toBeDefined()
expect(agents.prometheus.reasoningEffort).toBe("low")
})
test("category reasoningEffort applied when no direct override", async () => {
// #given - category has reasoningEffort but no direct override
const pluginConfig: OhMyOpenCodeConfig = {
sisyphus_agent: {
planner_enabled: true,
},
categories: {
"reasoning-cat": {
model: "openai/gpt-5.2",
reasoningEffort: "high",
},
},
agents: {
prometheus: {
category: "reasoning-cat",
},
},
}
const config: Record<string, unknown> = {
model: "anthropic/claude-opus-4-5",
agent: {},
}
const handler = createConfigHandler({
ctx: { directory: "/tmp" },
pluginConfig,
modelCacheState: {
anthropicContext1MEnabled: false,
modelContextLimitsCache: new Map(),
},
})
// #when
await handler(config)
// #then - category's reasoningEffort is applied
const agents = config.agent as Record<string, { reasoningEffort?: string }>
expect(agents.prometheus).toBeDefined()
expect(agents.prometheus.reasoningEffort).toBe("high")
})
test("direct temperature takes priority over category temperature", async () => {
// #given
const pluginConfig: OhMyOpenCodeConfig = {
sisyphus_agent: {
planner_enabled: true,
},
categories: {
"temp-cat": {
model: "openai/gpt-5.2",
temperature: 0.8,
},
},
agents: {
prometheus: {
category: "temp-cat",
temperature: 0.1,
},
},
}
const config: Record<string, unknown> = {
model: "anthropic/claude-opus-4-5",
agent: {},
}
const handler = createConfigHandler({
ctx: { directory: "/tmp" },
pluginConfig,
modelCacheState: {
anthropicContext1MEnabled: false,
modelContextLimitsCache: new Map(),
},
})
// #when
await handler(config)
// #then - direct temperature wins over category
const agents = config.agent as Record<string, { temperature?: number }>
expect(agents.prometheus).toBeDefined()
expect(agents.prometheus.temperature).toBe(0.1)
})
})
describe("Deadlock prevention - fetchAvailableModels must not receive client", () => {
test("fetchAvailableModels should be called with undefined client to prevent deadlock during plugin init", async () => {
// #given - This test ensures we don't regress on issue #1301
// Passing client to fetchAvailableModels during config handler causes deadlock:
// - Plugin init waits for server response (client.provider.list())
// - Server waits for plugin init to complete before handling requests
const fetchSpy = spyOn(shared, "fetchAvailableModels" as any).mockResolvedValue(new Set<string>())
const pluginConfig: OhMyOpenCodeConfig = {
sisyphus_agent: {
planner_enabled: true,
},
}
const config: Record<string, unknown> = {
model: "anthropic/claude-opus-4-5",
agent: {},
}
const mockClient = {
provider: { list: () => Promise.resolve({ data: { connected: [] } }) },
model: { list: () => Promise.resolve({ data: [] }) },
}
const handler = createConfigHandler({
ctx: { directory: "/tmp", client: mockClient },
pluginConfig,
modelCacheState: {
anthropicContext1MEnabled: false,
modelContextLimitsCache: new Map(),
},
})
// #when
await handler(config)
// #then - fetchAvailableModels must be called with undefined as first argument (no client)
// This prevents the deadlock described in issue #1301
expect(fetchSpy).toHaveBeenCalled()
const firstCallArgs = fetchSpy.mock.calls[0]
expect(firstCallArgs[0]).toBeUndefined()
fetchSpy.mockRestore?.()
})
})

