Commit Graph

1442 Commits

Author SHA1 Message Date
yimingll 4311e5b264 fix: auto-truncate question option labels exceeding 30 characters
When AI generates AskUserQuestion tool calls with option labels longer
than 30 characters, opencode validation rejects them with "too_big" error.

This fix adds a pre-tool-use hook that automatically truncates labels
to 30 characters (with "..." suffix) before the validation occurs.

Fixes the error:
"The question tool was called with invalid arguments: expected string
to have <=30 characters"

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-24 15:59:45 +09:00
Stephen Wang eef98e27f2 Fix MCP disabled flag not removing previously loaded servers (#985)
When a later-loaded MCP config (e.g., .claude/.mcp.json) marks a server
as disabled, it now properly removes that server from both the servers
object and loadedServers array.

Previously, disabled servers were only skipped during loading, which
meant they wouldn't override servers loaded from earlier configs. This
made it impossible to disable project-level MCPs using local overrides.

Now the disabled flag works as expected: local configs can disable
servers defined in project or user configs.
2026-01-24 15:55:59 +09:00
Rouven Hi! d7b11234c8 fix(slashcommand): include built-in commands (like start-work) in discovery (#1031)
This ensures that commands defined in src/features/builtin-commands/commands.ts
(like /start-work, /refactor, /init-deep) are visible to the slashcommand tool
and the agent. Previously, only markdown-based commands were discovered.
2026-01-24 15:55:31 +09:00
justsisyphus 3e58321175 fix(background-task): pass config to BackgroundManager for concurrency limits
The background_task config (providerConcurrency, modelConcurrency, etc.)
was not being passed to BackgroundManager, causing all models to use
the hardcoded default limit of 5 instead of user-configured values.
2026-01-24 15:50:44 +09:00
justsisyphus bbee08e157 fix(todo-continuation): filter compaction agent to prevent infinite loop
- Add 'compaction' to DEFAULT_SKIP_AGENTS
- Skip compaction agent messages when resolving agent info
- Skip injection when compaction occurred but no real agent resolved
- Replace cooldown-based approach with agent-based filtering
2026-01-24 15:50:44 +09:00
Sungho Park 816c22660d Add xhigh reasoningEffort to config schema (#965)
* test: cover xhigh reasoningEffort

* feat: add xhigh reasoningEffort option

* test: make reasoningEffort xhigh test model-agnostic
2026-01-24 15:48:15 +09:00
YeonGyu-Kim 4c3e19c1a3 fix(multimodal-looker): update fallback chain order (#1050)
New order:
1. google/gemini-3-flash
2. openai/gpt-5.2
3. zai-coding-plan/glm-4.6v
4. anthropic/claude-haiku-4-5
5. opencode/gpt-5-nano (FREE, ultimate fallback)

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-24 15:40:24 +09:00
YeonGyu-Kim 8af6774ae8 fix(models): update model names to match OpenCode Zen catalog (#1048)
* fix(models): update model names to match OpenCode Zen catalog

OpenCode Zen recently updated their official model catalog, deprecating
several preview and free model variants:

DEPRECATED → NEW (Official Zen Names):
- gemini-3-pro-preview → gemini-3-pro
- gemini-3-flash-preview → gemini-3-flash
- grok-code → gpt-5-nano (FREE tier maintained)
- glm-4.7-free → big-pickle (FREE tier maintained)
- glm-4.6v → glm-4.6

Changes:
- Updated 6 source files (model-requirements, delegate-task, think-mode, etc.)
- Updated 9 documentation files (installation, configurations, features, etc.)
- Updated 14 test files with new model references
- Regenerated snapshots to reflect catalog changes
- Removed duplicate think-mode entries for preview variants

Impact:
- FREE tier access preserved via gpt-5-nano and big-pickle
- All 55 model-related tests passing
- Zero breaking changes - pure string replacement
- Aligns codebase with official OpenCode Zen model catalog

