Issues

• verify: reports '✓ no hallucinations detected' when the symbol check did not run

  bugP2
  manojmallick/sigmap#1007 · Filter by author manojmallick opened on Oct 18, 2026

• ci: supply-chain baseline - 0 of 50 action references SHA-pinned, workflow-level id-token: write, no Dependabot or code scanning

  choreP2
  manojmallick/sigmap#1000 · Filter by author manojmallick opened on Oct 17, 2026

• release: 9 of the last 59 npm releases changed no runtime file, CHANGELOG.md is 16% of every tarball, and CONTRIBUTING's test counts are stale

  choreP2release
  manojmallick/sigmap#999 · Filter by author manojmallick opened on Oct 17, 2026

• cli: verify --json is cut at 64 KB when piped, and verify <dir> throws EISDIR

  bugP1
  manojmallick/sigmap#998 · Filter by author manojmallick opened on Oct 17, 2026

• index: zero-config root detection indexes none of Rails' activerecord, actionpack, actionview or activemodel, and the printed grade hides it

  bugP1
  manojmallick/sigmap#997 · Filter by author manojmallick opened on Oct 17, 2026

• typescript: $ names, generic arrows, anonymous default exports and obj.x = function methods are not indexed, and explain gives the wrong fix

  bugP2parser
  manojmallick/sigmap#996 · Filter by author manojmallick opened on Oct 17, 2026

• defaults: the codex adapter writes AGENTS.md past Codex's 32 KiB limit (gin: 43 KB), and a plain mcp install advertises 22 tools, not 7

  adapterbugmcpP2
  manojmallick/sigmap#995 · Filter by author manojmallick opened on Oct 17, 2026

• mcp: mcp install claude and mcp install codex write config the host never reads - claude mcp list and codex mcp list show nothing

  bugmcpP1
  manojmallick/sigmap#994 · Filter by author manojmallick opened on Oct 17, 2026
  1

• determinism: the generated map depends on the checkout path length, and the first run is not a fixed point (gin: 69 to 50 sections)

  bugP1
  manojmallick/sigmap#993 · Filter by author manojmallick opened on Oct 17, 2026

• docs: six published claims an outsider can falsify in one step (per-repo tuning, hidden files, Zenodo data, 61% faster, prompts, 5.9x)

  bugdocumentationP1
  manojmallick/sigmap#992 · Filter by author manojmallick opened on Oct 17, 2026
  1

• verify: compose with tsc and pyright and ship a GitHub Action instead of out-detecting compilers

  enhancementP2
  manojmallick/sigmap#991 · Filter by author manojmallick opened on Oct 17, 2026

• verify: the installed-library index is empty for zod and rxjs, yet the output says 'Grounded against' them

  bugP1
  manojmallick/sigmap#990 · Filter by author manojmallick opened on Oct 17, 2026

• verify: reports 'Grounded' for invented library APIs and undefined calls, and the README says it flags every fabrication

  bugP1
  manojmallick/sigmap#989 · Filter by author manojmallick opened on Oct 17, 2026

• retrieval: pre-registered reranker spike (rank fusion, exact-identifier stage, diversification) - 22 of 24 misses are ranking misses, 11 within the top 20

  benchmarkenhancementP2
  manojmallick/sigmap#985 · Filter by author manojmallick opened on Oct 17, 2026

• benchmark: grow the third-party corpus and compare changes pairwise - 83 tasks cannot see a 5-point retrieval change

  benchmarkenhancementP2
  manojmallick/sigmap#984 · Filter by author manojmallick opened on Oct 17, 2026

• benchmark: extraction recall against language-native ground truth (Python ast, Ruby Ripper first) - nothing measures what the extractors find

  benchmarkenhancementP2parser
  manojmallick/sigmap#983 · Filter by author manojmallick opened on Oct 17, 2026
  1

• index: decouple the retrieval index's signature cap from the context file budget (Django public-symbol recall 58% to 95%, hit@5 unchanged)

  enhancementP2parser
  manojmallick/sigmap#982 · Filter by author manojmallick opened on Oct 17, 2026
  1

• graph: add import resolvers for C/C++, PHP, C#, Dart, Vue/Svelte/Astro, Lua, GDScript and Swift (graph reads 8 language families today)

  enhancementP2
  manojmallick/sigmap#980 · Filter by author manojmallick opened on Oct 17, 2026

• epic: close the gap - 2026-10-17 gap analysis (scorecard 59.8/100 vs codebase-memory-mcp 83.2, code-review-graph 66.9)

  benchmarkenhancementP2
  manojmallick/sigmap#978 · Filter by author manojmallick opened on Oct 17, 2026
  2

• growth: distribution plan from the 2026-10-17 gap analysis (traction is the lowest-scoring category)

  choredocumentationP2
  manojmallick/sigmap#977 · Filter by author manojmallick opened on Oct 17, 2026

• benchmark: call-graph accuracy against a compiler-derived reference (SCIP) - no one publishes a non-circular number

  benchmarkenhancementP2
  manojmallick/sigmap#976 · Filter by author manojmallick opened on Oct 17, 2026
  1

• parser: Ruby and C/C++ are Tier 3, and the third-party gate has no Ruby or C/C++ repo

  benchmarkenhancementP2parser
  manojmallick/sigmap#975 · Filter by author manojmallick opened on Oct 17, 2026
  1

• benchmark: run the agent-level A/B live and publish one measured result (the harness has never run)

  benchmarkenhancementP2
  manojmallick/sigmap#974 · Filter by author manojmallick opened on Oct 17, 2026

• benchmark: measured head-to-head - codebase-memory-mcp and code-review-graph on the third-party corpus (extends #678)

  benchmarkenhancementP2
  manojmallick/sigmap#972 · Filter by author manojmallick opened on Oct 17, 2026

• scale: a re-run is as slow as the first run, and a first run on a large repo grades itself D (6%)

  benchmarkenhancementP2
  manojmallick/sigmap#971 · Filter by author manojmallick opened on Oct 17, 2026
  1