1a6b543cc5
* feat(search-lite): token budget + semantic query cache + intent weighting
Adds three additive features to the hybrid search pipeline. All
backward-compatible: existing callers see identical behavior unless they
opt in to the new options.
## 1. Token Budget Enforcement (src/core/search/token-budget.ts)
Cap the cumulative token cost of returned results so search payloads
fit downstream context windows. Greedy top-down walk; preserves caller
ordering; no re-rank. char/4 heuristic for token counting (no
tokenizer dependency \u2014 keeps the bun --compile bundle small).
SearchOpts.tokenBudget \u2014 numeric cap. Default undefined = no-op.
HybridSearchMeta.token_budget = { budget, used, kept, dropped }
HTTP query op: pass `token_budget` param.
## 2. Semantic Query Cache (src/core/search/query-cache.ts + migration v52)
Cache search results keyed by query embedding similarity. HNSW lookup:
`embedding <=> $1 < 0.08` (cosine similarity >= 0.92). Per-source
isolation so multi-source brains don\u2019t bleed. Per-row TTL (default 3600s).
Best-effort writes; all errors swallowed so the cache never breaks the
search hot path.
Migration v52 creates query_cache table with HALFVEC where pgvector >= 0.7;
falls back to VECTOR with the resolved config.embedding_dimensions dim.
New `gbrain cache` CLI: stats / clear --yes / prune.
Config keys: search.cache.enabled / similarity_threshold / ttl_seconds.
HybridSearchMeta.cache = { status, similarity?, age_seconds? }
Routed through new `hybridSearchCached(engine, query, opts)` wrapper;
the operations.ts query op now uses this wrapper so MCP/CLI calls
benefit automatically. Skipped for two-pass walks + non-default
embedding columns where cache semantics don\u2019t hold.
## 3. Zero-LLM Intent Weighting (src/core/search/intent-weights.ts)
Builds on the existing query-intent classifier (4 intents: entity /
temporal / event / general). New weight-adjustment layer applies subtle
per-intent nudges:
entity \u2192 boost keyword RRF + exact slug/title match
temporal \u2192 default recency=on when caller left it unset
event \u2192 boost keyword RRF (rare named entities) + soft recency
general \u2192 no-op (1.0 multipliers everywhere)
All adjustments are SUBTLE (max 1.25x). Caller-explicit options ALWAYS
win \u2014 intent weighting never silently overrides recency / salience.
Default ON; opt out via `opts.intentWeighting = false`. LLM query
expansion (expansion.ts) is still available and opt-in via
`opts.expansion = true` \u2014 it just isn\u2019t the default anymore.
HybridSearchMeta.intent now surfaces classifier output for debugging.
## Tests
test/token-budget.test.ts (10 tests, pure module)
test/intent-weights.test.ts (13 tests, pure module)
test/query-cache.test.ts (12 tests, PGLite)
test/hybrid-search-lite.serial.test.ts (9 tests, PGLite e2e)
Plus 105 pre-existing search tests still pass. `bun run verify` clean.
Co-authored-by: Wintermute <agents@garrytan.com>
* feat(search-mode): MODE_BUNDLES + resolveSearchMode wired into bare hybridSearch
Three named modes (conservative / balanced / tokenmax) that bundle the
search-lite knobs from PR #897 into a single config key. Mode resolution
lives in bare hybridSearch (NOT just the cached wrapper) so eval-replay
and eval-longmemeval — which call bare hybridSearch — test the same
mode-affected behavior as production. See [CDX-5+6] in the plan.
The mode bundle supplies DEFAULTS for intentWeighting, tokenBudget,
expansion, and searchLimit when the caller leaves those undefined.
Per-call SearchOpts and per-key config overrides still win (matches the
v0.31.12 model-tier resolution chain at model-config.ts:resolveModel).
knobsHash() exposes a stable SHA-256 of the resolved knob set; the cache
contamination hotfix (next commit) consumes it to prevent a tokenmax
write from being served to a conservative read.
Three new fields on HybridSearchMeta:
- mode (resolved mode name)
- existing token_budget meta now fires from bare hybridSearch too
Bare hybridSearch now applies tokenBudget at all three return paths
(no-embedding-provider, keyword-only-fallback, main). Previously only
hybridSearchCached enforced budget; eval commands missed it.
Tests: 37 unit cases pin the 3x7 bundle table cell-by-cell, the
resolution chain semantics, knobs hash determinism + cross-mode
separation, and the config-table parser. All 72 search-lite tests pass.
Bisect-friendly: this commit ONLY adds mode resolution. The cache-key
contamination hotfix [CDX-4] is a separate atomic commit (next).
* fix(query-cache): cross-mode contamination hotfix [CDX-4]
PR #897's query_cache keyed rows on sha256(source_id::query_text) only.
A tokenmax search (expansion=on, limit=50) populated a row that a
subsequent conservative call (no expansion, limit=10) read back, serving
the wrong-shape results. This is a real bug in PR #897 today, regardless
of the v0.32.3 mode picker work — Codex caught it in plan review.
