80 Commits

Author SHA1 Message Date
YeonGyu-Kim
dab2f90051 test(run): make completion metadata timing assertion deterministic
Avoid Date.now call-order flakiness by pinning the mocked current time and setting the message start time explicitly in the test setup.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-24 21:43:52 +09:00
CloudWaddie
54d0dcde48 fix: address code review feedback on PR #1988
- Fix operator precedence bug in hasActiveWork boolean expression
- Reuse getMainSessionStatus result from watchdog to avoid duplicate API calls
- Add flag to only check secondary timeout once to avoid unnecessary API traffic
2026-02-24 21:32:07 +09:00
CloudWaddie
159ade05cc fix(run): add event watchdog and secondary timeout for hasReceivedMeaningfulWork
Implements fixes from issue #1880 and #1934 to prevent exit code 130 timeout in CI environments:

- Add lastEventTimestamp to EventState for tracking when events were last received
- Add event watchdog: if no events for 30s, verify session status via direct API call
- Add secondary timeout: after 60s without meaningful work events, check for active children/todos and assume work is in progress

This prevents the poll loop from waiting for full 600s timeout when:
1. Event stream drops silently (common in CI with network instability)
2. Main session delegates to children without producing meaningful work on main session
2026-02-24 21:32:07 +09:00
YeonGyu-Kim
cd6c9cb5dc fix(cli/run): replace as any with Record type cast
Cast session body to Record<string, unknown> instead of as any

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-23 02:42:40 +09:00
YeonGyu-Kim
4268cada8d test(events): use baseline snapshot pattern for console spy isolation
Replace exact call count assertions with delta-based checks:
- capture errorSpy.mock.calls.length before processing events
- slice to only check calls made during this test's execution
- use try/finally to guarantee mockRestore() even on assertion failure

This prevents test pollution from cross-file spy leakage in CI batch runs.
2026-02-21 05:08:58 +09:00
YeonGyu-Kim
07c89f0091 docs: restore coding on steroids narrative with future-betting manifesto in all READMEs 2026-02-21 04:54:21 +09:00
YeonGyu-Kim
b1eccf7425 docs: update all 31 AGENTS.md files with current project state 2026-02-21 04:38:18 +09:00
YeonGyu-Kim
f9c78de171 fix(run): set default stabilization to 1s and coerce non-positive values
- Change MIN_STABILIZATION_MS from 0 to 1_000 to prevent premature exits
- Coerce non-positive minStabilizationMs to default instead of treating as disabled
- Fix stabilization logic: track firstWorkTimestamp inside the meaningful-work branch
- Add tests for default stabilization behavior and zero-value coercion

