Skip to content

feat(repo)!: retire the summarizer package and LLM symbol-summary feature#284

Open
theagenticguy wants to merge 1 commit into
mainfrom
chore/retire-summarizer
Open

feat(repo)!: retire the summarizer package and LLM symbol-summary feature#284
theagenticguy wants to merge 1 commit into
mainfrom
chore/retire-summarizer

Conversation

@theagenticguy

Copy link
Copy Markdown
Owner

What

Retires the LLM code-summarization capability end to end. A capable coding agent regenerates task-conditioned summaries better than an index-time generic summary, so OpenCodeHub now hands agents deterministic structure (locations, edges, blast-radius, owners, license facts) and leaves prose to the agent. Removing summaries also drops the one non-deterministic ingestion phase, so every OpenCodeHub output is now re-derivable.

Removed (BREAKING)

  • @opencodehub/summarizer package — deleted entirely.
  • Ingestion summarize phase — removed from the default phase set.
  • Storage — the symbol_summaries table + DDL, SymbolSummaryRow, and the four SymbolSummary* ITemporalStore methods (bulkLoad / lookup / lookupByNode / count).
  • Retrieval — MCP query and CLI query summary-fusion (the join, the summary / signatureSummary fields, the summaries_joined probe).
  • CLI flagscodehub analyze --summaries / --no-summaries / --max-summaries / --summary-model (and the CODEHUB_BEDROCK_SUMMARIES / CODEHUB_BEDROCK_DISABLED env vars); codehub wiki --llm / --max-llm-calls / --llm-model. codehub wiki is now deterministic-only.
  • Deps — the now-orphaned @aws-sdk/client-bedrock-runtime from @opencodehub/ingestion and @opencodehub/wiki.
  • Docs/config — the dedicated summarization-and-fusion.md architecture page, ~15 adjacent doc references, the tsconfig project refs, and the summarizer commitlint scope.

Determinism is unaffected

Summaries never entered graphHash / packHash (see storage/interface.ts"Summaries never participate in [the hash]"), so the determinism + cross-adapter parity contract is unchanged. The parity suite stays green.

Notable

The embeddings phase gains a direct dep on confidence-demote to preserve its canonical last-in-pipeline ordering (it must observe the final reconciled graph). That ordering previously arrived transitively via the now-removed summarize phase; pinning it directly is behavior-preserving and covered by the phase-order regression test.

Verification

  • Full test suite green: 0 failures across all 20 packages, including the graphHash parity suite.
  • biome check, typecheck (CI filter, docs excluded per ci.yml), and banned-strings all pass.
  • Pre-push gate (typecheck + test + verdict) passed on push.

Diff: 72 files, +145 / −8266.

…ture

Removes the LLM code-summarization capability end to end. A capable coding
agent regenerates task-conditioned summaries better than an index-time
generic summary, so OpenCodeHub now hands agents deterministic structure
(locations, edges, blast-radius, owners, license facts) and leaves prose to
the agent. Removing summaries also drops the one non-deterministic ingestion
phase, so every OpenCodeHub output is now re-derivable.

BREAKING CHANGE: removes the `@opencodehub/summarizer` package, the ingestion
`summarize` phase, the `symbol_summaries` storage table + SymbolSummaryRow
type + the four SymbolSummary ITemporalStore methods, MCP + CLI query
summary-fusion, the `codehub analyze` flags `--summaries` / `--no-summaries`
/ `--max-summaries` / `--summary-model` (and `CODEHUB_BEDROCK_SUMMARIES` /
`CODEHUB_BEDROCK_DISABLED` env vars), and the `codehub wiki` `--llm` /
`--max-llm-calls` / `--llm-model` flags. `codehub wiki` is now
deterministic-only.

Notes:
- Summaries never entered graphHash/packHash, so the determinism + parity
  contract is unchanged (parity suite stays green).
- The embeddings phase gains a direct dep on `confidence-demote` to preserve
  its canonical last-in-pipeline ordering (previously arrived transitively
  via summarize).
- Drops the now-orphaned `@aws-sdk/client-bedrock-runtime` dependency from
  `@opencodehub/ingestion` and `@opencodehub/wiki`.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant