catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-14 02:42:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: resolve data flow inconsistencies found in post-migration review

Browse Source 
- test-fix-agent: remove flow_control references, use pre_analysis and convergence.criteria
- code-developer: shared_context reads from plan.json instead of task meta
This commit is contained in:
catlog22
2026-02-13 11:50:42 +08:00
parent 17f52da4c6
commit 659fb48c08
2 changed files with 8 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.claude/agents/test-fix-agent.md
View File

@@ -56,8 +56,8 @@ You will execute tests across multiple layers, analyze failures with layer-speci
jq --arg ts "$(date -Iseconds)" '.status="in_progress" | .status_history += [{"from":.status,"to":"in_progress","changed_at":$ts}]' IMPL-X.json > tmp.json && mv tmp.json IMPL-X.json
```
### Flow Control Execution
When task JSON contains `flow_control` field, execute preparation and implementation steps systematically.
### Task Execution Flow
When task JSON contains `pre_analysis` and `implementation` fields, execute preparation and implementation steps systematically.
**Pre-Analysis Steps** (`pre_analysis`):
1. **Sequential Processing**: Execute steps in order, accumulating context
@@ -91,7 +91,7 @@ When task JSON contains implementation_approach array:
- `"agent"` (default) → Agent direct execution:
- Parse `modification_points` as files to modify
- Follow `logic_flow` for test-fix iteration
- Use test_commands from flow_control for test execution
- Use test_commands from convergence.criteria for test execution
### 1. Context Assessment & Test Discovery