elias/oh-my-opencode
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,231 Commits 26 Branches 165 Tags
Commit Graph

3231 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
YeonGyu-Kim
96d27ff56b
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
YeonGyu-Kim
017c18c1b3
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
YeonGyu-Kim
fb194fc944
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
YeonGyu-Kim
10c25d1d47
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
YeonGyu-Kim
86fcade9a4
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
YeonGyu-Kim
5bc3a9e0db
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
YeonGyu-Kim
810ebec1cd
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
YeonGyu-Kim
8f7ed2988a
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
YeonGyu-Kim
7ff8352a0a fix(config): preserve formatter config from opencode settings 
Closes #2117
 2026-02-26 21:01:31 +09:00
YeonGyu-Kim
d425f9bb80 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
YeonGyu-Kim
cc5e9d1e9b fix(ci): add baseline CPU variant binaries for legacy hardware support 
Closes #2121
 2026-02-26 21:00:45 +09:00
YeonGyu-Kim
269f37af1c fix(windows): add windowsHide to Bun.spawn calls to prevent stray terminal windows 
Closes #1915
 2026-02-26 21:00:40 +09:00
YeonGyu-Kim
1e060e9028 fix(look-at): add timeout to sync model retry to prevent process hang 
Closes #2087
 2026-02-26 20:59:53 +09:00
YeonGyu-Kim
ccb789e5df fix(stop-continuation): wire backgroundManager to cancel running tasks on stop 
Closes #2017
 2026-02-26 20:59:35 +09:00
YeonGyu-Kim
a6617d93c0 fix(ralph-loop): add inFlight guard and improve completion detection to prevent infinite loops 
Closes #2084
 2026-02-26 20:59:18 +09:00
YeonGyu-Kim
2295161022 fix(ralph-loop): add inFlight guard and improve completion detection to prevent infinite loops 
Closes #2084
 2026-02-26 20:58:55 +09:00
YeonGyu-Kim
0516f2febc fix(todo-continuation): exclude blocked todos from incomplete count to prevent infinite loops 
Closes #2025
 2026-02-26 20:58:48 +09:00
YeonGyu-Kim
df02c73a54 fix(agents): retain original agent keys in remapAgentKeysToDisplayNames to prevent crash 
Closes #1922
 2026-02-26 20:58:47 +09:00
YeonGyu-Kim
52658ac1c4 fix(config): preserve existing user config when writing new defaults 
Closes #2064
 2026-02-26 20:58:07 +09:00
YeonGyu-Kim
fab820e919 fix(compaction): add timeout and ensure cleanup to prevent indefinite hangs on rate limit 
Closes #2062
 2026-02-26 20:58:01 +09:00
YeonGyu-Kim
6f54404a51 fix(hephaestus): add explicit auto-commit instructions to agent prompt 
Closes #2102
 2026-02-26 20:57:58 +09:00
YeonGyu-Kim
a3169c9287 fix(hashline-edit): limit diff context to 3 lines to prevent oversized hunks 
Closes #2051
 2026-02-26 20:57:47 +09:00
YeonGyu-Kim
0639ce8df7 fix(atlas): allow task and call_omo_agent tools for subagent dispatch 
Closes #2044
 2026-02-26 20:55:20 +09:00
YeonGyu-Kim
685b8023dd fix(background-task): make background_output block=true actually wait for task completion 
Closes #2115
 2026-02-26 20:55:11 +09:00
YeonGyu-Kim
07e8d965a8 fix(atlas): allow task and call_omo_agent tools for subagent dispatch 
Closes #2044
 2026-02-26 20:54:42 +09:00
YeonGyu-Kim
c505989ad4
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
YeonGyu-Kim
088984a8d4 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
YeonGyu-Kim
0b69a6c507 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
YeonGyu-Kim
5fe1640f2a 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
YeonGyu-Kim
ad01f60e99 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
YeonGyu-Kim
87d6b2b519 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
YeonGyu-Kim
b7b6721796 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
0c59d2dbe7 refactor(ultrawork): remove thinking config injection from model override 
Delegate thinking config control to the provider layer rather than
injecting it manually in ultrawork model override.

