When using `opencode run`, the process exits prematurely if the main
agent dispatches background subtasks. The CLI completion checker relies
on `session.children()` + `session.status()` APIs which cannot see
tasks in "pending" state (no session created yet) or tasks whose
sessions are momentarily idle between operations.
This fix bridges BackgroundManager state to the CLI completion checker
using the existing run-continuation-state marker system:
- Add "background-task" continuation marker source
- BackgroundManager writes/clears markers on task lifecycle events
(launch, cancel, complete, crash)
- CLI completion checker blocks exit when marker is active
- Fix todo-continuation-enforcer to also check "pending" task status
Closes#3452
- #3354: Coerce data.name to String in loadSkillFromPath/loadSkillFromPathAsync
to prevent crash when YAML parses numeric skill names (e.g., name: 12306)
- #3416: Add required run_in_background parameter to all task() examples in
ultrawork prompts (default, gpt, gemini, planner) to match tool schema
- #3379/#3417/#3418/#3337/#3335: Strip ZWSP (U+200B) before agent name
comparisons in agent-tool-restrictions, sync-prompt-sender, tool-execute-after,
tool-execute-before, oracle-verification-detector, call-omo-agent,
recovery-prompt-config, and agent-variant to prevent ZWSP-prefixed display
names from breaking exact-match lookups
- shell-env: detect Git Bash via MSYSTEM env var when SHELL is unset (#3366)
On some Git Bash installations SHELL is not set but MSYSTEM (MINGW64/MSYS)
is always present. Check MSYSTEM before PSModulePath to avoid emitting
PowerShell syntax in bash shells.
- session-state: resolve legacy agent names in resolveRegisteredAgentName (#3272)
Historical sessions stored agent names like 'Sisyphus (Ultraworker)' which
don't match the current registered format. Fall back to getAgentConfigKey
for legacy/parenthesized name resolution before returning the raw name.
- config-migration: skip backup when file content is unchanged (#3222)
Compare serialized config with existing file content before creating a
timestamped .bak file. Only create backup when the on-disk content
actually differs from the migrated content.
The update checker was using strict string comparison (===) to compare
current and latest versions. This caused false-positive update notifications
when versions were semantically equal but had different string representations
(e.g., with/without 'v' prefix, different formatting).
Changed to use compareVersions() which properly parses and compares
semver versions, handling 'v' prefixes and other variations correctly.
Fixes: incorrect 'v3.17.2 available' notifications when already on latest version
setSessionFallbackChain stored the fallback chain but the sync path
never consumed it when sendSyncPrompt returned an error. Added a
retry loop that iterates getNextFallback() until the prompt succeeds
or the chain is exhausted, preserving the finally-block cleanup.
🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
Hardcoded platform check forced PowerShell env syntax on Windows
regardless of the actual shell. Replaced with detectShellType() so
Git Bash, WSL, and similar environments use unix prefixes while
native PowerShell continues to get powershell prefixes.
🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
github-copilot routes Claude models but rejects the Anthropic effort
parameter. Added an explicit guard so effort is no longer injected
when the provider ID is github-copilot, while preserving native
Anthropic provider support.
🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
Atlas verification reminders instructed 'git diff --stat' which
included node_modules noise in the output. Added pathspec exclude
to both VERIFICATION_REMINDER and VERIFICATION_REMINDER_GEMINI
templates.
🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
- context-info-builder referenced a non-existent /plan command;
now directs users to the Prometheus agent for planning
- skill tool description example referenced 'code-review' which
does not exist; changed to 'review-work' (actual built-in skill)
- skill tool execute path now surfaces the missing host permission
gap so callers understand OpenCode plugin context limits
🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
Addresses cubic-dev-ai review feedback. The Haiku early-return now
runs immediately after model validation, ensuring it's always reached
regardless of any upstream variant normalization.
Haiku models do not support the effort parameter and return API errors
when it is passed. The hook now explicitly checks for Haiku model
patterns and skips effort injection, preventing silent title generation
failures.
Added EFFORT_UNSUPPORTED_PATTERN and isEffortUnsupportedModel() to
detect and skip Haiku models.
Fixes#3308
Update various modules to use centralized constants from plugin-identity:
- get-local-version/formatter: Use PUBLISHED_PACKAGE_NAME
- run/session-resolver: Use PUBLISHED_PACKAGE_NAME
- background-agent/task-poller: Use PUBLISHED_PACKAGE_NAME
- mcp-oauth/provider: Use PUBLISHED_PACKAGE_NAME
- auto-update-checker/constants: Use ACCEPTED_PACKAGE_NAMES
- comment-checker/downloader: Use PUBLISHED_PACKAGE_NAME
- legacy-plugin-toast/hook: Use PLUGIN_NAME
- shared/data-path: Use CACHE_DIR_NAME
- shared/external-plugin-detector: Use ACCEPTED_PACKAGE_NAMES
- shared/logger: Use LOG_FILENAME
- tools/ast-grep/downloader: Use PUBLISHED_PACKAGE_NAME
- tools/call-omo-agent/tools: Use PUBLISHED_PACKAGE_NAME
- tools/delegate-task/category-resolver: Use PUBLISHED_PACKAGE_NAME
- tools/grep/constants: Use PUBLISHED_PACKAGE_NAME
- tools/grep/downloader: Use PUBLISHED_PACKAGE_NAME
- tools/lsp/lsp-client-wrapper: Use PUBLISHED_PACKAGE_NAME
🤖 Generated with assistance of OhMyOpenCode
Extract hardcoded GPT apply_patch permission logic into a reusable module
to ensure consistent behavior across all agents. This prevents GPT models
from using the unreliable apply_patch tool while allowing other models.