Fix:
- Migration v56 adds query_cache.knobs_hash TEXT column + composite
(source_id, knobs_hash, created_at) index. Existing rows have NULL
knobs_hash and are excluded from lookups (silently re-populated with
the right hash on first hit — no orphan data, no destructive migration).
- cacheRowId(query, source, knobsHash) — knobsHash now part of the PK so
a tokenmax write and a conservative write for the same (query, source)
land in distinct rows.
- SemanticQueryCache.lookup({knobsHash}) filters WHERE knobs_hash = $.
- SemanticQueryCache.store({knobsHash}) writes the resolved hash.
- hybridSearchCached threads knobsHash from resolveSearchMode through
every cache call. Cache config (enabled/threshold/TTL) now reads from
the resolved mode bundle, not directly from the config table.
Tests (test/query-cache-knobs-hash.test.ts, 11 cases):
- cacheRowId bifurcates by knobsHash
- Tokenmax write does NOT contaminate conservative lookup
- Three modes coexist as distinct rows for same query
- Legacy NULL-knobs_hash rows are excluded from lookup
- Same-mode write updates in place (no duplicate rows)
All 58 cache + mode tests pass. Migration v56 applies cleanly on a fresh
PGLite brain.
Bisect-friendly: this commit is the cache-key hotfix alone. Mode
resolution wiring lives in the previous commit.
* feat(search-telemetry): in-process rollup writer + search_telemetry table
Migration v57 creates search_telemetry (date, mode, intent, count,
sum_results, sum_tokens, sum_budget_dropped, cache_hit, cache_miss,
first_seen, last_seen). PK (date, mode, intent) caps growth at ~4380
rows/year. Sums + counts only — averages derive at read time so
concurrent ON CONFLICT writes from multiple gbrain processes accumulate
correctly [CDX-17].
In-memory bucket flushed periodically (60s OR 100 calls) + on process
beforeExit/SIGINT/SIGTERM with a 2-second cap. The search hot path NEVER
waits on this write [D2, CDX-19].
Date-bucketed cache_hit / cache_miss columns make hit rate over --days N
derivable [CDX-18]. query_cache.hit_count is a lifetime counter and
can't be sliced by window.
Wired into bare hybridSearch via emitMeta: every search call sync-bumps
a bucket. flush() drains atomically by swapping the map before SQL writes
so a record() during flush lands in the new map.
readSearchStats(engine, {days}) returns the StatsWindow shape that
gbrain search stats consumes (next commit).
Tests: 16 unit cases pin record/flush/read semantics including
ON-CONFLICT-adds-raw-values, concurrent-flush coalescing, cache hit-rate
math, missing-table graceful degradation, and window clamping.
53 migrations apply on a fresh PGLite brain.
* feat(config): add unset + listConfigKeys + readLineSafe helper [CDX-7+8+9]
CDX-8: gbrain config has no unset path today. Required before
`gbrain search modes --reset` can clear search.* overrides.
- BrainEngine.unsetConfig(key) → returns rows deleted (0|1)
- BrainEngine.listConfigKeys(prefix) → exact-literal prefix match
with LIKE-escape on user-supplied % / _ / \ characters
- PGLiteEngine + PostgresEngine implementations
- `gbrain config unset <key>` and `gbrain config unset --pattern <prefix>`
sub-subcommands
CDX-9: readLine has no EOF detection or timeout. Mode-picker plan calls
out "TTY closes mid-prompt → defaults to balanced" but the raw helper
hangs forever. New readLineSafe(prompt, defaultValue, timeoutMs=60s):
- Returns defaultValue on stdin 'end' event
- Returns defaultValue on timeout
- Returns defaultValue on empty Enter
- Non-TTY stdin returns defaultValue immediately (e2e safe)
- Returns trimmed user input otherwise
Exported so install picker (next task) can use it.
Tests: 9 cases pin unset semantics + prefix matcher edge cases
(glob-wildcard escape, sort order, idempotent loop, search.* sweep).
All 53 migrations apply on a fresh PGLite brain.
* feat(init): install-time mode picker + upgrade banner
Install picker (src/commands/init-mode-picker.ts):
- Runs as a phase inside `gbrain init` AFTER engine.initSchema() so DB
config writes work [CDX-7].
- Idempotent: skipped on re-init if search.mode is already set.
- Smart auto-suggestion via recommendModeFor() reads
models.tier.subagent / models.default / OPENAI_API_KEY:
* Opus default/subagent → tokenmax (quality ceiling)
* Haiku subagent → conservative (4K budget keeps cost down)
* No OpenAI key → conservative (no LLM expansion possible)
* Sonnet / unknown → balanced (safe default)
- TTY shows menu via readLineSafe (60s timeout, defaults on EOF/empty).
- Non-TTY auto-selects + emits operator hint:
[gbrain] search mode: X (auto-selected — reason)
[gbrain] To change: gbrain config set search.mode <...>
- --json mode emits structured `{phase: 'search_mode_picker', ...}` event.
- Wired into both initPGLite and initPostgres flows.
Upgrade banner (src/commands/upgrade.ts):
- One-shot stderr banner in runPostUpgrade.
- State persisted via config key `search.mode_upgrade_notice_shown=true`
— fires at most once per install.
