Apply env filtering after customEnv merge to prevent filtered
variables (API keys, secrets) from being reintroduced through
custom environment configuration.
Bun's mock.module() leaks across test files in single-process runs,
causing 357 unrelated test failures. Removing these tests for now.
The code fix is correct and verified manually.
Previously, when websearch was configured with Tavily provider and the
TAVILY_API_KEY environment variable was not set, the entire plugin would
fail to load with no visible error to the user.
Changes:
1. createWebsearchConfig now returns undefined when Tavily key is missing
2. Added warning log: '[websearch] Tavily API key not found, skipping websearch MCP'
3. createBuiltinMcps now skips undefined configs instead of adding them
4. Added tests for both missing and present Tavily API key scenarios
Fixes#2996
The auto-download mechanism for ripgrep existed but was never called.
When 'rg' wasn't in PATH, the grep tool silently fell back to GNU grep,
which wastes ~10% token budget due to noisy results.
Changes:
1. Wired up resolveGrepCliWithAutoInstall() in the CLI resolution path
2. When 'rg' is not found in PATH, auto-downloads ripgrep v14.1.1
3. Caches the downloaded binary in OpenCode data directory
4. Falls back to GNU grep only if auto-download fails (with warning)
Fixes#3003
Previously, Claude Code's .mcp.json would silently override OpenCode user
config when MCP server names collided. This was unexpected behavior since
users expect their explicit OpenCode configuration to take precedence.
Changes:
1. Swapped merge order: Claude Code .mcp.json is now merged BEFORE user
config, so user config wins on collision
2. Added warning log when user config overrides a Claude Code MCP server:
'warning: MCP server X from user config overrides Claude Code .mcp.json'
3. Added comprehensive tests for collision scenarios
Fixes#2946
Previously, Prometheus always used params.currentModel (UI-selected model)
when no explicit configuration existed. This bypassed the intended fallback
chain (claude-opus-4-6 → gpt-5.4 → glm-5 → gemini-3.1-pro).
Now, the UI-selected model is only used if it matches one of the models
in Prometheus's fallback chain. Otherwise, the fallback chain resolution
takes over and finds an available model.
Fixes#2986
Adds a defensive tool-pair-validator hook that runs as the final step in
the messages transform pipeline. When compaction or context-window recovery
removes user messages containing tool_result blocks without removing the
preceding assistant message with tool_use blocks, this validator detects
the mismatch and either:
1. Injects missing tool_result parts into the next user message, or
2. Creates a synthetic user message with placeholder tool_results
This prevents Anthropic API errors like 'tool_use ids found without
tool_result blocks immediately after'.
Fixes#3014
When a skill has a namespaced name like 'superpowers/systematic-debugging',
users see the short name 'systematic-debugging' in the listing but can't
invoke it — the resolver only accepts exact full names.
Add short-name fallback: if exact match fails, try matching the basename
of namespaced skills. Only resolves when unambiguous (single match).
- Exact match still takes priority
- Ambiguous short names (multiple namespaces) fall through to error
- 4 new tests covering all cases
Fixes#2971
When .claude/commands exists as a file instead of a directory,
readdirSync throws ENOTDIR and crashes command discovery, stalling
OMO initialization. Add statSync().isDirectory() guard with a
warning log.
Fixes#3010
Reduce repeated session.idle work by reusing hook config loads across a short TTL and by retrying parent session lookup instead of permanently caching transient failures.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Static slash-command discovery runs before agent registration, so /start-work regressed to Sisyphus even though config-time wiring still needed Atlas-aware fallback. Split builtin command resolution so discovery stays Atlas-first while command config remains availability-aware.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Use the plugin session directory instead of process.cwd() when resolving project slash commands. This restores project and opencode-project slashcommand behavior when the runtime cwd differs from the actual session workspace.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Keep native /start-work resolvable on Sisyphus, but switch the work session back to Atlas when Atlas is registered. Stamp the outgoing agent with Atlas's actual list-display key so config→start-work execution resolves correctly and still falls back to Sisyphus when Atlas is unavailable.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
These agents should only be usable as primary session agents, not as
subagent targets via call_omo_agent/task(). Previously MODE was 'all'
which allowed them to be spawned as subagents, leading to confusing
behavior (e.g. Atlas delegating to Hephaestus as a subagent).
Subagent-callable agents remain: oracle, explore, librarian,
multimodal-looker, metis, momus, sisyphus-junior.
Note: Prometheus is not a BuiltinAgentName and is only invoked via
slash commands, so no change needed there.
/start-work should leave plan mode even when Atlas is unavailable. This prevents Prometheus from being persisted into boulder state and keeping resumed work sessions in md-only mode.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Deep category now uses gpt-5.4 as its default model across all providers
(openai, github-copilot, venice, opencode), matching Hephaestus's GPT 5.4
upgrade. The requiresModel constraint is removed since gpt-5.4 is widely
available. Adds openai/gpt-5.3-codex -> openai/gpt-5.4 config migration
for existing user configs. Deep category prompt optimized for GPT 5.4's
stronger native capabilities (leaner, less verbose).
Embed user-level skills into the plugin's built-in system so they ship
with the product rather than requiring per-user configuration.
- review-work: 5-agent parallel post-implementation review orchestrator
- ai-slop-remover: per-file AI-generated code smell detector and remover
- /remove-ai-slops: command that orchestrates parallel ai-slop-remover runs
YeonGyu-Kim