Only clear recentAnyIdles when the stored marker matches the synthetic idle timestamp for the same session, preventing accidental clobbering of newer idle markers. Add a regression test to verify other sessions keep their dedup state during this bypass path.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
When the binary resolved as 'opencode' on PATH is the OpenCode Desktop GUI (not the CLI), it does not respond to --version with prompt exit. proc.exited then waits forever, freezing the installer at 'Checking OpenCode installation'.
Fix: race proc.exited against OPENCODE_VERSION_CHECK_TIMEOUT_MS=1500. On timeout, proc.kill() and treat the binary as failed so the next candidate is tried. Success requires both timedExitCode === 0 and proc.exitCode === 0.
Fixes#3766
- Add /exceeded.*quota/i and /usage\s*quota/i to classifyErrorType quota block
- Align /usage.?quota/i -> /usage\s*quota/i in RETRYABLE_ERROR_PATTERNS for consistency
- Strengthen auto-retry-signal test assertion
- Add classifyErrorType assertion to Volcano Engine regression test
Ensures Volcano Engine errors are both retryable AND logged as
errorType: quota_exceeded.
Volcano Engine sends quota exceeded errors with the words in reverse
order: 'You have exceeded the 5-hour usage quota'. The existing
patterns required 'quota' to precede 'exceeded', so they never matched.
- Add /exceeded.*quota/i and /usage.?quota/i to RETRYABLE_ERROR_PATTERNS
- Add exceeded.*quota and usage\s*quota to AUTO_RETRY_PATTERNS
- Add regression tests for both detection paths
Fixes: runtime-fallback not triggering on Volcano Engine quota errors
The deep and artistry category fallback chains had no opencode-go provider
entries, causing them to fall through to the ultimate fallback
(opencode/gpt-5-nano) which is not available to opencode-go users.
Add opencode-go entries:
- deep: deepseek-v4-pro -> kimi-k2.6 -> glm-5.1
- artistry: kimi-k2.6 -> glm-5.1
Fixes#3924
The same output.trim() bug fixed in PR #3909 for doctor exists in the
installer's opencode-binary.ts. Without this fix, `bunx oh-my-opencode
install` would store polluted Electron stdout (e.g., `00:24:25.202 >
app starting { version: '1.14.33', packaged: true }`) as the OpenCode
version in config, breaking downstream version-dependent logic.
- Extract extractSemverFromOutput to src/shared/extract-semver.ts
(precedent: spawn-with-windows-hide is in shared because used by
both doctor and installer)
- src/cli/doctor/checks/system-binary.ts now imports from shared and
re-exports for backward compat
- src/cli/config-manager/opencode-binary.ts uses the shared helper
with `?? output.trim()` fallback to preserve legacy behavior on
non-semver-shaped successful outputs (e.g., custom builds)
- Add 4 installer regression tests covering: clean semver, polluted
Electron stdout (regression for #3765 installer caller), fallback
for non-semver, null when no binary on PATH
Refs #3765
MessageAbortedError/worker shutdown could race with scheduled removeTask, leaving background_output's manager.getTask returning 'Task not found' even though the task had completed cleanly.
Fix: add completedTaskArchive (max 500, FIFO eviction). On removeTask, archive non-running/pending tasks with sessionId. getTask falls back to archive on active-map miss. addTask clears stale archive entries on re-registration.
Fixes#3895
When session.status(idle) is converted to synthetic session.idle and recorded in recentAnyIdles, a real session.idle arriving within 500ms was being dropped by the dedup logic. recentSyntheticIdles was cleared but recentAnyIdles persisted, causing TODO-DIAG to red-alert with 'no todossession.idle event'.
Fix: when real session.idle arrives, also clear recentAnyIdles entry so dedup does not drop it. Test renamed and expected dispatchCalls updated 1 → 2.
Fixes#2667
openSync with read-only mode fails fsync on Windows because FlushFileBuffers requires write-permission FD. This caused atomic writes to fail silently, leaving migrated config unwritten and triggering repeated migration + .bak.<timestamp> generation on every startup.
Same root cause as PR #3644 (#3643). Hyperplan disappear is a secondary symptom of plugin load instability.
Fixes#3877
The Electron-based OpenCode build leaks log lines like
`00:24:25.202 > app starting { version: '1.14.33', packaged: true }`
into stdout, so `getOpenCodeVersion` was returning the entire log
line as the 'version'. `compareVersions` then split that string on
'.' and produced a nonsensical numeric array (e.g., `[0, 0, 14, 0]`),
which it judged as < the minimum 1.4.0. Result: doctor incorrectly
flagged OpenCode 1.14.x as below the minimum required version.
Replace the raw `stdout.trim()` return with a small
`extractSemverFromOutput` helper that runs a semver-shaped regex
across the output. A negative lookbehind `(?<![\d:])` skips the
milliseconds segment of timestamps (e.g., `25.202` in
`00:24:25.202`), so the parser locks onto the real version token.
Adds 12 unit tests covering plain semver, v-prefix, pre-release,
build metadata, the Electron regression, timestamp-only stdout,
and various invalid inputs.
Fixes#3765
Keep ordinary delegated subagents from seeing team tools while preserving communication tools for real team-mode member sessions, including fallback retry sessions.
Atlas was delegating tasks one-by-one because the workflow framed parallel
as a conditional ("if tasks can run in parallel..."), letting models default
to the safer sequential path. The new shared ATLAS_PARALLEL_BY_DEFAULT block
flips the default: parallel is mandatory; sequential requires a NAMED
blocking dependency (input dependency or file conflict).
Adds two new prompt variants — kimi (K2.6 thinking-mode calibration:
commitment framing + concrete budgets) and opus-4-7 (counters 4.7's lower
default subagent count and literal-following bias). Recalibrates default
(Claude 4.6 family), gpt (GPT-5.5 outcome-first / decision rules over
absolutes), and gemini (preserves TOOL_CALL_MANDATE; replaces stale
session_id with task_id). All five variants share the parallel mandate
positioned BEFORE the workflow so "mandate above" references resolve.
Strengthens the orchestrator-direct-edit reminder hooks
(ORCHESTRATOR_DELEGATION_REQUIRED + DIRECT_WORK_REMINDER) with the central
challenge "Do you ACTUALLY need to be the one doing this?" — replacing the
previous bullet-heavy framing.
Tests now parametrized over all 5 variants. Adds prompt-routing.test
covering GPT/Gemini/Kimi/Opus 4.7/default routing and edge cases, plus a
session_id rejection test (every variant must use task_id for retries).
YeonGyu-Kim