- P1: When allowedEnvVars is provided, PATH was missing from the base
restricted env, causing non-builtin commands to fail at exec time
- P2: Allowlisted HOME/CLAUDE_PROJECT_DIR could overwrite normalized
values from getHomeDirectory()/cwd with ambient process.env values
- P2: Test suite mutated shared pluginHooksState singleton without
resetting it in afterEach, causing cross-test state leaks
Resolve built-in local MCP runtime executables before handing command arrays to OpenCode so lsp and ast_grep do not depend on a bare node or bun lookup in the host PATH.
Keep source, dist, bootstrap, workspace-safety, and disabled_mcps behavior covered by focused tests and real OpenCode MCP status QA.
Plan: plans/fix-built-in-mcp-runtime-executables.md
- Apply mcp_env_allowlist to plugin hooks: intersect HTTP allowedEnvVars
with MCP allowlist, set command allowedEnvVars to full MCP allowlist
- Scrub process.env in executeHookCommand when allowedEnvVars provided
- Add PluginHooksState class with per-directory Map storage
- Add PluginHooksConfig interface for typed boundary layer
- Pass directory context through hook-config-handler
- Add 16 tests across 4 files (40 assertions) covering allowlist
filtering, env scrubbing, directory isolation, and edge cases
- Remove unnecessary 'as' type assertions, use discriminated union
narrowing instead
Todo continuation could reinject with a lowercase built-in config key such as hephaestus when no registered alias was available. OpenCode prompt dispatch expects the prompt-facing agent name, so the continuation failed with an agent-not-found error.
Normalize the dispatch fallback through the existing prompt agent display-name resolver and pin the lowercase Hephaestus regression.
OpenAI streaming responses can surface mid-stream errors with type
'server_error' or with the prose message 'An error occurred while processing
your request'. Neither matched any entry in RETRYABLE_MESSAGE_PATTERNS, so
shouldRetryError returned false and the runtime-fallback / fallback-retry
code paths skipped retry. The result was that GPT-5.5 subagent (and main)
turns silently stalled until the stale timeout fired.
The maintainer's diagnosis on issue #3799 explicitly recommends adding
these two patterns to model-error-classifier.ts; this commit does exactly
that and adds two regression tests covering the JSON envelope and the
prose form.
Gate idle ready notifications on the existing background-task continuation marker so cmux does not receive premature ready alerts while delegated work is still active.
Constraint: Reuse marker state from background task lifecycle without adding new notification config
Rejected: Patch cmux directly | notification readiness belongs upstream in OMO
Confidence: high
Scope-risk: narrow
- CHANGELOG: detail BUG-A/B (team-mode delivery), BUG-C/D
(runtime-fallback event/finish blind spots), BUG-E (parent-wake
same-source reservation), BUG-F (markerless workspace rules); the
packages/rules-core and packages/ast-grep-mcp extractions; the
prompt-async-gate hold default change; the new symlink-escape security
fix; the rules-core isolation note; and the v4.3.0 deferred items
(prompt-async-gate.ts split, @ast-grep/napi stale dep cleanup).
- README.ru.md: add the OmO logo block so the Russian README matches
README.md / README.ja.md / README.ko.md / README.zh-cn.md.
YeonGyu-Kim