Verified:
- Zero deprecated model names in codebase
- All model-related tests pass (55/55)
- Snapshots regenerated and validated

Affects: 30 files (6 source, 9 docs, 14 tests, 1 snapshot)

* fix(multimodal-looker): update fallback chain with glm-4.6v and gpt-5-nano

- Change glm-4.6 to glm-4.6v for zai-coding-plan provider
- Add opencode/gpt-5-nano as 4th fallback (FREE tier)
- Push gpt-5.2 to 5th position

Fallback chain now:
1. gemini-3-flash (google, github-copilot, opencode)
2. claude-haiku-4-5 (anthropic, github-copilot, opencode)
3. glm-4.6v (zai-coding-plan)
4. gpt-5-nano (opencode) - FREE
5. gpt-5.2 (openai, github-copilot, opencode)

* chore: update bun.lock

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-24 15:30:35 +09:00
justsisyphus 5d14e09279 feat(website): add layout with header, sidebar, footer and navigation
- Create Header component with logo, nav, theme toggle, language switcher
- Create Sidebar component with doc navigation from config
- Create Footer component
- Create MobileNav component with hamburger menu
- Create navigation config file (docsConfig)
- Integrate all layout components into [locale]/layout.tsx
- Add framer-motion for mobile nav animations
- All tests passing, build successful
2026-01-24 14:25:05 +09:00
justsisyphus f28c8a45dd feat(website): add next-intl i18n and dark mode support 2026-01-24 14:25:05 +09:00
justsisyphus b7d3417d2e fix(website): resolve @opennextjs/cloudflare and test configuration issues
- Successfully installed @opennextjs/cloudflare v1.15.1
- Fixed Vitest configuration to exclude e2e tests
- Renamed e2e test files from .spec.ts to .e2e.ts to avoid Bun test runner conflicts
- Updated eslint.config.mjs and playwright.config.ts
- All tests passing: Vitest (1/1), Playwright (6/6)
- Production bundle size: ~5MB < 10MiB limit
- Marked TODO 0 complete in plan
2026-01-24 14:25:05 +09:00
justsisyphus e68600a76b feat(website): initialize Next.js 15 project with @opennextjs/cloudflare 2026-01-24 14:25:05 +09:00
github-actions[bot] 691fffb2aa @AndersHsueh has signed the CLA in code-yeongyu/oh-my-opencode#1042 2026-01-24 04:41:56 +00:00
github-actions[bot] 64d4d9b8b9 @gongxh0901 has signed the CLA in code-yeongyu/oh-my-opencode#1037 2026-01-24 02:27:36 +00:00
github-actions[bot] 7f6a334aa3 @RouHim has signed the CLA in code-yeongyu/oh-my-opencode#1031 2026-01-23 19:32:14 +00:00
github-actions[bot] ed83f12753 release: v3.0.0-beta.16 2026-01-23 18:12:07 +00:00
justsisyphus 29d2f94979 fix(delegate-task): use lowercase sisyphus-junior agent name in API calls
Previous fix (7ed7bf5c) only updated Atlas → atlas, but missed Sisyphus-Junior.
OpenCode does case-sensitive agent lookup, causing crash when delegate_task
tried to spawn 'Sisyphus-Junior' (registered as 'sisyphus-junior').