- Copy corrected per [CDX-1+2+3]: production query op STILL defaults
expand=true and limit=20. The banner reframes from "behavior is
regressing" to "named modes available + here's how to preserve
exact current shape."
Tests (test/init-mode-picker.test.ts, 16 cases):
- recommendModeFor heuristic for all 4 input shapes
- parseModeInput accepts numeric/named/case-insensitive, rejects garbage
- runModePicker non-TTY auto-selects + writes config
- Idempotent + --force re-prompt + JSON output
- Opus → tokenmax, Haiku → conservative real wiring through engine
* feat(cli): gbrain search modes/stats/tune command
Three sub-subcommands mirroring the gbrain models (v0.31.12) shape:
gbrain search modes [--json]
Read-only routing dashboard. Shows the three mode bundles, the active
mode, and the source of every resolved knob:
cache_enabled = true [override: search.cache.enabled]
tokenBudget = 4000 [mode: conservative]
Plus knob descriptions for legibility.
gbrain search modes --reset [--source <mode>]
Clears every search.* override (NOT search.mode itself). Preserves
the upgrade-notice state key. --source <mode> is a dry-run that
lists what --reset would change without writing — the paved path
[CDX-8] flagged as missing.
gbrain search stats [--days N] [--json]
Observability. Reads the search_telemetry rollup over the window
(clamps to [1, 365]). Prints cache hit rate, mode mix, intent mix,
budget drops, avg results/tokens. JSON output includes
_meta.metric_glossary block per [CDX-25].
gbrain search tune [--apply] [--json]
Recommendation engine. 5 rules cover the bug class:
- Insufficient data → "no_recommendations" status
- Conservative + high budget-drop rate → suggest balanced
- High cache hit rate (>85%) → suggest similarity threshold bump
- Tokenmax + Haiku subagent → suggest balanced (cost mismatch)
- Cache disabled but stats show usage → suggest re-enabling
--apply mutates config via setConfig / unsetConfig with a paste-ready
revert command printed at the end.
Registered in src/cli.ts dispatch table. 17 unit cases pin:
- Dashboard report shape + per-knob source attribution
- --reset preserves search.mode + notice key
- --source dry-run never writes
- stats reads telemetry rollup; --days clamps
- tune recommendation rules fire on real telemetry data
- --apply mutates config
- --help + unknown subcommand exit codes
* feat(eval): metric glossary module + auto-gen METRIC_GLOSSARY.md + CI guard
Single source of truth at src/core/eval/metric-glossary.ts. Every entry
carries 3 fields:
- industry_term (canonical IR/NLP literature name, preserved verbatim)
- eli10 (plain-English a 16-year-old can follow)
- range (numeric range + interpretation)
Covers 4 metric families:
- Retrieval: P@k, R@k, MRR, nDCG@k
- Stability: Jaccard@k, top-1 stability
- Statistical: p-value (paired bootstrap + Bonferroni), 95% CI
- Operational: cache hit rate, avg results/tokens, cost per query, p99 latency
Public surface:
- getMetricGloss(metric) → full entry or null
- eli10For(metric) → plain-English string or null
- buildMetricGlossaryMeta(metrics[]) → {metric → eli10} record for
JSON `_meta.metric_glossary` blocks per [CDX-25]. ONE block per
response, NOT sibling `_gloss` fields on every metric.
- renderMetricGlossaryMarkdown() → deterministic Markdown for the doc
Auto-generation:
scripts/generate-metric-glossary.ts emits docs/eval/METRIC_GLOSSARY.md.
Deterministic (same input → same bytes) so the CI guard can diff.
CI guard:
scripts/check-eval-glossary-fresh.sh regenerates into a temp file and
diffs against the committed doc. Out-of-date doc fails the build.
Wired into `bun run verify` (and therefore `bun run test:full`).
Tests (test/metric-glossary.test.ts, 18 cases):
- Every documented metric is present
- Every entry has all 3 required fields
- Accessors return null on unknown metrics (no throw)
- buildMetricGlossaryMeta silently drops unknown metrics
- renderer output is deterministic across calls
- Renderer groups metrics into 4 sections
docs/eval/METRIC_GLOSSARY.md: 5491 bytes, 124 lines, fresh.
* feat(doctor): search_mode + eval_drift checks + drift-watch module
src/core/eval/drift-watch.ts — curated retrieval watch-list [CDX-6].
Five patterns covering the surface that actually affects retrieval quality:
- src/core/search/ (search pipeline)
- src/core/embedding.ts (embedding shape)
- src/core/chunkers/ (chunk granularity)
- src/core/ai/recipes/anthropic.ts + openai.ts (expansion + embed routing)
- src/core/operations.ts (the query op definition)
Adding to the list is a deliberate act — requires a CHANGELOG line so
coverage grows on purpose, not by accident. Pure functions:
- matchesWatchPattern(path) — trailing-slash = prefix, bare = equality
- filesDriftedSince(repoRoot, sha?) — git diff --name-only wrapper
- watchedFilesDrifted(repoRoot, sha?) — composite
src/commands/doctor.ts — two new checks.
checkSearchMode [CDX-20]: status stays 'ok' (never warns, never docks
health score). Hint in message field. Three branches:
- unset → "search.mode is unset (using balanced fallback). Run
`gbrain search modes` to see what is running and pick a mode."