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-02-19 10:46:40 +09:00
YeonGyu-Kim
bd2e23584b docs: update AGENTS.md metadata
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-02-19 10:46:40 +09:00
YeonGyu-Kim
d5bd9cae98 feat(cli): enable timestamped run output by default 2026-02-19 10:46:40 +09:00
YeonGyu-Kim
b0e8f5ec7b feat(run): print agent/model/duration on assistant completion 2026-02-18 21:10:21 +09:00
YeonGyu-Kim
75ff6e1be1 feat(atlas): enforce 4-phase critical QA with mandatory hands-on verification
Rewrite Atlas GPT verification from a checklist to a 4-phase protocol:
Phase 1 (Read Code First), Phase 2 (Automated Checks), Phase 3 (Hands-On QA),
Phase 4 (Gate Decision). Hands-on QA is now mandatory for user-facing changes,
not 'if applicable'. Hook message reinforces subagent distrust and requires
actually running deliverables before proceeding to next task.
2026-02-18 17:50:26 +09:00
YeonGyu-Kim
a717a95e13 fix: clear spy call history in completion-verbose-logging test
spyOn(console, 'log') accumulates calls across test files in bun:test.
Add mockClear() after spy creation to prevent cross-file contamination
when run in the same bun test batch as completion.test.ts.
2026-02-18 17:43:16 +09:00
YeonGyu-Kim
5bb0e69dea fix(cli-run): silence wait noise and suppress raw arrow escape input 2026-02-18 17:25:13 +09:00
YeonGyu-Kim
dacada152a fix(cli-run): attach to default server when auto port range exhausted 2026-02-18 16:02:57 +09:00
YeonGyu-Kim
ada8c127aa refactor(cli-run): remove redundant opencode bin path shim 2026-02-18 16:00:33 +09:00
YeonGyu-Kim
3f16057a4b fix(cli-run): skip unresolved opencode bin path injection 2026-02-18 15:49:44 +09:00
YeonGyu-Kim
1e05f4770e fix(cli-run): retry server start on port binding race condition
When port appears available but binding fails (race with another opencode
instance), retry on next available port (auto mode) or attach to existing
server (explicit port mode) instead of crashing with exit code 1.
2026-02-18 15:01:09 +09:00
YeonGyu-Kim
c21e0b094f fix(cli-run): strip ANSI codes in think block test assertions for CI compatibility 2026-02-18 02:13:41 +09:00
YeonGyu-Kim
2f659e9b97 fix(cli-run): improve agent header and think block spacing
Add newlines around agent header for visual separation, dim the thinking
label, and add trailing newline after think block close.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode) assistance
2026-02-18 02:01:16 +09:00
YeonGyu-Kim
d9751bd5cb fix(cli-run): deduplicate tool headers and message counter resets on repeated events
Guard against duplicate tool header/output rendering when both tool.execute
and message.part.updated fire for the same tool, and prevent message counter
resets when message.updated fires multiple times for the same assistant message.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode) assistance
2026-02-18 02:01:08 +09:00
YeonGyu-Kim
3313ec3e4f chore: regenerate AGENTS.md knowledge base
🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode) assistance
2026-02-18 01:26:19 +09:00
YeonGyu-Kim
04e95d7e27 refactor(cli-run): stream reasoning text instead of summarized thinking line
Replace the single-line "Thinking: <summary>" rendering with direct streaming
of reasoning tokens via writePaddedText. Removes maybePrintThinkingLine and
renderThinkingLine in favor of incremental output with dim styling.

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-02-18 01:14:01 +09:00
YeonGyu-Kim
eaf315a8d7 feat(cli-run): add streaming delta, think block rendering, and rich tool headers
Adds message.part.delta event handling for real-time streaming output,
reasoning/think block display with in-place updates, per-agent profile
colors, padded text output, and semantic tool headers with icons.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-02-18 01:08:39 +09:00
YeonGyu-Kim
d0bd24bede fix(cli-run): rely on continuation markers for completion
Use hook-written continuation marker state to gate run completion checks and remove the noisy event-stream shutdown timeout log in run mode.
2026-02-17 17:50:47 +09:00
YeonGyu-Kim
0d888df879 fix(cli-run): avoid infinite wait on missing child status
Treat child sessions missing from session.status as transient so completion polling can proceed while still blocking on explicit non-idle descendants.
2026-02-17 16:15:25 +09:00
YeonGyu-Kim
5f9cfcbcf3 feat(cli-run): show agent/model header and suppress toast output 2026-02-17 16:11:34 +09:00
YeonGyu-Kim
4d3cce685d refactor: remove cli run timeout path and rely on strict completion 2026-02-17 16:01:57 +09:00
YeonGyu-Kim
7b2c2529fe fix: enforce continuation-aware completion gating 2026-02-17 16:01:57 +09:00
YeonGyu-Kim
47a8c3e4a9 fix: harden run completion checks and graceful timeout 2026-02-17 16:01:57 +09:00
YeonGyu-Kim
5f5b476f12 fix: gate run event traces behind --verbose 2026-02-17 16:01:57 +09:00
YeonGyu-Kim
17994693af fix: add directory parameter and improve CLI run session handling
- Add directory parameter to session API calls (session.get, session.todo,
  session.status, session.children)
- Improve agent resolver with display name support via agent-display-names
- Add tool execution visibility in event handlers with running/completed
  status output
- Enhance poll-for-completion with main session status checking and
  stabilization period handling
- Add normalizeSDKResponse import for consistent response handling
- Update types with Todo, ChildSession, and toast-related interfaces

