Commit Graph

1825 Commits

Author SHA1 Message Date
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
justsisyphus 903e8e75d2 refactor(models): update agent/category fallback chains
- quick: replace openai fallback with opencode/grok-code
- writing: add zai-coding-plan/glm-4.7 between sonnet and gpt
- unspecified-low: gpt-5.2 → gpt-5.2-codex (medium)
- Sisyphus: add zai/glm-4.7 before openai, use gpt-5.2-codex (medium)
- Momus & Metis: add variant 'max' to gemini-3-pro
- explore: simplify to haiku (anthropic/opencode) → grok-code (opencode)
2026-01-23 15:07:58 +09:00
justsisyphus a572ca5332 fix(agents): use resolved variant from fallback chain instead of requirement default
resolveModelWithFallback() returns entry-specific variant but it was being
ignored. Agents like oracle now correctly get variant 'high' from their
fallback chain entry instead of undefined.
2026-01-23 14:44:02 +09:00
justsisyphus 6ddf5735e7 refactor(atlas): rewrite prompt with lean orchestrator structure
- Reduce prompt from ~1280 to ~280 lines (78% reduction)
- Apply prompt engineering principles: remove model-already-knows content
- Use clean XML sections: identity, mission, delegation_system, workflow, etc.
- Adopt 6-section delegation format (TASK, EXPECTED OUTCOME, REQUIRED TOOLS, MUST DO, MUST NOT DO, CONTEXT)
- Preserve: identity, category+skills system, notepad protocol, parallelization, project-level QA
- Consolidate critical overrides at end with strong framing
2026-01-23 14:37:52 +09:00
justsisyphus 3441453f66 fix(atlas): register tool.execute.before and pass backgroundManager
- Add atlasHook?.['tool.execute.before'] call in tool.execute.before handler
- Pass backgroundManager option to createAtlasHook for proper bg task checking
- Move atlasHook declaration after backgroundManager initialization
2026-01-23 14:25:59 +09:00
justsisyphus 8a8d3c4da6 feat: show warning toast when model cache is not available
- Added isModelCacheAvailable() to check if cache file exists
- Shows warning toast on session start if cache is missing
- Suggests running 'opencode models --refresh' or restarting
2026-01-23 14:20:38 +09:00
justsisyphus b876776858 fix: use cache file for model availability instead of SDK calls
- Changed fetchAvailableModels to read from ~/.cache/opencode/models.json
- Prevents plugin startup hanging caused by SDK client.config.providers() call
- Updated doctor model-resolution check to show available models from cache
- Added cache info display: provider count, model count, refresh command
2026-01-23 14:09:37 +09:00
justsisyphus 87c7e0e069 fix: model fallback properly falls through to system default
- Remove Step 3 in model-resolver that forced first fallbackChain entry
  even when unavailable, blocking system default fallback
- Add sisyphusJuniorModel option to delegate_task so agents["Sisyphus-Junior"]
  model override is respected in category-based delegation
- Update tests to reflect new fallback behavior
2026-01-23 10:56:31 +09:00
github-actions[bot] 7d02cc1152 @l3aro has signed the CLA in code-yeongyu/oh-my-opencode#999 2026-01-22 19:52:54 +00:00
l3aro 5b1e36acbf docs: rename Orchestrator-Sisyphus to Atlas 2026-01-23 02:40:13 +07:00
github-actions[bot] 9510efac3d release: v3.0.0-beta.13 2026-01-22 18:04:51 +00:00
justsisyphus fc38ec2599 fix(delegate-task): reset model cache between tests 2026-01-23 02:59:03 +09:00
justsisyphus b38133eaad refactor(atlas): improve delegation guidance in validation step 2026-01-23 02:59:03 +09:00
Kenny 098ae8093b Merge pull request #989 from boojongmin/dev
docs: add Korean (한국어) README
2026-01-22 12:49:36 -05:00
justsisyphus 44bc28e99a fix(test): update model-fallback snapshots for github-copilot model naming 2026-01-23 02:27:52 +09:00
justsisyphus 87142466f6 fix(model-resolver): return variant from fallback chain, handle model name normalization
- Add variant to ModelResolutionResult return type
- Return variant from matched fallback entry
- Add normalizeModelName() for Claude model hyphen/period differences
- Add transformModelForProvider() for github-copilot model names
- Update delegate-task to use resolved variant (user config takes priority)
- Fix test expectations for new fallback behavior
2026-01-23 02:20:32 +09:00
justsisyphus f067f8e6fc docs: regenerate all AGENTS.md files with updated structure 2026-01-23 02:14:08 +09:00
justsisyphus d2491e9309 refactor(keyword-detector): change keyword injection from synthetic to direct message transform
- Replace collector.register() with direct output.parts[textIndex].text modification
- All keyword types (ultrawork, search, analyze) now prepend to user message text
- Message format: keyword message + '---' separator + original text
- Update tests to verify text transformation instead of collector registration
- All 18 tests pass
2026-01-23 01:53:59 +09:00