- mode + no overrides → "Mode: X (no per-key overrides — mode bundle
is canonical)."
- mode + overrides → "Mode: X with N per-key override(s) (k1, k2, …).
To consolidate to the pure mode bundle: gbrain search modes --reset"
Upgrade-notice state key (search.mode_upgrade_notice_shown) is excluded
from the override roster — it's not a knob.
checkEvalDrift [CDX-6]: surfaces uncommitted changes to retrieval-watched
files. Always 'ok'; operator-facing reminder. Names up to 3 drifted files
in the message + paste-ready re-eval command.
Both helpers exported (was: file-private) so tests can pin behavior
without walking the full runDoctor pipeline.
Tests: 12 drift-watch cases + 7 doctor-check cases. Pin watch-list shape,
prefix-vs-equality matcher semantics, missing-repo graceful failure, and
all three search_mode branches.
* feat(eval): --mode flag on longmemeval/replay + run-all + compare
Per-mode --mode flag plumbed into:
- gbrain eval longmemeval --mode <conservative|balanced|tokenmax>
Sets search.mode in the benchmark brain's config table; config is
in PRESERVE_TABLES so resetTables doesn't wipe it between questions.
Mode surfaces in the per-question NDJSON row.
- gbrain eval replay --mode <m> + --compare-limit N
--compare-limit forces a constant K across modes [CDX-13]; without
it, Jaccard@k against the captured baseline measures K-drift, not
quality. Mode is set once before the replay loop.
- NOT cross-modal per [CDX-11]: cross-modal scores OUTPUT against
TASK; it doesn't retrieve. Adding --mode there is theater.
New: gbrain eval run-all orchestrator (src/commands/eval-run-all.ts):
- Sweeps every requested mode × suite combination
- Sequential default per D9; --parallel N opt-in (clamped to mode count)
- Cost guard with split caps [CDX-15+16]:
--budget-usd-retrieval N (default $5)
--budget-usd-answer N (default $20)
Non-TTY refuses with exit 2 unless --yes AND explicit --budget-usd-*
flags pass. TTY refuses without --yes (defense against agent loops).
- estimateRunCost computes per-(suite,mode) breakdown including the
expansion-Haiku surcharge for tokenmax.
- Audit trail: appends to <repo>/.gbrain-evals/eval-results.jsonl
[CDX-23]. Personal brain (~/.gbrain) NEVER touched.
- v0.32.3 ships orchestrator + argv + guard + persist hook.
In-process per-suite invocation is a v0.32.4 follow-up (operator
runs the per-suite CLIs with the documented --mode flag for now;
each completion calls persistRunRecord to log).
New: gbrain eval compare report (src/commands/eval-compare.ts):
- Reads eval-results.jsonl, groups by (suite, mode), renders MD or JSON
- Most-recent (suite, mode, commit) wins when duplicates exist
- JSON output has schema_version=2 + _meta.metric_glossary block per
[CDX-25] (ONE block per response, not sibling _gloss fields)
- _meta.methodology field names the paired-bootstrap + Bonferroni
discipline per [CDX-14] so haters can reproduce
- Missing file → friendly hint pointing at `gbrain eval run-all`
Wired into eval dispatch table in src/commands/eval.ts.
Metric glossary fuzzy fallback: `recall@10` → `recall@k` lookup
(the glossary documents the family; report rows carry specific K
values). Routes through getMetricGloss for every call site.
Tests (42 cases total — all green):
- eval-run-all.test.ts (19): argv parser, cost estimate, guard
semantics for all 4 (over/under × tty/non-tty) shapes, persist hook
NDJSON shape.
- eval-compare.test.ts (5): JSON + MD output shapes, glossary
integration, missing-file graceful, mode filter, most-recent-wins.
- metric-glossary.test.ts (18): unchanged but updated assertions to
cover the fuzzy `@N` → `@k` fallback.
Pre-existing eval-replay / eval-longmemeval / eval-export / eval-prune
tests (42 cases) still pass — --mode + --compare-limit are additive.
* docs: methodology + CLAUDE.md/README/RESOLVER + skills/conventions
docs/eval/SEARCH_MODE_METHODOLOGY.md — haters-immune 8-section template.
Documents what the eval measures + does NOT measure, datasets + sizes
(LongMemEval n=500, Replay n=200, BrainBench n=1240 docs / 350 qrels),
random seed 42, run procedure verbatim, threats to validity (LongMemEval
English+technical skew, char/4 heuristic ~5-10% off, expansion ~97.6%
relative lift on this corpus), per-question raw outputs, pre-registered
expectations (tokenmax wins R@10 by 5-15pp, conservative wins cost by
5-15x, balanced lands within 3pp), re-run cadence anchored to the
src/core/eval/drift-watch.ts watch-list.
Statistical-significance section pins paired bootstrap with 10,000
resamples + Bonferroni correction across 3 modes × 4 metrics [CDX-14].
