feat(prompt): include req_changed diagnostics in --prompt output#6
Closed
xen0n wants to merge 5 commits into
Closed
feat(prompt): include req_changed diagnostics in --prompt output#6xen0n wants to merge 5 commits into
xen0n wants to merge 5 commits into
Conversation
The TMPL_SHIFTED_SPAN template used {old_start}, {old_end}, {new_start},
{new_end} but the code produces old_span and new_span as arrays.
Fix the template to use the correct variable names.
Signed-off-by: WANG Xuerui <git@xen0n.name>
The --prompt mode now includes req_changed diagnostics, which fire when a related requirement's text has changed. This completes the coverage of all actionable diagnostic types in prompt mode. - Add TMPL_REQ_CHANGED template with instructions to run liyi approve - Handle DiagnosticKind::ReqChanged in build_prompt_output - Add test fixture verification for req_changed prompt group Signed-off-by: WANG Xuerui <git@xen0n.name>
Update the design document to reflect that ReqChanged diagnostics are now included in --prompt output, bringing the total to seven diagnostic types. Signed-off-by: WANG Xuerui <git@xen0n.name>
Add the req_changed diagnostic type to the prompt output schema, including the enum value and the reqChangedItem definition for validation. Signed-off-by: WANG Xuerui <git@xen0n.name>
Signed-off-by: WANG Xuerui <git@xen0n.name>
xen0n
force-pushed
the
feat/prompt-req-changed
branch
from
March 21, 2026 11:24
2041d71 to
f9cec6c
Compare
Contributor
Author
|
Failed instruction following, not even AIGC trailers. Sigh. |
xen0n
added a commit
that referenced
this pull request
Jun 1, 2026
Risk #6 (Agent reliability spectrum) and "The cognitive load inversion" section both make the "unreliable agents make the linter more valuable, not less" argument. The cognitive-load section is the canonical treatment (it develops the --prompt inversion, the MUST/SHOULD/REFERENCE tiers, and the value-proposition reframing in full). Keep Risk #6's unique content -- the five-problem diagnosis of why AGENTS.md is poorly optimized for weak models, and the action item -- and compress its second paragraph, which re-derived the cognitive-load section's "Implications", into a one-line statement plus cross-reference. Risk #6 already points to that section for the remedy. Original prompt: > please go through the liyi-design.md and identify streamlining > chances -- the document underwent multiple rounds of reviews and > iterative improvement from multiple models, and there may well be > redundant reasoning and info here and there. AI-assisted-by: Claude Opus 4.8 (GitHub Copilot) Signed-off-by: WANG Xuerui <git@xen0n.name>
xen0n
added a commit
that referenced
this pull request
Jun 1, 2026
Risk #6 (Agent reliability spectrum) and "The cognitive load inversion" section both make the "unreliable agents make the linter more valuable, not less" argument. The cognitive-load section is the canonical treatment (it develops the --prompt inversion, the MUST/SHOULD/REFERENCE tiers, and the value-proposition reframing in full). Keep Risk #6's unique content -- the five-problem diagnosis of why AGENTS.md is poorly optimized for weak models, and the action item -- and compress its second paragraph, which re-derived the cognitive-load section's "Implications", into a one-line statement plus cross-reference. Risk #6 already points to that section for the remedy. Original prompt: > please go through the liyi-design.md and identify streamlining > chances -- the document underwent multiple rounds of reviews and > iterative improvement from multiple models, and there may well be > redundant reasoning and info here and there. AI-assisted-by: Claude Opus 4.8 (GitHub Copilot) Signed-off-by: WANG Xuerui <git@xen0n.name>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
req_changedgroups to--promptoutputshifted_spantemplate to match emitted item fieldsTesting