🤖 Generated with OhMyOpenCode assistance
2026-02-17 02:34:35 +09:00
YeonGyu-Kim
d9f21da026 fix: prefer a runnable opencode binary for cli run 2026-02-17 02:12:36 +09:00
YeonGyu-Kim
51dde4d43f feat(hashline): port hashline edit tool from oh-my-pi
This PR ports the hashline edit tool from oh-my-pi to oh-my-opencode as an experimental feature.

## Features
- New experimental.hashline_edit config flag
- hashline_edit tool with 4 operations: set_line, replace_lines, insert_after, replace
- Hash-based line anchors for safe concurrent editing
- Edit tool disabler for non-OpenAI providers
- Read output enhancer with LINE:HASH prefixes
- Provider state tracking module

## Technical Details
- xxHash32-based 2-char hex hashes
- Bottom-up edit application to prevent index shifting
- OpenAI provider exemption (uses native apply_patch)
- 90 tests covering all operations and edge cases
- All files under 200 LOC limit

## Files Added/Modified
- src/tools/hashline-edit/ (7 files, ~400 LOC)
- src/hooks/hashline-edit-disabler/ (4 files, ~200 LOC)
- src/hooks/hashline-read-enhancer/ (3 files, ~400 LOC)
- src/features/hashline-provider-state.ts (13 LOC)
- src/config/schema/experimental.ts (hashline_edit flag)
- src/config/schema/hooks.ts (2 new hook names)
- src/plugin/tool-registry.ts (conditional registration)
- src/plugin/chat-params.ts (provider state tracking)
- src/tools/index.ts (export)
- src/hooks/index.ts (exports)
2026-02-17 00:03:10 +09:00
YeonGyu-Kim
1a6810535c refactor: create normalizeSDKResponse helper and replace scattered patterns across 37 files 2026-02-16 18:20:19 +09:00
YeonGyu-Kim
5f97a58019 fix(test): stabilize waitForEventProcessorShutdown timeout test for CI
- Reduce timeout from 500ms to 200ms to lower CI execution time
- Add 10ms margin to elapsed time check for scheduler variance
- Replace pc.dim() string matching with call count assertion
  to avoid ANSI escape code mismatch on CI runners
2026-02-16 16:13:40 +09:00
YeonGyu-Kim
96a67e2d4e fix(test): increase timeouts for CI-flaky polling tests
- runner.test.ts: waitForEventProcessorShutdown timeout 50ms → 500ms
  (50ms was consistently too tight for CI runners)
- tools.test.ts: MAX_POLL_TIME_MS 2000ms → 8000ms
  (polling timed out at ~2009ms on CI due to resource contention)
2026-02-16 16:13:40 +09:00
YeonGyu-Kim
e90734d6d9 fix(todo): make Todo id field optional for OpenCode beta compatibility
- Make id field optional in all Todo interfaces (TodoInfo, Todo, TodoItem)
- Fix null-unsafe comparisons in todo-sync.ts to handle missing ids
- Add test case for todos without id field preservation
- All tests pass and typecheck clean
2026-02-16 16:13:39 +09:00
YeonGyu-Kim
b7c32e8f50 fix(test): use string containment check for ANSI-wrapped console.log output
The waitForEventProcessorShutdown test was comparing exact string match
against console.log spy, but picocolors wraps the message in ANSI dim
codes. On CI (bun 1.3.9) this caused the assertion to fail. Use
string containment check instead of exact argument match.
2026-02-14 14:57:48 +09:00
YeonGyu-Kim
c24c4a85b4 fix(cli-run): bounded shutdown wait for event stream processor
Prevents Run CLI from hanging indefinitely when the event stream
fails to close after abort.

