mirror of
https://github.com/allaunthefox/Research-Stack.git
synced 2026-07-30 18:56:16 +00:00
f70552211b
Follow-up to PR #10. Addresses comments left by Devin Review. Primary fix (the BUG comment, .pre-commit-config.yaml:86-87): The receipt-required-for-math-content hook used files: '<math-track regex>' with pass_filenames: true. Pre-commit applies that regex to the staged file list BEFORE invoking the hook, so evidence files (receipts under shared-data/artifacts/deepseek_review/, claims.yaml) were stripped from argv. require_math_evidence.py then saw only the math-track files, found no evidence, and exited 1 -- even when proper evidence was committed alongside. The only case that worked was Lean-only commits, because Lean files are dual-classified as both math-track and evidence. Fix: drive the hook from the index instead of argv. * require_math_evidence.py grows a --staged mode that runs 'git diff --cached --name-only' itself, plus a mutex check so --staged, --from-git-diff, and explicit FILES cannot be combined. * .pre-commit-config.yaml hook switches to always_run: true, pass_filenames: false, and 'entry: ... --staged'. The script exits 0 early when no math-track files are staged, so the cost of always_run is negligible. Polish: * claims-registry.schema.json: add required: ["status"] inside each 'if' subschema. Without it, an entry missing 'status' would also spuriously trip the 'then' clauses (review_receipts, lean) before the top-level required catch. Pure error-message cleanup. * validate_claims_registry.py: replace the catch-all re.compile(r'^[A-Za-z]+:') with a closed list of well-known URI schemes (http, https, arxiv, doi, isbn, mailto, urn). Module-name-shaped strings like 'Module:Theorem' will no longer silently bypass the on-disk path check. * validate_claims_registry.py: thread a FormatChecker through the Draft202012Validator so format-keyword behaviour matches validate_deepseek_receipts.py. No-op for today's schema but cheap insurance for the next contributor who adds 'format'. Regression tests: * New scripts/math-first/test_require_math_evidence.py covers ten classification cases plus the actual --staged regression: it spins up a temp git repo, stages a math-track file + a receipt, invokes the script with --staged, and asserts exit 0. Without the fix this case fails, demonstrating the bug end-to-end. * math-check.yml runs the new self-tests in CI. Docs: * docs/math-first-tooling.md: document the --staged contract, why always_run + pass_filenames: false is necessary, and how to run the new self-tests. Co-Authored-By: Allaun Silverfox <bigdataiscoming+9i37y6j2@protonmail.com>
88 lines
2.8 KiB
JSON
88 lines
2.8 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"$id": "https://github.com/allaunthefox/Research-Stack/shared-data/schemas/claims-registry.schema.json",
|
|
"title": "Research Stack Mathematical Claim Registry",
|
|
"description": "Schema for claims.yaml at the repo root. Tracks the rigor level of every mathematical claim the stack stands behind, plus the Lean proof and/or DeepSeek review receipts that back it. See docs/math-first-tooling.md.",
|
|
"type": "object",
|
|
"required": ["claims"],
|
|
"additionalProperties": false,
|
|
"properties": {
|
|
"claims": {
|
|
"type": "array",
|
|
"minItems": 1,
|
|
"items": { "$ref": "#/$defs/claim" }
|
|
}
|
|
},
|
|
"$defs": {
|
|
"claim": {
|
|
"type": "object",
|
|
"required": ["id", "title", "status"],
|
|
"additionalProperties": false,
|
|
"properties": {
|
|
"id": {
|
|
"type": "string",
|
|
"pattern": "^[a-z0-9][a-z0-9-]*$",
|
|
"description": "Stable kebab-case slug. Must remain unique across the registry."
|
|
},
|
|
"title": {
|
|
"type": "string",
|
|
"minLength": 1,
|
|
"description": "One-line natural-language statement of the claim."
|
|
},
|
|
"status": {
|
|
"type": "string",
|
|
"enum": ["conjecture", "verified-by-ai", "formally-proven", "published"],
|
|
"description": "Current rigor level for the claim."
|
|
},
|
|
"lean": {
|
|
"type": "string",
|
|
"minLength": 1,
|
|
"description": "Optional repo-relative Lean source file or `theorem` symbol carrying the proof obligation."
|
|
},
|
|
"review_receipts": {
|
|
"type": "array",
|
|
"uniqueItems": true,
|
|
"items": {
|
|
"type": "string",
|
|
"pattern": "\\.receipt\\.json$",
|
|
"description": "Repo-relative path to a DeepSeek review receipt."
|
|
}
|
|
},
|
|
"sources": {
|
|
"type": "array",
|
|
"uniqueItems": true,
|
|
"items": {
|
|
"type": "string",
|
|
"minLength": 1,
|
|
"description": "Repo-relative path or external citation supporting the claim."
|
|
}
|
|
},
|
|
"notes": {
|
|
"type": "string",
|
|
"description": "Free-form context. Keep short."
|
|
}
|
|
},
|
|
"allOf": [
|
|
{
|
|
"if": {
|
|
"required": ["status"],
|
|
"properties": { "status": { "const": "verified-by-ai" } }
|
|
},
|
|
"then": {
|
|
"required": ["review_receipts"],
|
|
"properties": {
|
|
"review_receipts": { "minItems": 1 }
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"if": {
|
|
"required": ["status"],
|
|
"properties": { "status": { "const": "formally-proven" } }
|
|
},
|
|
"then": { "required": ["lean"] }
|
|
}
|
|
]
|
|
}
|
|
}
|
|
}
|