- SISYPHUS_JUNIOR_AGENT constant: 'Sisyphus-Junior' → 'sisyphus-junior'
- agent-tool-restrictions key: 'Sisyphus-Junior' → 'sisyphus-junior'
- Updated related test mocks
2026-01-24 03:00:58 +09:00
github-actions[bot] d0497f0e86 release: v3.0.0-beta.15 2026-01-23 17:44:45 +00:00
justsisyphus 101c1a8965 fix(agents): use lowercase agent names in API calls
- atlas/index.ts: agent: 'Atlas' -> 'atlas'
- start-work/index.ts: updateSessionAgent(..., 'Atlas') -> 'atlas'
- builtin-commands/commands.ts: agent: 'Atlas' -> 'atlas'
- Updated tests to match lowercase convention
2026-01-24 02:39:12 +09:00
github-actions[bot] f18778555b release: v3.0.0-beta.14 2026-01-23 17:09:52 +00:00
justsisyphus f92d2ec57f refactor(agents): add prometheus agent and normalize agent key lookups
- Add 'prometheus' to BuiltinAgentNameSchema enum
- Update delegate_task parameter names in documentation (agent → subagent_type, background → run_in_background)
- Make agent name comparison case-insensitive in Atlas hook
- Implement case-insensitive agent config lookup in shared utilities
- Relax type signature for disabled agents parameter

🤖 Generated with assistance of OhMyOpenCode
2026-01-24 02:00:17 +09:00
justsisyphus 439d0e58c8 test: add integration tests for agent key normalization 2026-01-23 21:54:27 +09:00
justsisyphus 8e8fefa5da test: update CLI tests for lowercase agent keys 2026-01-23 21:47:21 +09:00
justsisyphus 691021cca0 refactor(model-requirements): use lowercase agent keys 2026-01-23 21:41:55 +09:00
justsisyphus 0762195a2d refactor(plugin): use lowercase agent keys throughout 2026-01-23 21:32:17 +09:00
justsisyphus 54c0ee372a refactor(agents): use lowercase config keys in utils 2026-01-23 21:27:26 +09:00
justsisyphus 2e6df9781d refactor(prometheus-hook): use lowercase config key 2026-01-23 20:49:17 +09:00
justsisyphus fdb227a816 refactor(schema): use lowercase agent config keys 2026-01-23 20:46:09 +09:00
justsisyphus 815a7b20ee refactor(migration): normalize agent keys to lowercase 2026-01-23 19:01:10 +09:00
justsisyphus 34035b9a04 feat(shared): add agent display names module 2026-01-23 18:50:03 +09:00
justsisyphus 9f6c777d79 feat(publish): add platform binary verification steps
- Add STEP 8.5: Wait for publish-platform workflow completion
- Add STEP 8.6: Verify all 7 platform binary packages on npm
- Update TODO list with platform verification tasks
- Add error handling for platform-specific failures
2026-01-23 17:35:24 +09:00
github-actions[bot] cb1ab7315c @veetase has signed the CLA in code-yeongyu/oh-my-opencode#985 2026-01-23 08:27:12 +00:00
justsisyphus ce83507c76 docs: add model configuration section to overview and quick start to configurations 2026-01-23 17:05:45 +09:00
justsisyphus 32bfd59b00 feat(agents): add aggressive resume instructions to Atlas prompt 2026-01-23 17:04:14 +09:00
justsisyphus 5c587540f3 docs: update multimodal-looker model name and fallback chain 2026-01-23 17:02:11 +09:00
justsisyphus 2f56fd13b0 fix(cli): update zai-coding-plan hints to include multimodal-looker 2026-01-23 17:00:22 +09:00
justsisyphus 90264103b0 feat(agents): add zai-coding-plan/glm-4.6v fallback for multimodal-looker 2026-01-23 16:58:33 +09:00
yimingll 32113c5ad0 fix(lsp): add data dir to LSP server detection paths (#992)
OpenCode downloads LSP servers (like clangd) to ~/.local/share/opencode/bin,
but isServerInstalled() only checked ~/.config/opencode/bin. This caused
LSP tools to report servers as 'not installed' even when OpenCode had
successfully downloaded them.

Add ~/.local/share/opencode/bin to the detection paths to match OpenCode's
actual behavior.

