973952af30
Merge pull request #2155 from code-yeongyu/fix/ultrawork-thinking-db-write
...
fix(ultrawork-db): write $.thinking alongside $.variant in deferred model override
2026-02-27 03:23:30 +09:00
a5b6681390
fix(ultrawork-db): write $.thinking alongside $.variant in deferred model override
2026-02-27 02:59:22 +09:00
485ef2476f
Merge pull request #2154 from minpeter/feat/hashline-benchmark
...
fix(hashline-edit): harden deduplication, validation, and add benchmark suite
2026-02-27 02:14:12 +09:00
a2b2cb7e87
fix(benchmarks): address review feedback on error handling and validation
...
- headless.ts: emit error field on tool_result when output starts with Error:
- test-multi-model.ts: errored/timed-out models now shown as RED and exit(1)
- test-multi-model.ts: validate --timeout arg (reject NaN/negative)
- test-edge-cases.ts: use exact match instead of trim() for whitespace test
- test-edge-cases.ts: skip file pre-creation for create-via-append test
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-02-27 01:44:51 +09:00
3cff4c1bce
feat(benchmarks): add hashline-edit test suites (46 tests)
...
Ported from code-editing-agent benchmark:
- test-edit-ops.ts: 21 basic edit operations (replace, append, prepend, delete, batch, range)
- test-edge-cases.ts: 25 edge cases (unicode, long lines, whitespace, special chars, file creation)
- test-multi-model.ts: multi-model comparison runner
Verified 21/21 + 25/25 (100%) with Minimax M2.5 via FriendliAI.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-02-27 01:37:49 +09:00
a71a97c2ea
feat(benchmarks): add hashline-edit benchmark agent and deps
...
Standalone headless agent using Vercel AI SDK v6 with FriendliAI provider.
Imports hashline-edit pure functions directly from src/ for benchmarking
the edit tool against LLMs (Minimax M2.5 via FriendliAI).
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-02-27 01:37:40 +09:00
26004f93ec
Fix hashline-edit deduplication and validation
...
- Canonicalize anchors in dedupe keys to handle whitespace variants
- Make lines field required in edit operations
- Only allow unanchored append/prepend to create missing files
- Reorder delete/rename validation to prevent edge cases
- Add allow_non_gpt_model and max_prompt_tokens to config schema
```
2026-02-27 01:37:19 +09:00
d491a20fe4
Merge pull request #2093 from code-yeongyu/fix/issue-1966-ultrawork-variant
...
fix(keyword-detector): respect ultrawork config variant instead of hardcoding "max"
2026-02-26 23:23:14 +09:00
8b3335fb2c
Merge pull request #2149 from code-yeongyu/fix/issue-1815-1733-prompt-token-count
...
fix(delegate-task): add token counting and truncation to prevent context overflow
2026-02-26 23:19:35 +09:00
51db9da426
fix(keyword-detector): respect ultrawork config variant instead of hardcoding "max"
...
Closes #1966
2026-02-26 23:15:32 +09:00
3981190fb6
ci: trigger CI
2026-02-26 23:14:33 +09:00
4b946c8883
Merge pull request #1963 from MoerAI/fix/multi-issue-1888-1693-1891
...
fix: resolve issues #1888 , #1693 , #1891
2026-02-26 23:13:00 +09:00
ec38875fd8
Merge pull request #2145 from code-yeongyu/fix/issue-1915-windows-spawn-hide
...
fix(windows): add windowsHide to Bun.spawn calls to prevent stray terminal windows
2026-02-26 23:12:57 +09:00
2d0ad603ff
Merge pull request #2148 from code-yeongyu/fix/issue-2121-legacy-hardware-baseline
...
fix(ci): add baseline CPU variant binaries for legacy hardware support
2026-02-26 21:09:19 +09:00
193ec5cd19
Merge pull request #2146 from code-yeongyu/fix/issue-2065-1968-model-updates
...
fix(models): update Gemini 3→3.1 Pro and add Kimi K2.5 to writing category
2026-02-26 21:07:23 +09:00
adf7980527
Merge pull request #2143 from code-yeongyu/fix/issue-2017-stop-continuation-cancel
...
fix(stop-continuation): wire backgroundManager to cancel running tasks on stop
2026-02-26 21:07:20 +09:00
a06ab8f5c1
Merge pull request #2141 from code-yeongyu/fix/issue-2084-ralph-loop-inflight
...
fix(ralph-loop): add inFlight guard and improve completion detection to prevent infinite loops
2026-02-26 21:07:17 +09:00
bf2c04928c
Merge pull request #2140 from code-yeongyu/fix/issue-2025-blocked-todo-continuation
...
fix(todo-continuation): exclude blocked todos from incomplete count to prevent infinite loops
2026-02-26 21:06:55 +09:00
f98943bb90
Merge pull request #2134 from code-yeongyu/fix/issue-2064-config-overwrite
...
fix(config): preserve existing user config when writing new defaults
2026-02-26 21:06:17 +09:00
8c993a99c9
Merge pull request #2138 from code-yeongyu/fix/issue-2062-compaction-timeout
...
fix(compaction): add timeout and cleanup to prevent indefinite hangs on rate limit
2026-02-26 21:06:05 +09:00
77bb0e46d0
Merge pull request #2147 from code-yeongyu/fix/issue-2117-preserve-formatter-config
...
fix(config): preserve formatter config from opencode settings
2026-02-26 21:05:46 +09:00
1c3b67bb19
Merge pull request #2144 from code-yeongyu/fix/issue-2087-look-at-hang
...
fix(look-at): add timeout to sync model retry to prevent process hang
2026-02-26 21:05:43 +09:00
96ffb3fd72
Merge pull request #2142 from code-yeongyu/fix/issue-1922-retain-agent-keys
...
fix(agents): retain original agent keys in remapAgentKeysToDisplayNames to prevent crash
2026-02-26 21:04:32 +09:00
ea240ae783
Merge pull request #2137 from code-yeongyu/fix/issue-2051-diff-context-limit
...
fix(hashline-edit): limit diff context to 3 lines to prevent oversized hunks
2026-02-26 21:04:29 +09:00
d14356503b
Merge pull request #2136 from code-yeongyu/fix/issue-2044-atlas-task-tool
...
fix(atlas): allow task and call_omo_agent tools for subagent dispatch
2026-02-26 21:04:26 +09:00
cbb342ab53
Merge pull request #2135 from code-yeongyu/fix/issue-2115-background-output-block
...
fix(background-task): make background_output block=true actually wait for task completion
2026-02-26 21:04:23 +09:00
1059a87a1f
fix(config): preserve formatter config from opencode settings
...
Closes #2117
2026-02-26 21:01:31 +09:00
7a88f151df
fix(models): update Gemini 3 to 3.1 Pro and add Kimi to writing category fallback
...
Closes #2065
Closes #1968
2026-02-26 21:01:26 +09:00
2eae64f1b2
fix(ci): add baseline CPU variant binaries for legacy hardware support
...
Closes #2121
2026-02-26 21:00:45 +09:00
06580aa548
fix(windows): add windowsHide to Bun.spawn calls to prevent stray terminal windows
...
Closes #1915
2026-02-26 21:00:40 +09:00
4128390e1b
fix(look-at): add timeout to sync model retry to prevent process hang
...
Closes #2087
2026-02-26 20:59:53 +09:00
da74ccc356
fix(stop-continuation): wire backgroundManager to cancel running tasks on stop
...
Closes #2017
2026-02-26 20:59:35 +09:00
f5b5f5315c
fix(ralph-loop): add inFlight guard and improve completion detection to prevent infinite loops
...
Closes #2084
2026-02-26 20:59:18 +09:00
5892d0fbb1
fix(ralph-loop): add inFlight guard and improve completion detection to prevent infinite loops
...
Closes #2084
2026-02-26 20:58:55 +09:00
38466ec676
fix(todo-continuation): exclude blocked todos from incomplete count to prevent infinite loops
...
Closes #2025
2026-02-26 20:58:48 +09:00
936fb98447
fix(agents): retain original agent keys in remapAgentKeysToDisplayNames to prevent crash
...
Closes #1922
2026-02-26 20:58:47 +09:00
448b481e03
fix(config): preserve existing user config when writing new defaults
...
Closes #2064
2026-02-26 20:58:07 +09:00
6de1b3ba7c
fix(compaction): add timeout and ensure cleanup to prevent indefinite hangs on rate limit
...
Closes #2062
2026-02-26 20:58:01 +09:00
2ce9501099
fix(hephaestus): add explicit auto-commit instructions to agent prompt
...
Closes #2102
2026-02-26 20:57:58 +09:00
a43d8b3bcc
fix(hashline-edit): limit diff context to 3 lines to prevent oversized hunks
...
Closes #2051
2026-02-26 20:57:47 +09:00
e4d1af4a7c
fix(atlas): allow task and call_omo_agent tools for subagent dispatch
...
Closes #2044
2026-02-26 20:55:20 +09:00
2b7ed4bbb4
fix(background-task): make background_output block=true actually wait for task completion
...
Closes #2115
2026-02-26 20:55:11 +09:00
1d549badc8
fix(atlas): allow task and call_omo_agent tools for subagent dispatch
...
Closes #2044
2026-02-26 20:54:42 +09:00
502bcf76dd
Merge pull request #2095 from code-yeongyu/fix/issue-1934-exit-code-130-timeout
...
fix(run): add event watchdog and secondary timeout to prevent infinite hang in CI
2026-02-26 20:48:46 +09:00
a34311a527
fix: remove Current date from env context since OpenCode already provides it
...
date is already injected by OpenCode's system.ts. omo-env now contains only
Timezone and Locale, which are stable across requests and never break cache.
2026-02-26 20:22:17 +09:00
bc2cc541cf
fix(atlas): replace permanent failure lockout with 5-minute backoff
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-02-26 20:20:45 +09:00
81328a585b
fix(boulder): count indented checkboxes in plan progress
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-02-26 20:20:28 +09:00
b3e2bc763d
fix: remove seconds-precision time from env context to stop breaking token cache
...
Current time with HH:MM:SS changed every second, invalidating the prompt cache
on every request. Date-level precision is sufficient; timezone and locale are
stable. Removes Current time field entirely from createEnvContext output.
2026-02-26 20:08:44 +09:00
60f86523b7
feat(agents): simplify GPT detection to name-based check, add hephaestus providers (venice uses gpt-5.3-codex)
...
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-02-26 20:08:44 +09:00
3b5d0dbb47
refactor(think-mode): migrate hook from chat.params to chat.message and remove thinking config injection
...
Drop provider-specific thinking config injection (THINKING_CONFIGS, getThinkingConfig,
resolveProvider) and instead rely on the provider to handle thinking based on the variant field.
Hook now fires on chat.message using model from input rather than from the message object.
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode )
2026-02-26 20:08:44 +09:00
YeonGyu-Kim