Post-rename cleanup from doc audit (4 fixes, 10 files, ±21)#1
Merged
Conversation
Found four issues during a fresh-user docs walkthrough: 1. `pnpm test` failed on Node 20 / 22.0–22.5 because the test script used `--experimental-strip-types` (introduced in 22.6). The flag is redundant when tsx is already loaded via `--import tsx`, so drop it. CI passes either way (it bypasses the script with explicit args), but the documented `pnpm test` now works on the supported Node range. 2. EXAMPLES.md §1 "Hello Augur" claimed `trace.decision.strategy → "hybrid"` for query `"vector database"`, but two-token queries correctly route to keyword. Bumping the example to a 6-token natural query that does route to hybrid as advertised. 3. docker-compose.yml referenced `pnpm --filter dashboard dev` after the rebrand renamed the package to `@augur/dashboard`. Fixed. 4. Brand consistency: my earlier rename swept `QueryBrain` and `querybrain` but missed UPPERCASE env vars `QUERYBRAIN_API_KEY`, `QUERYBRAIN_ADAPTER`, `QUERYBRAIN_EMBEDDER`, `QUERYBRAIN_URL` across server/cli.ts, the dashboard, docker-compose, API_REFERENCE.md, and DEVELOPMENT_GUIDE.md. Renamed to AUGUR_*. Defaults still apply, so old deployments work until they upgrade. Verified: - pnpm -r --filter './packages/*' build clean - pnpm test now passes (12/12) - "best vector database for production" routes hybrid live - AUGUR_API_KEY enforces auth: 401 without, 200 with correct key Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Per follow-up: prefer `const augr = new Augur()` over `const qb = ...`
(which was a leftover abbreviation from QueryBrain).
Sed `\bqb\b` → `augr` across:
- README.md, EXAMPLES.md, API_REFERENCE.md, packages/core/README.md
- packages/core/src/augur.ts (doctring), augur.test.ts
- examples/basic-search/index.ts, custom-adapter/index.ts
- packages/server/src/server.ts (internal var)
- DEVELOPMENT_GUIDE.md (just the one variable use, line 125)
Intentionally NOT changed:
- DEVELOPMENT_GUIDE.md DB name `postgres://localhost/qb` (different category)
- DEVELOPMENT_GUIDE.md reverse-proxy paths `/api/qb/*` and `/qb/*`
(full word `augur` reads better there; punt as a separate cleanup)
Verified:
- pnpm -r build clean
- pnpm test passes 12/12
- example-basic-search produces same output
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
willgitdata
commented
May 7, 2026
| import { TraceView } from "@/components/TraceView"; | ||
|
|
||
| const QB = process.env.QUERYBRAIN_URL ?? "http://localhost:3001"; | ||
| const QB = process.env.AUGUR_URL ?? "http://localhost:3001"; |
Owner
Author
There was a problem hiding this comment.
you forgot to change the "QB" variable. Fix this for augur's setup and abbreviations.
Owner
Author
There was a problem hiding this comment.
Fixed in 9475fad — renamed QB → AUGR in this file. (Earlier sed was case-sensitive lowercase, missed the SCREAMING_CASE const.)
willgitdata
commented
May 7, 2026
| import { ResultList } from "@/components/ResultList"; | ||
|
|
||
| const QB = process.env.QUERYBRAIN_URL ?? "http://localhost:3001"; | ||
| const QB = process.env.AUGUR_URL ?? "http://localhost:3001"; |
Owner
Author
There was a problem hiding this comment.
forgot this QB as well.
Owner
Author
There was a problem hiding this comment.
Fixed in 9475fad — renamed QB → AUGR in this file. (Earlier sed was case-sensitive lowercase, missed the SCREAMING_CASE const.)