View File

@@ -133,16 +133,20 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
];
const browserProvider = pluginConfig.browser_automation_engine?.provider ?? "playwright";
// config.model represents the currently active model in OpenCode (including UI selection)
// Pass it as uiSelectedModel so it takes highest priority in model resolution
const currentModel = config.model as string | undefined;
const builtinAgents = await createBuiltinAgents(
migratedDisabledAgents,
pluginConfig.agents,
ctx.directory,
config.model as string | undefined,
undefined, // systemDefaultModel - let fallback chain handle this
pluginConfig.categories,
pluginConfig.git_master,
allDiscoveredSkills,
ctx.client,
browserProvider
browserProvider,
currentModel // uiSelectedModel - takes highest priority
);
// Claude Code agents: Do NOT apply permission migration
@@ -223,9 +227,18 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
);
const prometheusOverride =
pluginConfig.agents?.["prometheus"] as
| (Record<string, unknown> & { category?: string; model?: string; variant?: string })
| (Record<string, unknown> & {
category?: string
model?: string
variant?: string
reasoningEffort?: string
textVerbosity?: string
thinking?: { type: string; budgetTokens?: number }
temperature?: number
top_p?: number
maxTokens?: number
})
| undefined;
const defaultModel = config.model as string | undefined;
const categoryConfig = prometheusOverride?.category
? resolveCategoryConfig(
@@ -236,20 +249,33 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
const prometheusRequirement = AGENT_MODEL_REQUIREMENTS["prometheus"];
const connectedProviders = readConnectedProvidersCache();
const availableModels = ctx.client
? await fetchAvailableModels(ctx.client, { connectedProviders: connectedProviders ?? undefined })
: new Set<string>();
// IMPORTANT: Do NOT pass ctx.client to fetchAvailableModels during plugin initialization.
// Calling client API (e.g., client.provider.list()) from config handler causes deadlock:
// - Plugin init waits for server response
// - Server waits for plugin init to complete before handling requests
// Use cache-only mode instead. If cache is unavailable, fallback chain uses first model.
// See: https://github.com/code-yeongyu/oh-my-opencode/issues/1301
const availableModels = await fetchAvailableModels(undefined, {
connectedProviders: connectedProviders ?? undefined,
});
const modelResolution = resolveModelWithFallback({
uiSelectedModel: currentModel,
userModel: prometheusOverride?.model ?? categoryConfig?.model,
fallbackChain: prometheusRequirement?.fallbackChain,
availableModels,
systemDefaultModel: defaultModel ?? "",
systemDefaultModel: undefined,
});
const resolvedModel = modelResolution?.model;
const resolvedVariant = modelResolution?.variant;
const variantToUse = prometheusOverride?.variant ?? resolvedVariant;
const reasoningEffortToUse = prometheusOverride?.reasoningEffort ?? categoryConfig?.reasoningEffort;
const textVerbosityToUse = prometheusOverride?.textVerbosity ?? categoryConfig?.textVerbosity;
const thinkingToUse = prometheusOverride?.thinking ?? categoryConfig?.thinking;
const temperatureToUse = prometheusOverride?.temperature ?? categoryConfig?.temperature;
const topPToUse = prometheusOverride?.top_p ?? categoryConfig?.top_p;
const maxTokensToUse = prometheusOverride?.maxTokens ?? categoryConfig?.maxTokens;
const prometheusBase = {
name: "prometheus",
...(resolvedModel ? { model: resolvedModel } : {}),
@@ -259,22 +285,16 @@ export function createConfigHandler(deps: ConfigHandlerDeps) {
permission: PROMETHEUS_PERMISSION,
description: `${configAgent?.plan?.description ?? "Plan agent"} (Prometheus - OhMyOpenCode)`,
color: (configAgent?.plan?.color as string) ?? "#FF6347",
...(categoryConfig?.temperature !== undefined
? { temperature: categoryConfig.temperature }
: {}),
...(categoryConfig?.top_p !== undefined
? { top_p: categoryConfig.top_p }
: {}),
...(categoryConfig?.maxTokens !== undefined
? { maxTokens: categoryConfig.maxTokens }
: {}),
...(temperatureToUse !== undefined ? { temperature: temperatureToUse } : {}),
...(topPToUse !== undefined ? { top_p: topPToUse } : {}),
...(maxTokensToUse !== undefined ? { maxTokens: maxTokensToUse } : {}),
...(categoryConfig?.tools ? { tools: categoryConfig.tools } : {}),
...(categoryConfig?.thinking ? { thinking: categoryConfig.thinking } : {}),
...(categoryConfig?.reasoningEffort !== undefined
? { reasoningEffort: categoryConfig.reasoningEffort }
...(thinkingToUse ? { thinking: thinkingToUse } : {}),
...(reasoningEffortToUse !== undefined
? { reasoningEffort: reasoningEffortToUse }
: {}),
...(categoryConfig?.textVerbosity !== undefined
? { textVerbosity: categoryConfig.textVerbosity }
...(textVerbosityToUse !== undefined
? { textVerbosity: textVerbosityToUse }
: {}),
};

View File

@@ -46,7 +46,7 @@ describe("Agent Config Integration", () => {
const config = {
sisyphus: { model: "anthropic/claude-opus-4-5" },
oracle: { model: "openai/gpt-5.2" },
librarian: { model: "opencode/big-pickle" },
librarian: { model: "opencode/glm-4.7-free" },
}
// #when - migration is applied
@@ -65,7 +65,7 @@ describe("Agent Config Integration", () => {
Sisyphus: { model: "anthropic/claude-opus-4-5" },
oracle: { model: "openai/gpt-5.2" },
"Prometheus (Planner)": { model: "anthropic/claude-opus-4-5" },
librarian: { model: "opencode/big-pickle" },
librarian: { model: "opencode/glm-4.7-free" },
}
// #when - migration is applied

Some files were not shown because too many files have changed in this diff Show More