Co-authored-by: yimingll <yimingll@users.noreply.github.com>
2026-01-23 16:37:40 +09:00
justsisyphus 4b8eee109a Merge pull request #913 from carlory/fix-doctor
fix(doctor): handle file:// protocol for local dev plugin detection
2026-01-23 16:36:16 +09:00
justsisyphus a54150c7e6 Merge pull request #962 from popododo0720/fix/issues-898-919
fix(doctor): improve AST-Grep NAPI detection for bunx environments
2026-01-23 16:36:05 +09:00
justsisyphus 4cf61cfb01 fix(skill): enforce agent restriction in createSkillTool (#1018)
* fix(skill): enforce agent restriction in createSkillTool

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

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

* fix(skill): block restricted skills when agent context missing

Addresses cubic review feedback: previously agent-restricted skills
could be invoked when ctx or ctx.agent was undefined because the
guard only ran when ctx?.agent was truthy.

Changed condition from:
  skill.definition.agent && ctx?.agent && skill.definition.agent !== ctx.agent
To:
  skill.definition.agent && (!ctx?.agent || skill.definition.agent !== ctx.agent)

This ensures restricted skills are blocked unless the exact matching
agent is present in the context.

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-23 16:32:41 +09:00
justsisyphus e591f562f7 fix(ci): build Windows binary natively to fix segfault (#1019)
Bun cross-compilation from Linux to Windows produces binaries that crash
with 'Segmentation fault at address 0xFFFFFFFFFFFFFFFF'.

Root cause: oven-sh/bun#18416

Solution:
- Use windows-latest runner for Windows platform in publish-platform.yml
- Set shell: bash for consistent behavior across runners

This is a simpler fix than PR #938 which modified publish.yml (wrong workflow).
The platform binaries are built and published by publish-platform.yml.

Fixes #873
Fixes #844

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-23 16:30:47 +09:00
justsisyphus 9aa2084072 fix(session): preserve custom agent after switching (#1017)
Use setSessionAgent (first-write wins) instead of updateSessionAgent in chat.message handler. This prevents the default agent from overwriting a custom agent that was set via UI switch.

Fixes #893

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

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-23 16:25:26 +09:00
YeonGyu-Kim 84a17c003e fix(tools): conditionally register look_at when multimodal-looker enabled (#1016)
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-23 16:25:17 +09:00
YeonGyu-Kim 31248a5904 fix(hooks): use unix shell syntax for bash tool on all platforms (#1015)
The bash tool always runs in a Unix-like shell (bash/sh), even on Windows (via Git Bash, WSL, etc.), so we should always use unix export syntax instead of detecting the shell type dynamically.

Fixes #983

Fixes #889

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

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-23 16:24:58 +09:00
justsisyphus cc8d2ee4d2 docs(agents): update AGENTS.md with current commit hash and line counts 2026-01-23 16:00:38 +09:00
justsisyphus d5e1344b87 fix(atlas): capture stderr from git commands to prevent help text leak
When git commands fail (e.g., not in a repo, invalid HEAD), git outputs
help text to stderr. Without explicit stdio option, execSync inherits
the parent's stdio causing help text to appear on terminal during
delegate_task execution.

Add stdio: ['pipe', 'pipe', 'pipe'] to capture stderr instead of
letting it leak to terminal.
2026-01-23 15:42:35 +09:00
justsisyphus c985ef9c99 fix(model-resolver): use first fallback entry when model cache unavailable
When availableModels is empty (no cache in CI), use the first entry
from fallbackChain directly instead of falling back to systemDefault.
This ensures categories and agents use their configured models even
when the model cache file doesn't exist.

Fixes:
- model-resolution check returning 'warn' instead of 'pass' in CI
- DEFAULT_CATEGORIES not being used when no cache available
- Unstable agent detection failing (models falling back to non-gemini)
2026-01-23 15:39:07 +09:00
github-actions[bot] 61f55d2f9b @Ssoon-m has signed the CLA in code-yeongyu/oh-my-opencode#1014 2026-01-23 06:31:37 +00:00
Nguyen Khac Trung Kien 4f76f727bc Merge pull request #999 from l3aro/dev 2026-01-23 13:14:02 +07:00