Per PR review feedback. Earlier sed used \bqb\b (lowercase) and missed the SCREAMING_CASE QB const used as a base-URL holder in the two client components. Renaming to AUGR to mirror the new augr variable convention while keeping the const casing. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
5 tasks
willgitdata
added a commit
that referenced
this pull request
May 8, 2026
…ranker Implements 10 fixes from a critical code review on the publish-ready SDK. Each item is independently shippable; this lands them as one coordinated bump because several feed each other (the eval smoke test exercises the new fusion module; the explicit-reranker breaking change needs MIGRATING.md to land at the same time). #1 Smoke eval harness — 16-doc / 12-query synthetic fixture with a regression floor (NDCG@10 > 0.65 on the stub stack). Runs in <50 ms as part of `pnpm test`. The full BEIR + 504-query eval stays where it already lives — git history — for "did this tweak win?" measurement. #2 Extract pure helpers to `fusion.ts` (composeFilter, pickVectorWeight, weightedRrfFuse, adaptWeightByConfidence, topGapNormalized, clamp) + 31 unit tests. Each empirical threshold is now annotated with what it was tuned against. #3 autoLanguageFilter integration tests — OFF default, ON for non-English, user-filter override wins, soft-fallback when the filtered pool empties. #4 Basic-search example wires the recommended stack: LocalEmbedder + LocalReranker + MetadataChunker(SentenceChunker) + InMemoryAdapter({ useStemming: true }). Matches the README's headline configuration so users copying from "hello world" land on the auto path that produces NDCG@10 = 0.920. #5 PineconeAdapter mocked-fetch tests (13 tests). Pins the wire format (URL, method, auth header, body shape, response decode) so refactors can't silently regress one of the three production adapters. Previously had zero coverage. #6 Ad-hoc scratch adapter cache — bounded LRU keyed by a deterministic fingerprint of (id, content). Repeat searches over the same `req.documents` skip re-chunking + re-embedding. Tunable via `adHocCacheSize` (default 8; set 0 to disable). #7 **BREAKING** Drop `HeuristicReranker` as silent default. The previous default did almost nothing while emitting a "yes I rerank" line in the trace. Default is now `null`; pass `new LocalReranker()` (or any provider's reranker) explicitly to keep cross-encoder voting on. Documented in MIGRATING.md. #8 MIGRATING.md — covers every BREAKING change in 0.2 with smallest-diff examples; non-breaking adoptions documented separately. #9 SemanticChunker tests (8 tests) — boundary detection, maxSize cap, async-only API, metadata propagation. Was the only chunker without coverage. #10 Magic-number provenance documented in `router.ts` and `fusion.ts`. Every threshold (≤2 / ≤6 word counts, 0.6 ambiguity floor, 800 ms latency floor, k=60 RRF, ±0.20 shift, 0.10–0.90 weight clamp, 0.3/0.4/0.5/0.7 priors) now records what it's tuned against and what's load-bearing vs negotiable. Test count: 100 → 163. Build green; full eval still ships against the published packages, not against the smoke fixture. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
willgitdata
added a commit
that referenced
this pull request
May 8, 2026
Round 1 left two critical lying-trace bugs and a handful of architectural papercuts. This commit clears the table. #1 (critical) Router no longer lies about reranking when no reranker is configured. `Router.decide` gained an optional `hasReranker` parameter; `HeuristicRouter` plumbs it through to `shouldRerank` and forces `reranked: false` when absent. The trace now records "reranking skipped (no reranker configured)" instead of pretending the cross-encoder fired. Augur passes `this.reranker !== null`. Default is `true` so existing third-party Router implementations keep working. #2 (critical) `SearchTrace` declares the four fields that augur.ts attaches at runtime: `adHoc`, `adHocCacheHit`, `autoLanguageFilter`, `autoLanguageFilterDropped`. `Tracer.finish` opts widened to `Omit<SearchTrace, "id"|"query"|"startedAt"|"totalMs"|"spans">` so adding a SearchTrace field propagates automatically. Tests drop their `as unknown as` casts. #3 (high) PgVectorAdapter mocked-fetch tests (14 tests). Pin SQL shape, INSERT batching at 200/round-trip, parameter renumbering across filter clauses, identifier-validation guard against `; DROP TABLE`, **and a filter-key SQL-injection regression test** — the JSON-path quote-doubling defense gets explicit coverage. #4 (high) Adapter trace-string format change reverted. `trace.adapter` is always the bare adapter name; ad-hoc / cache-hit signals surface as the new structured boolean fields from #2. No more "in-memory (ad-hoc, cached)" string parsing. #5 (high) `fingerprintDocs` extracted to `fingerprint.ts` with 10 direct unit tests covering reorder, byte-change, prefix-equal corpora, id|content boundary, doc-record boundary, empty list, unicode, and the output format contract. #6 (medium) Async chunkers no longer pretend to be `Chunker`s. Introduced an explicit `AsyncChunker` interface; `SemanticChunker`, `Doc2QueryChunker`, `ContextualChunker` implement