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>
* 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>
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#873Fixes#844
Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
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.
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)
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.
- 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
- 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
- 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
- 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
- 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
- Add sisyphus-orchestrator → atlas hook rename mapping
- Add null mappings for removed hooks (preemptive-compaction, empty-message-sanitizer)
- Update migrateHookNames() to filter out removed hooks and return removed list
- Log warning when obsolete hooks are removed from disabled_hooks
- Add tests for new migration scenarios
Apply case-insensitive utilities across agents, delegation, and tool
restrictions. Removes duplicate implementations from agents/utils.ts.
Agent validation now normalizes input to canonical names.
Add findCaseInsensitive, includesCaseInsensitive, findByNameCaseInsensitive,
and equalsIgnoreCase functions for consistent case-insensitive lookups across
the codebase. Enables 'Oracle', 'oracle', 'ORACLE' to work interchangeably.
- Update category tables to match DEFAULT_CATEGORIES in constants.ts
- Remove non-existent 'most-capable' and 'general' categories
- Add 'unspecified-low' and 'unspecified-high' categories
- Update model names to full paths (e.g., openai/gpt-5.2-codex)
- Add new CategoryConfig schema fields: description, variant, top_p, etc.
- Fix atlas.ts prompt examples with correct category names
Generate tool description dynamically from available categories and skills. Remove hardcoded DELEGATE_TASK_DESCRIPTION constant. Improve parameter handling with unified 'subagent_type' field replacing 'agent'.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
justsisyphus