sapient/oh-my-openagent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: remove copy-paste artifacts in hephaestus gpt-5-3-codex prompt

Browse Source 
Same issue as gpt.ts and gpt-5-4.ts: duplicated CORRECT block with pipe
characters and duplicated Hard Constraints/Task Scope Clarification sections.
This commit is contained in:
YeonGyu-Kim
2026-03-24 10:14:53 +09:00
parent 8879581fc1
commit a00a22ac4c
1 changed files with 5 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
src/agents/hephaestus/gpt-5-3-codex.ts
View File

@@ -152,19 +152,7 @@ Asking the user is the LAST resort after exhausting creative alternatives.
- "I'll do X" / "I recommend X" then ending turn → You COMMITTED to X. DO X NOW before ending.
- Explaining findings without acting on them → ACT on your findings immediately.
|**CORRECT:**
|- Keep going until COMPLETELY done
|- Run verification (lint, tests, build) WITHOUT asking
|- Make decisions. Course-correct only on CONCRETE failure
|- Note assumptions in final message, not as questions mid-work
|- Need context? Fire explore/librarian in background IMMEDIATELY — continue only with non-overlapping work while they search
|- User asks "did you do X?" and you didn't → Acknowledge briefly, DO X immediately
|- User asks a question implying work → Answer briefly, DO the implied work in the same turn
|- You wrote a plan in your response → EXECUTE the plan before ending turn — plans are starting lines, not finish lines
|
### Task Scope Clarification
|
You handle multi-step sub-tasks of a SINGLE GOAL. What you receive is ONE goal that may require multiple steps to complete — this is your primary use case. Only reject when given MULTIPLE INDEPENDENT goals in one request.
**CORRECT:**
- Keep going until COMPLETELY done
- Run verification (lint, tests, build) WITHOUT asking
- Make decisions. Course-correct only on CONCRETE failure
@@ -174,6 +162,10 @@ You handle multi-step sub-tasks of a SINGLE GOAL. What you receive is ONE goal t
- User asks a question implying work → Answer briefly, DO the implied work in the same turn
- You wrote a plan in your response → EXECUTE the plan before ending turn — plans are starting lines, not finish lines
### Task Scope Clarification
You handle multi-step sub-tasks of a SINGLE GOAL. What you receive is ONE goal that may require multiple steps to complete — this is your primary use case. Only reject when given MULTIPLE INDEPENDENT goals in one request.
## Hard Constraints
${hardBlocks}