Commit Graph

8 Commits

Author SHA1 Message Date
YeonGyu-Kim 16b0d9eb77 fix(atlas): gate final-wave approval on real plan state
Ignore nested plan checkboxes and track parallel final-wave approvals so Atlas only pauses for user approval when the real top-level review wave is complete.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-16 10:38:55 +09:00
YeonGyu-Kim 554392e639 fix(agents): add anti-duplication rules to Atlas agent prompts 2026-03-11 20:38:46 +09:00
YeonGyu-Kim e4fd29ac8b fix: prevent agents from duplicating delegated subagent work
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-11 17:42:42 +09:00
YeonGyu-Kim 4517699d5e fix(atlas): clarify capped directory diagnostics guidance 2026-03-09 11:09:13 +09:00
acamq 858b10df6f feat(lsp): add directory support to lsp_diagnostics via extension param
- Add isDirectoryPath helper to lsp-client-wrapper.ts
- Create directory-diagnostics.ts with aggregateDiagnosticsForDirectory
- Update diagnostics-tool.ts with extension parameter for directory paths
- Update Atlas agent prompts to use extension param for directory diagnostics
- Add unit tests for isDirectoryPath and aggregateDiagnosticsForDirectory

Fixes #2362
2026-03-07 13:05:58 -07:00
YeonGyu-Kim bf8d0ffcc0 fix(atlas): enforce checkbox completion before next task
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-03-08 01:41:45 +09:00
YeonGyu-Kim cde6566792 refactor(atlas): add Final Verification Wave to orchestration workflow
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-06 14:26:04 +09:00
YeonGyu-Kim da13a2f673 feat(agents): add Gemini-optimized prompts for Sisyphus, Sisyphus-Junior, Prometheus, Atlas
Gemini models are aggressively optimistic and avoid tool calls in favor of
internal reasoning. These prompts counter that with:
- TOOL_CALL_MANDATE sections forcing actual tool usage
- Anti-optimism checkpoints before claiming completion
- Stronger delegation enforcement (Gemini prefers doing work itself)
- Aggressive verification language (subagent results are 'EXTREMELY SUSPICIOUS')
- Mandatory thinking checkpoints in Prometheus (prevents jumping to conclusions)
- Scope discipline reminders (creativity → implementation quality, not scope creep)
2026-02-22 15:30:40 +09:00