Conversation
![graphify-labs[bot]](https://avatars.githubusercontent.com/in/4356270?s=60&v=4){kind=small}
There was a problem hiding this comment.
Graphify reviewed this change.
Worth a look — the grounded gate found no coupling regressions or blocking issues, but 3 advisory finding(s) below merit a look before merge.
Formal verification. No changes could be formally verified in this run.
Graphify review — findings
Reworks community-label sampling to be size-aware: when top_k is None (now the default), _community_label_lines picks each community's representative count via _adaptive_sample_size (12–32 by membership), ranks members by god-node status, internal degree, global degree, then id, and applies a per-source-file diversity cap with a backfill pass so single-file communities still fill their quota; passing an explicit top_k keeps the old fixed-cap behaviour. Replaces the fixed count-based batching with _pack_label_batches, which greedily packs communities into batches bounded by both batch_size and an _LABEL_MAX_PROMPT_TOKENS (8000) budget estimated via _estimate_text_tokens, keeping largest-first order and emitting an oversized community as its own single-item batch rather than dropping it. Hoists the naming prompt into the shared _LABEL_PROMPT_PREAMBLE constant used by both the batch call and the token estimate.
Worth a look
- label_communities default top_k changed from fixed cap to adaptive sampling —
graphify/llm.py:3551· Escalate · medium- agreed by 2 of 2 members but NOT verified (no proof, no reproducing execution) — consensus is not a verdict; needs human review
- label_communities top_k default changed from int to None alters public behavior —
graphify/llm.py:3551· Escalate · medium- agreed by 2 of 2 members but NOT verified (no proof, no reproducing execution) — consensus is not a verdict; needs human review
- New parameter inserted before existing positional argument —
graphify/llm.py:3658· Escalate · medium- agreed by 2 of 2 members but NOT verified (no proof, no reproducing execution) — consensus is not a verdict; needs human review
Analysis details — impact, health, verification
Impact & health
Graphify review
Impact — 933 functions depend on the 281 functions this change touches.
Health — this change adds coupling hotspots:
- new:
deduplicate_entities()— 77 callers, 24 callees - new:
build_merge()— 76 callers, 14 callees - new:
extract_files_direct()— 17 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, 125 callees - new:
_extract_with_adaptive_retry()— 22 callers, 10 callees - …and 16 more — each is listed as a finding
Verification — 933 functions in the blast radius were not formally verified this run (proofs are advisory here).
Health delta baseline: last indexed commit 26b02b5 (diverged from this PR's base — delta is approximate).
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: 598 function(s) in the blast radius were not formally verified this run
Test selection
Test selection
41 of 286 test file(s) selected (14%) via static blast radius.
tests/test_backend_env_isolation.py— impacttests/test_backend_extras.py— impacttests/test_build.py— impacttests/test_build_merge_dedup_scope.py— impacttests/test_build_merge_hyperedges_and_prune.py— impacttests/test_build_merge_shrink_guard.py— impacttests/test_carried_hyperedge_remap.py— impacttests/test_charmap_encoding.py— impacttests/test_chunking.py— impacttests/test_claude_cli_backend.py— impacttests/test_corrupt_graph_json.py— impacttests/test_cross_extension_reexport_self_cycle.py— impacttests/test_dedup.py— impacttests/test_dedup_remaps_hyperedges.py— impacttests/test_dedup_survivor_richness.py— impacttests/test_evidence_binding.py— impacttests/test_file_slice.py— impacttests/test_global_graph.py— impacttests/test_go_qualified_resolution.py— impacttests/test_hyperedge_member_shapes.py— impacttests/test_image_vision.py— impacttests/test_injection_sentinel_coverage.py— impacttests/test_issue_3472_source_file_collision.py— impacttests/test_label_retry.py— impacttests/test_labeling.py— impact, changed-testtests/test_llm_backends.py— impacttests/test_llm_parser.py— impacttests/test_llm_parser_reasoning.py— impacttests/test_no_dedup_flag.py— impacttests/test_non_string_node_ids.py— impacttests/test_ollama.py— impacttests/test_ollama_retry_cap.py— impacttests/test_oversized_document_slicing.py— impacttests/test_partial_cache.py— impacttests/test_pdf_slicing.py— impacttests/test_pdf_token_estimate.py— impacttests/test_provider_registry.py— impacttests/test_prs.py— impacttests/test_prune_sweeps_orphans.py— impacttests/test_semantic_fragment_sanitize.py— impacttests/test_unverified_semantic_shrink.py— impact
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.
Formal verification
Could not verify: Could not verify \_community\_label\_lines.
The verifier did not have enough to check \_community\_label\_lines, so it is saying so rather than guessing. No false assurance is the whole point.
Guarantee: No guarantee either way, this is an honest abstention, not a pass.
Note: Reason: no capturable inputs from the test suite; property tier: not verifiable: all 200 sampled inputs raised on both versions — the function never executed, so 'no divergence' would be vacuous (mostly TypeError — names the real obstacle, not a sampling gap)
Could not verify: Could not verify generate\_community\_labels.
The verifier did not have enough to check generate\_community\_labels, so it is saying so rather than guessing. No false assurance is the whole point.
Guarantee: No guarantee either way, this is an honest abstention, not a pass.
Note: Reason: no capturable inputs from the test suite; property tier: non-vacuity: domain too small (only 1 distinct inputs exercised, need 3) — 'no divergence' would be near-vacuous
Could not verify: Could not verify \_label\_batch\_with\_retry.
The verifier did not have enough to check \_label\_batch\_with\_retry, so it is saying so rather than guessing. No false assurance is the whole point.
Guarantee: No guarantee either way, this is an honest abstention, not a pass.
Note: Reason: no capturable inputs from the test suite; property tier: not verifiable: all 9 sampled inputs raised on both versions — the function never executed, so 'no divergence' would be vacuous (mostly TypeError — names the real obstacle, not a sampling gap)
Could not verify: Could not verify label\_communities.
The verifier did not have enough to check label\_communities, so it is saying so rather than guessing. No false assurance is the whole point.
Guarantee: No guarantee either way, this is an honest abstention, not a pass.
Note: Reason: no capturable inputs from the test suite; property tier: not verifiable: all 49 sampled inputs raised on both versions — the function never executed, so 'no divergence' would be vacuous (mostly TypeError — names the real obstacle, not a sampling gap)
· 1 grounded finding(s) anchored inline below; 23 more finding(s) on lines outside this diff (see the check run).
| return batches | ||
|
|
||
|
|
||
| def label_communities( |
There was a problem hiding this comment.
label_communities()
22 callers depend on it (afferent coupling).
Grounded coupling-delta finding (deterministic), not an LLM guess.
1 participant
Summary
Fixes #3586 by making community labeling more representative for large communities and safer for large labeling batches.
Changes
Replace the fixed 12-node community sample with size-aware sampling, scaling up to 32 representatives for large communities.
Improve representative selection using:
Add token-aware batching while preserving
batch_sizeas the maximum number of communities per LLM call.Preserve explicit
top_koverrides and backward compatibility.Add regression tests covering adaptive sampling, representative diversity, backfill, and token-aware batching.
Validation
pytest tests/test_labeling.py tests/test_llm_backends.py tests/test_community_hub_labels.py -qgit diff --checkCloses #3586