CLAUDE.md gets two new sections: ## Search Mode (3-mode table + resolution
chain + [CDX-4] cache contamination fix note + CLI commands) and ## Eval
discipline (single-source-of-truth glossary, methodology doc, eval_results
in repo NOT personal brain per [CDX-23]).
README.md Quick Start gets a paragraph naming the install picker, mode
heuristic, and the methodology link.
skills/conventions/search-modes.md NEW — convention file consumed by
brain-ops + query + signal-detector skills via the existing
`> **Convention:**` callout pattern. Routes "what mode" / "tune
retrieval" / "compare modes" queries to the right CLI surface.
skills/RESOLVER.md gets two new trigger rows pointing at
gbrain search * and gbrain eval compare.
* chore: regen llms.txt + llms-full.txt for v0.32.3 search-mode docs
bun run build:llms — picks up the new CLAUDE.md sections (Search Mode +
Eval discipline) and the docs/eval/SEARCH_MODE_METHODOLOGY.md addition.
build-llms.test.ts gate now passes.
* fix(doctor): wire search_mode + eval_drift checks into runDoctor main flow
The v0.32.3 search_mode + eval_drift helpers were inserted into the
DB-checks sub-helper at runDbChecks (line 345-355), but runDoctor itself
maintains its own check list and only calls the helpers' subset. Push
the two checks into the main runDoctor path (after the existing
sync_freshness check at line 2347) so they actually appear in
`gbrain doctor --json` output.
Both checks gated on engine !== null. Progress reporter heartbeat fires
for each. Both still return status 'ok' per [CDX-20] so health score is
preserved.
Verified end-to-end on a real Postgres brain: gbrain doctor --json now
includes 'search_mode' and 'eval_drift' in the checks array.
* fix: claw-test hang — DATABASE_URL leak + telemetry beforeExit deadlock
Two root causes for the hang, both fixed.
1. DATABASE_URL leak in claw-test scripted harness
The harness inherits the parent process's env via `...process.env`
for every phase child (init / import / query / extract / doctor).
When the e2e runner sets DATABASE_URL (for OTHER e2e tests), it
leaks into claw-test's children. `loadConfig` at src/core/config.ts:143
then flips inferredEngine to 'postgres' for every subsequent phase,
breaking the hermetic-PGLite-tempdir contract: phases race against
each other on a shared test Postgres while pointing at different
brain states.
Fix: strip DATABASE_URL + GBRAIN_DATABASE_URL from the child env
before forwarding. Re-apply GBRAIN_HOME / GBRAIN_FRICTION_RUN_ID
after the merge so a parent's override can't win. The harness is
PGLite-only by design.
2. Telemetry beforeExit deadlock
v0.32.3's recordSearchTelemetry installed a `process.on('beforeExit',
drainOnExit)` hook that wrapped the flush in `Promise.race([flush(),
setTimeout(2000)])`. beforeExit fires when the event loop empties,
but the hook enqueued NEW async work (the race's setTimeout +
pending flush), so the event loop never re-emptied. Short-lived
CLI invocations (`gbrain query "the"` finishing in ~100ms) ended
up waiting on the DB write indefinitely.
The claw-test harness spawns several short-lived gbrain queries.
Each one hung after its real work finished. The harness then waited
forever on its child subprocess's exit code.
Fix: drop the beforeExit + SIGINT + SIGTERM hooks. Per [CDX-19]'s
"stats are directional, not exact" contract, losing one unflushed
bucket on process exit is acceptable. The unref'd setInterval
handles long-running processes (HTTP MCP, autopilot, jobs work).
Short-lived CLI invocations exit immediately.
Verified:
- `gbrain query "the"` on a fresh PGLite brain exits in <1s (was
hanging forever).
- `bun test test/e2e/claw-test.test.ts` → 3 pass / 0 fail / 3.86s
(was hanging at the banner indefinitely).
- 85/85 e2e files / 574/574 tests pass including claw-test, with
DATABASE_URL set (the configuration that originally repro'd the
hang).
- 6235/6235 unit tests pass.
- Typecheck clean.
The two bugs interacted: the DATABASE_URL leak meant queries hit the
real Postgres (slow), making the beforeExit deadlock visible. Fixing
either alone would have masked the other. Both fixed in this commit.
* feat(install-picker): cost anchors in mode prompt + upgrade banner + docs
The install picker already asks explicitly (1/2/3 menu, default to the
recommendation on Enter). What was missing: a way to reason about the
cost tradeoff. Without numbers, "tokenmax" looks free and "conservative"
sounds restrictive; with numbers, the operator picks intentionally.
Cost anchors added everywhere the user encounters the mode choice:
- Install picker MENU_TEXT (gbrain init)
- Upgrade banner (gbrain upgrade post-upgrade)
- CLAUDE.md ## Search Mode section
- README.md Quick Start
- docs/eval/SEARCH_MODE_METHODOLOGY.md (with the math)
Anchors at Sonnet 4.6 downstream ($3/M input):
conservative ~$0.012/query ~$12/mo @ 1K ~$1,200/mo @ 100K
balanced ~$0.030/query ~$30/mo @ 1K ~$3,000/mo @ 100K
tokenmax ~$0.060/query ~$60/mo @ 1K ~$6,000/mo @ 100K
Plus tokenmax's Haiku expansion overhead: ~$1.50 per 1K queries on top.