it (no longer Chunker). The runtime traps in their throwing `chunk()` methods are gone — the type system catches misuse at compile time. APIs that accept either flavor (`AugurOptions.chunker`, all chunker `base` fields, `chunkDocument`) now use `Chunker | AsyncChunker`. `MetadataChunker` keeps its dual sync+async path with a runtime guard for the user-opted-in case where its base is async. #7 (medium) `StubEmbedder` consolidated into `packages/core/src/test-fixtures.ts`. Excluded from the published package via tsconfig. Three duplicated copies dropped. #8 (low) `eval-smoke.test.ts` header explicitly distinguishes the synthetic-fixture smoke test (structural) from the BEIR / 504-query eval that produced the README's NDCG@10 = 0.920 numbers (preserved at git `feffc73^`, runs in ~30 min). #9 (low) `BaseAdapter` JSDoc rewritten as the canonical "starting point for custom adapters" comment, including the RRF / capability / `searchHybrid` override guidance. `AsyncChunker` added to public exports. #10 (low) `examples/basic-search/index.ts` header documents the `npm i @huggingface/transformers` requirement for users copying the file out of the repo. Test count: 163 → 191 (+28). Build green; published-package contents verified clean (`find dist -name "test-fixtures*"` → empty, `find dist -name "*.test.*"` → empty). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
willgitdata
added a commit
that referenced
this pull request
May 11, 2026
Post-rename cleanup from doc audit (4 fixes, 10 files, ±21)
willgitdata
added a commit
that referenced
this pull request
May 11, 2026
…ranker Implements 10 fixes from a critical code review on the publish-ready SDK. Each item is independently shippable; this lands them as one coordinated bump because several feed each other (the eval smoke test exercises the new fusion module; the explicit-reranker breaking change needs MIGRATING.md to land at the same time). #1 Smoke eval harness — 16-doc / 12-query synthetic fixture with a regression floor (NDCG@10 > 0.65 on the stub stack). Runs in <50 ms as part of `pnpm test`. The full BEIR + 504-query eval stays where it already lives — git history — for "did this tweak win?" measurement. #2 Extract pure helpers to `fusion.ts` (composeFilter, pickVectorWeight, weightedRrfFuse, adaptWeightByConfidence, topGapNormalized, clamp) + 31 unit tests. Each empirical threshold is now annotated with what it was tuned against. #3 autoLanguageFilter integration tests — OFF default, ON for non-English, user-filter override wins, soft-fallback when the filtered pool empties. #4 Basic-search example wires the recommended stack: LocalEmbedder + LocalReranker + MetadataChunker(SentenceChunker) + InMemoryAdapter({ useStemming: true }). Matches the README's headline configuration so users copying from "hello world" land on the auto path that produces NDCG@10 = 0.920. #5 PineconeAdapter mocked-fetch tests (13 tests). Pins the wire format (URL, method, auth header, body shape, response decode) so refactors can't silently regress one of the three production adapters. Previously had zero coverage. #6 Ad-hoc scratch adapter cache — bounded LRU keyed by a deterministic fingerprint of (id, content). Repeat searches over the same `req.documents` skip re-chunking + re-embedding. Tunable via `adHocCacheSize` (default 8; set 0 to disable). #7 **BREAKING** Drop `HeuristicReranker` as silent default. The previous default did almost nothing while emitting a "yes I rerank" line in the trace. Default is now `null`; pass `new LocalReranker()` (or any provider's reranker) explicitly to keep cross-encoder voting on. Documented in MIGRATING.md. #8 MIGRATING.md — covers every BREAKING change in 0.2 with smallest-diff examples; non-breaking adoptions documented separately. #9 SemanticChunker tests (8 tests) — boundary detection, maxSize cap, async-only API, metadata propagation. Was the only chunker without coverage. #10 Magic-number provenance documented in `router.ts` and `fusion.ts`. Every threshold (≤2 / ≤6 word counts, 0.6 ambiguity floor, 800 ms latency floor, k=60 RRF, ±0.20 shift, 0.10–0.90 weight clamp, 0.3/0.4/0.5/0.7 priors) now records what it's tuned against and what's load-bearing vs negotiable. Test count: 100 → 163. Build green; full eval still ships against the published packages, not against the smoke fixture. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
willgitdata
added a commit
that referenced
this pull request
May 11, 2026