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
 2026-02-26 20:08:44 +09:00
YeonGyu-Kim
52d366e866 feat(start-work): update template with --worktree flag documentation 
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
YeonGyu-Kim
9cd6fc6135 feat(atlas): inject worktree_path into boulder continuation 
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
YeonGyu-Kim
f872f5e171 feat(start-work): add --worktree flag support in hook 
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
YeonGyu-Kim
f500fb0286 feat(start-work): add --worktree flag parsing from user request 
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
YeonGyu-Kim
9a94e12065 feat(start-work): add worktree path detection 
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
YeonGyu-Kim
808a50d808 feat(boulder-state): add worktree_path field to BoulderState 
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
github-actions[bot]
a263188abd
@maou-shonen has signed the CLA in code-yeongyu/oh-my-opencode#2131 2026-02-26 09:50:58 +00:00
maou shonen
acb51d1702
fix(comment-checker): bump dependency to ^0.7.0 for --prompt support 2026-02-26 09:48:57 +00:00
github-actions[bot]
155ed5248d
@imwxc has signed the CLA in code-yeongyu/oh-my-opencode#2129 2026-02-26 09:22:45 +00:00
github-actions[bot]
ed5a2fe393
@spacecowboy0416 has signed the CLA in code-yeongyu/oh-my-opencode#2126 2026-02-26 06:05:38 +00:00
github-actions[bot]
cd504a2694
@zhzy0077 has signed the CLA in code-yeongyu/oh-my-opencode#2125 2026-02-26 04:45:36 +00:00
Zhiyuan Zheng
890a737d1e fix(chat-headers): skip x-initiator override for @ai-sdk/github-copilot models 
OpenCode's copilot fetch wrapper already sets x-initiator based on the
actual HTTP request body content. When oh-my-opencode's chat.headers
hook overrides it with 'agent', the Copilot API detects a mismatch
between the header and the request body and rejects the request with
'invalid initiator'.

This matches the approach OpenCode's own chat.headers handler uses
(copilot.ts:314) — it explicitly skips @ai-sdk/github-copilot models
because the fetch wrapper handles x-initiator correctly on its own.
 2026-02-26 12:38:05 +08:00
github-actions[bot]
e556c4a5c8
@SupenBysz has signed the CLA in code-yeongyu/oh-my-opencode#2119 2026-02-25 22:01:04 +00:00
east-shine
94ff673d40 test(model-fallback): google provider 모델명 변환 테스트 추가 
google provider에서 gemini-3-pro → gemini-3-pro-preview 변환이
getNextFallback를 통해 정상 적용되는지 검증하는 테스트 추가.
기존 github-copilot 테스트와 동일한 패턴으로 작성.
 2026-02-25 21:40:28 +09:00
github-actions[bot]
be7f408049
@east-shine has signed the CLA in code-yeongyu/oh-my-opencode#2113 2026-02-25 08:19:44 +00:00
Jaden
f6d5f6f79f fix(model-fallback): apply transformModelForProvider in getNextFallback 
The getNextFallback function returned raw model names from the
hardcoded fallback chain without transforming them for the target
provider. For example, github-copilot requires dot notation
(claude-sonnet-4.6) but the fallback chain stores hyphen notation
(claude-sonnet-4-6).

The background-agent retry handler already calls
transformModelForProvider correctly, but the sync chat.message
hook in model-fallback was missing it — a copy-paste omission.

Add transformModelForProvider call in getNextFallback and a test
verifying github-copilot model name transformation.
 2026-02-25 17:15:13 +09:00
YeonGyu-Kim
2ab40124ee
Merge pull request #2111 from code-yeongyu/fix/background-notification-idle-queue 
fix(background-agent): queue notifications for idle parent sessions
 2026-02-25 16:30:09 +09:00