Cache hits roughly halve these on a brain with repeat-query traffic.
The math is documented in SEARCH_MODE_METHODOLOGY.md so a reviewer can
audit each variable (T = ~400 tokens/chunk from the recursive chunker's
300-word target; N = `searchLimit` cap; R = downstream model rate from
src/core/anthropic-pricing.ts). Drift away from these numbers requires
updating CLAUDE.md + the picker + the methodology doc in lockstep — a
regression test pins the picker's anchor strings to enforce this.
The framing also names the cost rule honestly: the dominant cost isn't
gbrain (semantic cache is free; Haiku expansion is rounding-error). It's
the downstream agent reading retrieved chunks back into its context.
Operators who don't realize this pick badly.
Tests: 5 new regression cases in init-mode-picker.test.ts pin every
cost string in MENU_TEXT. Total 21/21 picker tests pass; 6240/6240
unit tests pass; verify gate green.
* docs: realistic-scale cost anchor for search modes
The per-query cost framing in the picker (~$0.012/$0.030/$0.060) is
honest but theoretical — it treats each search as an isolated billable
event. Real agent loops amortize a lot of context across turns via
Anthropic prompt caching, so the per-query 5x ratio doesn't translate
1:1 into total agent spend.
Added a "Realistic-scale anchor" section to SEARCH_MODE_METHODOLOGY.md
representing one heavy power-user agent loop running tokenmax:
- ~860 turns/mo (~29/day, one active agent)
- ~900K tokens/turn (system + tools + history + reasoning + search)
- ~$0.85/turn → ~$700/mo total agent spend at tokenmax
- ~88% Anthropic prompt-cache hit rate
Scaling balanced + conservative DOWN from that anchor:
- tokenmax → ~$700/mo, search ~22% of total spend
- balanced → ~$620/mo, search ~12% (saves ~$78/mo vs tokenmax)
- conservative → ~$575/mo, search ~5% (saves ~$124/mo vs tokenmax)
Honest takeaway: at realistic agent-loop scale WITH disciplined prompt
caching, mode choice saves 10-20% of total agent spend, not 5x. The
per-query math kicks back in for setups WITHOUT cache discipline (churn
the prompt prefix every turn → search payload becomes a larger fraction).
Both framings live in the doc.
CLAUDE.md ## Search Mode gets a forward-pointer paragraph naming the
"per-query math vs real-world spend" delta so agents reading the section
find the methodology footnote.
Numbers in the doc are anonymized + scaled away from any specific
deployment. No model names, no specific dollar figures from a real
production setup — just the per-turn / cache-hit-rate / search-count
shape ratios that a thoughtful operator can validate against their own
billing dashboard.
* feat(picker): mode × model cost matrix (25x corner-to-corner spread)
Previous version showed mode costs assuming Sonnet-only downstream.
That muted the spread to 5x and made mode choice look minor. Reality:
the downstream model tier is the BIGGER cost lever — pairing mode with
model is where the 25x spread lives.
New 3×3 matrix in the install picker, CLAUDE.md, methodology doc, README:
Haiku 4.5 Sonnet 4.6 Opus 4.7
($1/M input) ($3/M input) ($5/M input)
conservative $400/mo $1,200/mo $2,000/mo
balanced $1,000/mo $3,000/mo $5,000/mo
tokenmax $2,000/mo $6,000/mo $10,000/mo
(per-query cost @ 100K queries/mo, full search payload, no cache savings)
The methodology doc gets a new "Mode × Model matrix" section above the
realistic-scale anchor with concrete right-sizing guidance:
- tokenmax + Haiku: wrong direction. Haiku can't filter 50 chunks → noise
not signal. Pay Haiku rates, get sub-Haiku quality.
- conservative + Opus: wasted Opus. 200K context window starved on
retrieval depth. Pay Opus rates, get conservative-shape retrieval.
- Natural pairings span ~4x; the matrix corners span 25x. The natural
diagonal is where most users should land.
Realistic-scale anchor refreshed:
- tokenmax + Opus: ~$700/mo at 860 turns
- balanced + Sonnet: ~$430/mo
- conservative + Haiku: ~$170/mo
Plus a "mismatched pairings" section showing the math for tokenmax+Haiku
and conservative+Opus — both burn budget for no improvement.
Regression test updated: pins the 25x framing + the four anchor cells
(two corners + two diagonal mids) + the three downstream model rates.
22/22 picker tests pass. 6241/6241 unit tests pass. CI guards green.
* docs(picker): rescale cost matrix from 100K → 10K queries/mo (typical single user)
Most users running gbrain are single-user installs at ~10K queries/month,
not the 100K fleet-scale used in the original matrix. The picker numbers
($400 to $10,000/mo) looked alien to the actual audience. Rescaled to
10K with an explicit linear-scaling callout.