- Add gpt-apply-patch-guard.ts with GPT_APPLY_PATCH_GUIDANCE and getGptApplyPatchPermission
- Update Hephaestus agent to use centralized permission logic
- Update Sisyphus-Junior agent to use centralized permission logic
- Update all GPT prompt builders to reference shared guidance constant
🤖 Generated with assistance of OhMyOpenCode
When a hook returns exit code 2 (deny) or 1 (ask), previously accumulated
modifiedInput and common fields from earlier allow hooks were discarded.
Now all exit paths (exit code and JSON) include accumulated state.
When a hook returns 'allow' with updatedInput or common fields
(suppressOutput, systemMessage, etc.), these values were silently
dropped. Now they are accumulated across hooks and included in the
final result, matching Claude Code's behavior where allow hooks can
still modify tool input and set metadata.
Revert the create-hooks.ts change — claudeCodeHooks is already created
in createTransformHooks() with proper config and contextCollector.
The previous commit overwrote it with a degraded instance (empty config,
no contextCollector).
Add 8 unit tests for executePreToolUseHooks covering:
- null/empty config handling
- exit code 2 (deny) and 1 (ask) behavior
- multiple merged hooks: allow continues to next hook (the actual bug)
- deny short-circuits remaining hooks
- modifiedInput propagation between hooks
TDD verified: tests fail with original code, pass with fix.
When multiple hook sources are merged (global ~/.claude/settings.json +
project .claude/settings.json), a global catch-all hook returning 'allow'
caused early return before project-level hooks could execute.
Only 'deny' and 'ask' decisions should short-circuit. 'allow' should
continue processing remaining hooks so project-specific guards (e.g.,
file budget enforcement) get a chance to block.
The /stop-continuation command was ineffective because the stop-
continuation-guard cleared its stopped state on the very next
chat.message event. Since any user message (including normal chat
after stopping) triggers chat.message, the continuation would
resume immediately.
Root cause: the chat.message handler called clear(sessionID) on
every user message, treating it as a 'user resumed work' signal.
But the user expects /stop-continuation to persist until they
explicitly start work again.
Changes:
- stop-continuation-guard chat.message: no longer clears stop state
- tool-execute-before: /start-work, /ralph-loop, /ulw-loop now
explicitly clear the stop state (so continuation resumes when
user intentionally restarts work)
- Updated and added tests: 12 pass (3 new), 125 related tests pass
Closes#3276
The auto-update-checker's version resolver hardcoded the canonical
oh-my-opencode package name in three read paths:
1. INSTALLED_PACKAGE_JSON pointed only at
cache/node_modules/oh-my-opencode/package.json
2. findPackageJsonUp() rejected any walked-up package.json whose name
did not equal PACKAGE_NAME
3. getLocalDevPath() only matched file:// plugin entries whose path
contained the canonical name
The publish pipeline ships the same code under two npm package names
(oh-my-opencode canonical, oh-my-openagent alias). Users who add
"oh-my-openagent" to their opencode config end up with
node_modules/oh-my-openagent/package.json, so every read path above
silently missed the installed version and the startup toast fell back
to "unknown".
Introduce ACCEPTED_PACKAGE_NAMES + INSTALLED_PACKAGE_JSON_CANDIDATES in
constants.ts and teach the three readers to accept both names. Writes
are untouched (sync-package-json, pinned-version-updater, cache
invalidation) because the auto-update-checker still owns its own cache
workspace and writes to the canonical name there.
Tests: 54 auto-update-checker tests pass (4 new), full 4444-test suite
passes, tsc clean. New tests cover both install paths, the walk-up
resolver, and the priority order when both candidates exist.
Closes#3257
Reports from david_66 on Discord: sessions get perceived as 'stuck' when
context usage crosses the 78% threshold. Investigation confirmed two
issues in the preemptive compaction hook:
1. PREEMPTIVE_COMPACTION_TIMEOUT_MS was 120s. While the summarize
request is in flight, tool.execute.after short-circuits via the
compactionInProgress guard. A hung summarize blocked the session
for two full minutes before giving up, which users reasonably
experience as a hang.
2. On failure (timeout or exception) only a log line was emitted. The
user had no visibility into why their session was unresponsive or
why auto-compaction never ran, so a transient upstream error could
silently leave them well above the threshold with no signal.
Fix:
- Reduce timeout 120s -> 60s. Still gives the upstream a generous
window, but caps the worst-case perceived hang at one minute.
- Show a warning toast via ctx.client.tui.showToast whenever the
catch block fires, including the underlying error string so users
can act (retry, manual /compact, or adjust provider).
- Include providerID/modelID in the Compaction failed log entry so
wild failures are easier to correlate to a specific target model.
Two existing failure-path assertions were updated to match the new
log shape and a new test covers the toast notification contract.
Discord report: https://discord.com/channels/1452487457085063218/1490536332961906829/1491345441399505037
Replace fragile regex text matching with structured detection for Oracle verification evidence.
- Add oracle-verification-detector.ts with parseOracleVerificationEvidence()
- Use structured parsing instead of multiple regex patterns
- Add comprehensive test coverage for edge cases
- Update completion-promise-detector.ts to use isOracleVerified()
- Update pending-verification-handler.ts to use structured extraction
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
柯杨