2.3.0: prompt mode speed + quality refresh (dense prompt v2) - #34
Conversation
Cites V24, V27, V28, V30, and V32.
Cites V31.
Closes T26. Enforces V18, V24, V29, V30, V33, V34, V35, and V36.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 6c3e04722d
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| intent, | ||
| legacy_system_prompt=ffp_config.CLAUDE_PROMPT_SYSTEM_PROMPT, | ||
| prompt_v1_system_prompt=ffp_config.CLAUDE_PROMPT_SYSTEM_PROMPT_V1, | ||
| prompt_v2_system_prompt=ffp_config.CLAUDE_PROMPT_SYSTEM_PROMPT_V2, |
There was a problem hiding this comment.
Apply v2 grounding in live prompt-builder eval
When tools/prompt_builder_eval.py --live runs the default Claude cases, this now sends the v2 draft prompt, which intentionally asks the model for a one-sentence draft; production then calls ground_prompt_v2_output() before validating. This evaluator still validates the raw draft against the four-section XML contract, so live eval artifacts for the default cases will report false failures instead of measuring shipped behavior.
Useful? React with 👍 / 👎.
2.3.0 — prompt mode speed + quality refresh
Rewrites the default
prompt:output to a dense, high-signal prompt v2 and lowers the token budget, cutting latency well under the 15 s goal while improving quality.Measured (committed A/B evidence, FLM
qwen3.5:4b)Changes
CLAUDE_PROMPT_SYSTEM_PROMPT_V2); old verbose prompt kept as..._V1for instant rollback.tools/prompt_speed_quality_eval.py) + artifacts; +33 tests.Gates: ruff clean, 381 pytest, version 2.3.0 consistent across the 4 files.
🤖 Generated with Claude Code