New matrix in picker, CLAUDE.md, README, methodology doc:
Haiku 4.5 Sonnet 4.6 Opus 4.7
($1/M) ($3/M) ($5/M)
conservative $40/mo $120/mo $200/mo
balanced $100/mo $300/mo $500/mo
tokenmax $200/mo $600/mo $1,000/mo
Still 25x corner-to-corner. Still 4x natural-diagonal spread. But now in
numbers a single user picks up and reasons about: "balanced + Sonnet at
$300/mo, that's fine" or "tokenmax + Opus at $1,000/mo, that's a
deliberate choice for max-quality high-stakes work."
Every surface updated:
- Install picker MENU_TEXT (with "scales linearly — multiply by 10
for 100K/mo" footnote so heavier users still see their number)
- CLAUDE.md ## Search Mode table + scaling prose
- README Quick Start
- methodology doc Mode × Model matrix section
- upgrade banner (post-upgrade notice)
Regression test updated: pins the 3 new anchor cells ($40, $300, $1,000)
+ the 10K/mo volume frame + the linear-scaling callout. 23/23 picker
tests pass, 6241/6241 unit tests pass, verify gate green.
Methodology doc's existing 1K/10K/100K Monthly cost breakdown tables
left intact (they already show the linear scaling explicitly).
* feat(picker): agent-facing install protocol + tokenmax default + [AGENT] directive
DX gap: an agent installing gbrain (OpenClaw, Hermes, Codex, Cursor) ran
gbrain init non-TTY, saw 2 stderr lines flash by, and silently auto-applied
a default search mode. The operator never saw the cost matrix or the choice.
At 25x corner-to-corner cost spread, that's surprise-spend territory.
Five surfaces fixed:
1. **Auto-suggest default flipped balanced → tokenmax.** The Sonnet/unknown
fallback now recommends tokenmax (preserves v0.31.x retrieval shape:
expand=on, generous result set). Haiku subagent → conservative still
wins (cost-sensitive signal). No-OpenAI-key → conservative still wins
(vector search not possible). Heuristic reordered: Haiku check now
fires BEFORE the Opus check, because a Haiku subagent loop signalling
cost sensitivity should win over a default-model heuristic.
2. **gbrain init non-TTY output rebuilt.** Previously: 2 stderr lines.
Now: the full 3×3 cost matrix + an explicit [AGENT] directive block
telling the agent to relay the matrix to its operator before
continuing. Includes a pointer to INSTALL_FOR_AGENTS.md Step 3.5 for
the full protocol.
3. **gbrain upgrade banner same treatment.** Existing v0.32.3 banner now
includes [AGENT] directive at the top so upgrading agents relay the
matrix to their operator instead of silently accepting v0.31.x →
v0.32.x default-applied behavior.
4. **INSTALL_FOR_AGENTS.md Step 3.5 NEW** with the matrix verbatim, the
exact paraphrasable ask-the-user wording, and the gbrain config set
commands to run after the operator picks. Plus a paragraph in the
Upgrade section pointing back at Step 3.5.
5. **AGENTS.md install checklist** gets a new Step 4 ("STOP — ask the
user about search mode") between init and the rest of the flow. The
agent's job description now explicitly says: silent acceptance is
the wrong default.
Tests (24/24 pass):
- Updated recommendModeFor heuristic order (Haiku floor > Opus default)
- New regression test: non-TTY output contains the matrix corners +
[AGENT] directive + INSTALL_FOR_AGENTS.md pointer
- withEnv() helper used for OPENAI_API_KEY mutation (test-isolation lint)
- Default-recommendation tests updated: Sonnet / unknown → tokenmax
Privacy + test-isolation gates clean. 6256/6256 unit tests pass.
---------
Co-authored-by: garrytan-agents <agents@garrytan.com>
Co-authored-by: Garry Tan <garrytan@gmail.com>
9.6 KiB
9.6 KiB
GBrain Installation Guide for AI Agents
Read this entire file, then follow the steps. Ask the user for API keys when needed. Target: ~30 minutes to a fully working brain.
Step 0: If you are not Claude Code
Read AGENTS.md at the repo root first. It's the non-Claude-agent operating
protocol (install, read order, trust boundary, common tasks). Claude Code reads
CLAUDE.md automatically and can skip ahead.
If you fetched this file by URL without cloning yet, the companion files live at:
https://raw.githubusercontent.com/garrytan/gbrain/master/AGENTS.md— start herehttps://raw.githubusercontent.com/garrytan/gbrain/master/llms.txt— full doc maphttps://raw.githubusercontent.com/garrytan/gbrain/master/llms-full.txt— same map, inlined
Step 1: Install GBrain
git clone https://github.com/garrytan/gbrain.git ~/gbrain && cd ~/gbrain
curl -fsSL https://bun.sh/install | bash
export PATH="$HOME/.bun/bin:$PATH"
bun install && bun link
Verify: gbrain --version should print a version number. If gbrain is not found,
restart the shell or add the PATH export to the shell profile.
Do NOT use
bun install -g github:garrytan/gbrain. Bun blocks the top-level postinstall hook on global installs, so schema migrations never run and the CLI aborts withAborted()when it opens PGLite. Use thegit clone + bun linkpath above. Tracking issue: #218.
