feat(method): refuse prompt boilerplate as unique content - #152
Conversation
Instruction and prompt boilerplate stays explicit method structure (ADR 0004 and 0012). It is not unique latent content and is not erased by a stopword list. Recovery is the computed share of prompt kinds that match known truth versus collapsing every token to unique content.
|
Warning Review limit reachedNext included review available in 32 minutes. View limit detailsLimit details: You’ve used the included review currently available. You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. Review configuration: ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (18)
📝 WalkthroughWalkthrough새 Changesprompt_source identity 구현
Estimated code review effort: 3 (Moderate) | ~25 minutes Merge Risk: 🟡 Moderate · up to The PR adds prompt-versus-unique-content classification, but its current documentation includes an overbroad recovery-rate claim and insufficient primary-source attribution for a scientific statement. Merge should wait until those documentation and traceability issues are corrected. 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
# Conflicts: # CHANGELOG.md # docs/validation/temporal-event-foundation.md
|
Current head |
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
|
Fixed the exact-head failure at Local proof: Python quality branch coverage 991 statements / 442 branches at 100%, workspace contract, Rust docstrings, documentation validation, and diff checks passed. Hosted Checks are rerunning for |
|
@opencode-agent @cwl-noema-review please independently review exact current HEAD |
|
Current-head review fix (9409d83): removed the duplicate active-PR Purpose-bound provider payloads ledger row; one implemented-main row now remains. Local validation passed: 89 quality tests, 100% statement/branch coverage (991/991, 442/442), workspace/docstring/documentation contracts, and diff check. Please re-review this exact head. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
|
Bound the prompt-source claim at exact head Local evidence: prompt_source tests (6 passed), fmt, clippy, documentation/workspace/docstring checks, and Python quality (89 tests; 100% statement/branch, 991/442) passed. Exact-head GitHub checks are re-running after this push. |
|
Review the exact current PR head a67d903 against base main with the protected independent agents. Re-check current source, tests, coverage, documentation, and security; do not modify or merge. @opencode-agent @cwl-noema-review |
|
Current-head review refresh for a67d903:
|
|
Rebased current head 601e402 onto origin/main. The changelog conflict retains both feature and current-main entries; inherited documentation trailing whitespace was removed. Local merge-tree, git diff --cached --check, and cargo fmt --all -- --check pass. Exact-head hosted checks and required independent approvals remain required before protected merge. |
|
@opencode-agent @cwl-noema-review Review-only request for exact current head |
|
Current-head review request: please review commit 70a6c66 only. Verify the prompt-source contract, the resolved ledger duplication, the conditional identity-recovery claim, and the APA 7 primary-source boundary across the changed files. Return an independent substantive verdict; do not merge or update the branch. |
|
Current-head review request: exact head |
Exact-head queue dispositionExact head |
# Conflicts: # ARCHITECTURE.md # CHANGELOG.md # Cargo.lock # Cargo.toml # README.md # docs/TRACEABILITY.md # docs/adr/0004-shared-multilingual-latent-space.md # docs/adr/0012-temporal-relational-shared-latent-topic-measurement.md # docs/adr/README.md # docs/research/standards-and-literature.md # docs/validation/temporal-event-foundation.md # scripts/check_workspace_contract.py # tests/quality/test_check_docstrings.py
| pub fn identity_recovery_rate( | ||
| truth: &[PromptKind], | ||
| decided: &[PromptKind], | ||
| ) -> Result<f64, PromptSourceError> { | ||
| if truth.is_empty() || truth.len() != decided.len() { | ||
| return Err(PromptSourceError::InvalidPromptPayload); | ||
| } | ||
| let mut matches = 0_u32; | ||
| for (truth_kind, decided_kind) in truth.iter().zip(decided) { | ||
| if truth_kind == decided_kind { | ||
| matches += 1; | ||
| } | ||
| } | ||
| Ok(f64::from(matches) / truth.len() as f64) | ||
| } |
There was a problem hiding this comment.
📝 Info: prompt_source recovery/refusal logic verified correct
The new crate's core logic in kind.rs was reviewed carefully. identity_recovery_rate fails closed on empty or length-mismatched slices (kind.rs), counts matches over the zipped pairs, and divides by truth.len() (safe since non-empty). The from_wire_name/wire_name round-trip and the two refusal functions are exhaustive over the closed PromptKind vocabulary. No correctness issues found here.
Was this helpful? React with 👍 or 👎 to provide feedback.
| "tepp_api", | ||
| "prompt_source", |
There was a problem hiding this comment.
📝 Info: Workspace member ordering matches EXPECTED_CRATES
prompt_source was appended to both members and default-members in Cargo.toml and to EXPECTED_CRATES in check_workspace_contract.py. The contract requires an exact ordered match (check_workspace_contract.py), and the append positions are consistent across all three lists, so the workspace contract check will pass.
Was this helpful? React with 👍 or 👎 to provide feedback.
1 participant
Instruction and prompt boilerplate stays explicit method structure (ADR 0004/0012). It is not unique latent content and is not erased by a stopword list. Recovery is the computed share of recovered kinds that match known truth versus collapsing every token to unique content.
Complementary to #75 report-template inferential-weight, #147 section, #148 style, #149 copied-text, #150 modality, and #151 corpus-background. This crate owns prompt-versus-unique-content identity.
Local gates:
Does not allocate migration `0008`. Does not recreate those in-flight method-source crates.
Keep this PR draft. Preferred merge remains #47 only when exact-head required Checks pass and a qualifying independent APPROVE exists. Do not empty-commit #47. Re-draft #144 if it is undrafted.
Summary by CodeRabbit
새로운 기능
문서