Fixes #1825

Co-authored-by: cloudwaddie-agent <cloudwaddie-agent@users.noreply.github.com>
2026-02-14 14:57:48 +09:00
YeonGyu-Kim
9afd0d1d41 fix(run): pass directory to event.subscribe for session-scoped events
The SSE event stream subscription was missing the directory parameter,
causing the OpenCode server to only emit global events (heartbeat,
connected, toast) but not session-scoped events (session.idle,
session.status, tool.execute, message.updated, message.part.updated).

Without session events:
- hasReceivedMeaningfulWork stays false (no message/tool events)
- mainSessionIdle never updates (no session.idle/status events)
- pollForCompletion either hangs or exits for unrelated reasons

Fix: Pass { directory } to client.event.subscribe(), matching the
pattern already used by client.session.promptAsync().

Also adds a stabilization period (10s) after first meaningful work
as defense-in-depth against early exit race conditions.
2026-02-12 11:52:31 +09:00
YeonGyu-Kim
686f32929c fix(cli-run): handle retry status type as non-idle in event handlers
Session status 'retry' was unhandled, leaving mainSessionIdle=true
during retries which could cause premature completion detection.
2026-02-11 00:45:51 +09:00
YeonGyu-Kim
c677042f05 fix(cli-run): set default timeout to 10 minutes and attach immediate .catch() on event processor
DEFAULT_TIMEOUT_MS was 0 (no timeout), causing opencode run to hang forever
if the session never completed. Also attached .catch() to processEvents()
immediately to prevent unhandled promise rejections before Promise.race.
2026-02-11 00:45:51 +09:00
YeonGyu-Kim
1199e2b839 fix(background): Wave 2 - fix interrupt status checks, display text, error recovery grace, LSP JSONC
- fix(background): include "interrupt" status in all terminal status checks (3 files)
- fix(background): display "INTERRUPTED" instead of "CANCELLED" for interrupted tasks
- fix(cli): add error recovery grace period in poll-for-completion
- fix(lsp): use JSONC parser for config loading to support comments

All changes verified with tests and typecheck.
2026-02-10 22:00:54 +09:00
YeonGyu-Kim
df0b9f7664 fix(delegate-task): Wave 1 - fix polling timeout, resource cleanup, tool restrictions, idle dedup, auth-plugins JSONC, CLI runner hang
- fix(delegate-task): return error on poll timeout instead of silent null
- fix(delegate-task): ensure toast and session cleanup on all error paths with try/finally
- fix(delegate-task): apply agent tool restrictions in sync-prompt-sender
- fix(plugin): add symmetric idle dedup to prevent double hook triggers
- fix(cli): replace regex-based JSONC editing with jsonc-parser in auth-plugins
- fix(cli): abort event stream after completion and restore no-timeout default

All changes verified with tests and typecheck.
2026-02-10 22:00:54 +09:00
YeonGyu-Kim
0565ce839e fix(cli/run): handle session.status idle event in addition to deprecated session.idle 2026-02-09 21:12:11 +09:00
YeonGyu-Kim
bb2df9fec6 fix(cli/run): set default timeout to 30 minutes to match help text 2026-02-09 21:12:00 +09:00
YeonGyu-Kim
564bb20f6a fix(cli/run): move error check before idle/tool gates in pollForCompletion 2026-02-09 21:11:48 +09:00
YeonGyu-Kim
5ca3d9c489 fix: address remaining Cubic issues — reset lastPartText on new message, TTY guard for installer, filter disabled skills, local-dev version resolution 2026-02-09 11:01:38 +09:00
YeonGyu-Kim
e5abf8702e merge: integrate origin/dev (4th merge) 2026-02-09 10:59:39 +09:00