Round 1 left two critical lying-trace bugs and a handful of architectural papercuts. This commit clears the table. #1 (critical) Router no longer lies about reranking when no reranker is configured. `Router.decide` gained an optional `hasReranker` parameter; `HeuristicRouter` plumbs it through to `shouldRerank` and forces `reranked: false` when absent. The trace now records "reranking skipped (no reranker configured)" instead of pretending the cross-encoder fired. Augur passes `this.reranker !== null`. Default is `true` so existing third-party Router implementations keep working. #2 (critical) `SearchTrace` declares the four fields that augur.ts attaches at runtime: `adHoc`, `adHocCacheHit`, `autoLanguageFilter`, `autoLanguageFilterDropped`. `Tracer.finish` opts widened to `Omit<SearchTrace, "id"|"query"|"startedAt"|"totalMs"|"spans">` so adding a SearchTrace field propagates automatically. Tests drop their `as unknown as` casts. #3 (high) PgVectorAdapter mocked-fetch tests (14 tests). Pin SQL shape, INSERT batching at 200/round-trip, parameter renumbering across filter clauses, identifier-validation guard against `; DROP TABLE`, **and a filter-key SQL-injection regression test** — the JSON-path quote-doubling defense gets explicit coverage. #4 (high) Adapter trace-string format change reverted. `trace.adapter` is always the bare adapter name; ad-hoc / cache-hit signals surface as the new structured boolean fields from #2. No more "in-memory (ad-hoc, cached)" string parsing. #5 (high) `fingerprintDocs` extracted to `fingerprint.ts` with 10 direct unit tests covering reorder, byte-change, prefix-equal corpora, id|content boundary, doc-record boundary, empty list, unicode, and the output format contract. #6 (medium) Async chunkers no longer pretend to be `Chunker`s. Introduced an explicit `AsyncChunker` interface; `SemanticChunker`, `Doc2QueryChunker`, `ContextualChunker` implement it (no longer Chunker). The runtime traps in their throwing `chunk()` methods are gone — the type system catches misuse at compile time. APIs that accept either flavor (`AugurOptions.chunker`, all chunker `base` fields, `chunkDocument`) now use `Chunker | AsyncChunker`. `MetadataChunker` keeps its dual sync+async path with a runtime guard for the user-opted-in case where its base is async. #7 (medium) `StubEmbedder` consolidated into `packages/core/src/test-fixtures.ts`. Excluded from the published package via tsconfig. Three duplicated copies dropped. #8 (low) `eval-smoke.test.ts` header explicitly distinguishes the synthetic-fixture smoke test (structural) from the BEIR / 504-query eval that produced the README's NDCG@10 = 0.920 numbers (preserved at git `4d52844^`, runs in ~30 min). #9 (low) `BaseAdapter` JSDoc rewritten as the canonical "starting point for custom adapters" comment, including the RRF / capability / `searchHybrid` override guidance. `AsyncChunker` added to public exports. #10 (low) `examples/basic-search/index.ts` header documents the `npm i @huggingface/transformers` requirement for users copying the file out of the repo. Test count: 163 → 191 (+28). Build green; published-package contents verified clean (`find dist -name "test-fixtures*"` → empty, `find dist -name "*.test.*"` → empty). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
6 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Walked the docs end-to-end as a fresh user (only the README + EXAMPLES + API_REFERENCE + DEVELOPMENT_GUIDE) and found four issues. This PR fixes all four. No semantic / behavioral changes — only doc accuracy and brand consistency.
Changes
pnpm testwas broken on Node ≤22.5 (packages/core/package.json). The test script usednode --experimental-strip-types, which was introduced in 22.6, butenginessays ≥20. The flag is redundant when--import tsxis present, so drop it. CI passed either way because the workflow uses explicit args, but the documentedpnpm testcommand now works on the supported Node range.EXAMPLES.md §1 doc bug (EXAMPLES.md). Comment claimed
trace.decision.strategy → "hybrid"for query"vector database", but two-token queries correctly route tokeyword. The router is right; the example query was wrong. Replaced with"best vector database for production"(6 tokens, routes hybrid live).docker-compose.yml referenced the pre-rebrand dashboard package name (docker-compose.yml#L32) —
pnpm --filter dashboard devno longer matches anything. Updated to@augur/dashboard.Brand consistency:
QUERYBRAIN_*env vars survived the rebrand. The earlier sed sweep matchedQueryBrain(PascalCase) andquerybrain(lowercase) but missedQUERYBRAIN_API_KEY,QUERYBRAIN_ADAPTER,QUERYBRAIN_EMBEDDER,QUERYBRAIN_URLacross:AUGUR_URL)All defaults are unchanged, so the in-memory / hash-embedder happy path was working both before and after — but anyone setting an API key or pointing at a real adapter would have been confused by the brand-vs-env-var mismatch.
Routing impact
None. No code in
packages/core/src/routing/is touched. Doc fix #2 changes the example query to one whose routing matches the existing comment.Testing
pnpm -r --filter './packages/*' buildcleanpnpm typecheckclean (already passing in CI)pnpm test— now passes (was broken pre-PR): 12/12 router + augur tests green"best vector database for production"returnsdecision.strategy === "hybrid"from the running server with the seeded corpusAUGUR_API_KEY=test-keyreturns 401 without the header and 200 withx-api-key: test-key— exactly as the renamed docs sayNotes for reviewer
pnpm format— that produces a 43-file pure-formatting commit (Prettier vs. the repo's existing style), which felt orthogonal to this audit. Worth doing as its own follow-up commit if you want a clean baseline.qbvariable in README/example code (legacy abbreviation for "QueryBrain"). It still works; rename it if you want full brand consistency in code samples.🤖 Generated with Claude Code