Preserve mathematical notation in semantic extraction

[hopstreax]

Summary

• Preserve mathematical expressions in synthesized semantic rationales using the source's original LaTeX notation.
• Document the math/LaTeX preservation contract in the canonical extraction spec and regenerate the platform references/snapshots.
• Add regression coverage for prompt/spec parity, extraction preservation, and JSON parsing of LaTeX notation.

Testing

• python -m pytest tests/test_llm_backends.py tests/test_llm_parser.py — 120 passed
• python -m tools.skillgen --check — passed
• git diff --check — passed

Closes #3560

[graphify-labs]

Graphify reviewed this change.

Looks safe to merge — no coupling regressions and no blocking issues, checked against the code graph (not a self-assessment).

---

Graphify review — findings

Adds guidance across the extraction prompt and all per-agent extraction-spec.md skill files instructing the model to preserve source math in original LaTeX notation ($...$/$$...$$, commands like \sum) when synthesizing rationale, rather than paraphrasing it into words, and to escape backslashes in the emitted JSON. Updates the expected-output fixtures for the vscode/kilo/copilot skill specs to match, and refreshes the corresponding backend/parser test rationale strings.

No blocking issues surfaced. 15 lower-confidence candidates did not survive cross-model review.

Analysis details — impact, health, verification

Impact & health

Graphify review

Impact — 961 functions depend on the 380 functions this change touches.

Health — this change adds coupling hotspots:

• new: deduplicate_entities() — 76 callers, 24 callees
• new: build_merge() — 76 callers, 14 callees
• new: extract_files_direct() — 18 callers, 20 callees
• new: build() — 52 callers, 6 callees
• new: _call_claude_cli() — 33 callers, 9 callees
• new: extract_corpus_parallel() — 26 callers, 11 callees
• new: dispatch_command() — 2 callers, 124 callees
• new: _extract_with_adaptive_retry() — 22 callers, 10 callees
• …and 16 more — each is listed as a finding

Verification — 961 functions in the blast radius were not formally verified this run (proofs are advisory here).

Gate & verification

graphify gate

PASS — objectively clean (no health regressions, tests not run — proofs not run this pass (advisory)). Grounded, not self-assessed.

Advisory (not blocking):

• verification_scope: 627 function(s) in the blast radius were not formally verified this run

Test selection

Test selection

275 of 275 test file(s) selected (100%) via static blast radius.

Escalated to a full run for safety — the selection is not trustworthy on its own (see below). CI should run the whole suite.

• tests/test_affected_cli.py — full-run-safety
• tests/test_affected_member_seed.py — full-run-safety
• tests/test_agents_platform.py — full-run-safety
• tests/test_analyze.py — full-run-safety
• tests/test_anthropic_custom_endpoint.py — full-run-safety
• tests/test_antigravity_install.py — full-run-safety
• tests/test_apm_fallback_version.py — full-run-safety
• tests/test_architecture_doc.py — full-run-safety
• tests/test_astro_extraction.py — full-run-safety
• tests/test_astro_import_ids.py — full-run-safety
• tests/test_atomic_canvas_export.py — full-run-safety
• tests/test_atomic_version_stamp.py — full-run-safety
• tests/test_atomic_writes.py — full-run-safety
• tests/test_backend_env_isolation.py — impact, full-run-safety
• tests/test_backend_extras.py — impact, full-run-safety
• tests/test_benchmark.py — full-run-safety
• tests/test_benchmark_raw_graph.py — full-run-safety
• tests/test_build.py — impact, full-run-safety
• tests/test_build_merge_dedup_scope.py — impact, full-run-safety
• tests/test_build_merge_hyperedges_and_prune.py — impact, full-run-safety
• tests/test_build_merge_shrink_guard.py — impact, full-run-safety
• tests/test_builtin_global_type_refs.py — full-run-safety
• tests/test_cache.py — full-run-safety
• tests/test_callflow_html.py — full-run-safety
• tests/test_cargo_introspect.py — full-run-safety
• tests/test_carried_hyperedge_remap.py — impact, full-run-safety
• tests/test_case_sensitive_resolution.py — full-run-safety
• tests/test_charmap_encoding.py — impact, full-run-safety
• tests/test_chunking.py — impact, full-run-safety
• tests/test_cjs_module_extension.py — full-run-safety
• tests/test_claude_cli_backend.py — impact, full-run-safety
• tests/test_claude_md.py — full-run-safety
• tests/test_cli_broken_pipe.py — full-run-safety
• tests/test_cli_export.py — full-run-safety
• tests/test_cli_help.py — full-run-safety
• tests/test_cluster.py — full-run-safety
• tests/test_codebuddy.py — full-run-safety
• tests/test_community_hub_labels.py — full-run-safety
• tests/test_community_labels_skill.py — full-run-safety
• tests/test_confidence.py — full-run-safety
• tests/test_corrupt_graph_json.py — impact, full-run-safety
• tests/test_cpp_nested_and_cli.py — full-run-safety
• tests/test_cpp_objc_cross_file_calls.py — full-run-safety
• tests/test_cpp_preprocess.py — full-run-safety
• tests/test_cross_extension_reexport_self_cycle.py — impact, full-run-safety
• tests/test_cross_language_call_resolution.py — full-run-safety
• tests/test_cross_repo_member_calls.py — full-run-safety
• tests/test_cross_repo_shared_types.py — full-run-safety
• tests/test_csharp_call_site_generic_args.py — full-run-safety
• tests/test_csharp_enum_members.py — full-run-safety
• … and 225 more

non-code file(s) changed (graphify/skills/agents/references/extraction-spec.md, graphify/skills/amp/references/extraction-spec.md, graphify/skills/claude/references/extraction-spec.md, graphify/skills/copilot/references/extraction-spec.md, graphify/skills/droid/references/extraction-spec.md …) → running the full suite for safety (a code graph can't see config/fixture/data deps)

changed code file(s) with no mapped test (graphify/skills/agents/references/extraction-spec.md, graphify/skills/amp/references/extraction-spec.md, graphify/skills/claude/references/extraction-spec.md, graphify/skills/copilot/references/extraction-spec.md, graphify/skills/droid/references/extraction-spec.md …) — a coverage gap or a missing link — running the full suite rather than only the selected tests

Selection is safe under the controlled-regression assumption; always-run tests + a periodic full run are the backstops. Advisory — it never changes the check verdict.

· 24 more finding(s) on lines outside this diff (see the check run).