Step 2: API Keys
Ask the user for these:
export OPENAI_API_KEY=sk-... # required for vector search
export ANTHROPIC_API_KEY=sk-ant-... # optional, improves search quality
Save to shell profile or .env. Without OpenAI, keyword search still works.
Without Anthropic, search works but skips query expansion.
Step 3: Create the Brain
gbrain init # PGLite, no server needed
gbrain doctor --json # verify all checks pass
The user's markdown files (notes, docs, brain repo) are SEPARATE from this tool repo. Ask the user where their files are, or create a new brain repo:
mkdir -p ~/brain && cd ~/brain && git init
Read ~/gbrain/docs/GBRAIN_RECOMMENDED_SCHEMA.md and set up the MECE directory
structure (people/, companies/, concepts/, etc.) inside the user's brain repo,
NOT inside ~/gbrain.
Step 3.5: Confirm search mode with the user (DO NOT SKIP)
gbrain init auto-applied a default search mode (tokenmax unless your subagent
tier is Haiku-class or no OpenAI key is configured). The init output included the
cost matrix below preceded by [AGENT] markers. You must NOT silently accept the
default. Stop and ask the operator.
Present this matrix verbatim:
Per-query cost @ 10K queries/mo (typical single-user volume):
Haiku 4.5 Sonnet 4.6 Opus 4.7
($1/M) ($3/M) ($5/M)
conservative $40/mo $120/mo $200/mo
balanced $100/mo $300/mo $500/mo
tokenmax $200/mo $600/mo $1,000/mo
(scales linearly: ×10 for 100K/mo, ÷10 for 1K. 25x corner-to-corner spread.
Natural diagonal pairings — cheap/cheap → frontier/frontier — span ~4x.)
Ask the operator (paraphrase if needed):
Your gbrain just installed with search mode
<auto-applied default>. This is a one-time setup decision that controls retrieval payload size. Which mode do you want?
conservative — tight 4K budget, no LLM expansion, 10 chunks max. Best for Haiku subagents, cost-sensitive setups, high-volume loops.
balanced — 12K budget, no expansion, 25 chunks. Sonnet-tier sweet spot.
tokenmax (recommended default — preserves v0.31.x retrieval shape) — no budget, LLM expansion ON, 50 chunks. Best for Opus/frontier models.
Cost depends on BOTH the mode AND the downstream model you run. See the matrix above for the 9-cell breakdown.
If the operator picks a non-default mode, run:
gbrain config set search.mode <mode>
If they pick tokenmax AND want to preserve the literal v0.31.x default (limit=20 instead of tokenmax's 50), also run:
gbrain config set search.searchLimit 20
Verify the choice with gbrain search modes before continuing.
Why this matters: the cost spread between corners of the matrix is 25x. An agent that silently accepts the default and starts running queries against a user who didn't expect tokenmax-class context loads can rack up surprise spend. Confirm before continuing.
Step 4: Import and Index
gbrain import ~/brain/ --no-embed # import markdown files
gbrain embed --stale # generate vector embeddings
gbrain query "key themes across these documents?"
Step 4.5: Wire the Knowledge Graph
If the user already had a brain repo (Step 3 imported existing markdown), backfill
the typed-link graph and structured timeline. This populates the links and
timeline_entries tables that future writes will maintain automatically.
gbrain extract links --source db --dry-run | head -20 # preview
gbrain extract links --source db # commit
gbrain extract timeline --source db # dated events
gbrain stats # verify links > 0
For brand-new empty brains, skip this step — auto-link populates the graph as the agent writes pages going forward. There is nothing to backfill yet.
After this step:
gbrain graph-query <slug> --depth 2works (relationship traversal)- Search ranks well-connected entities higher (backlink boost)
- Every future
put_pageauto-creates typed links and reconciles stale ones
If a user has a very large brain (>10K pages), extract --source db is idempotent
and supports --since YYYY-MM-DD for incremental runs.
Step 5: Load Skills
Read ~/gbrain/skills/RESOLVER.md. This is the skill dispatcher. It tells you which
skill to read for any task. Save this to your memory permanently.
The three most important skills to adopt immediately:
-
Signal detector (
skills/signal-detector/SKILL.md) — fire this on EVERY inbound message. It captures ideas and entities in parallel. The brain compounds. -
Brain-ops (
skills/brain-ops/SKILL.md) — brain-first lookup on every response. Check the brain before any external API call. -
Conventions (
skills/conventions/quality.md) — citation format, back-linking iron law, source attribution. These are non-negotiable quality rules.
Step 6: Identity (optional)
Run the soul-audit skill to customize the agent's identity:
Read skills/soul-audit/SKILL.md and follow it.
This generates SOUL.md (agent identity), USER.md (user profile), ACCESS_POLICY.md (who sees what), and HEARTBEAT.md (operational cadence) from the user's answers.
If skipped, minimal defaults are installed automatically.
Step 7: Recurring Jobs
Set up using your platform's scheduler (OpenClaw cron, Railway cron, crontab):
- Live sync (every 15 min):
gbrain sync --repo ~/brain && gbrain embed --stale - Auto-update (daily):
gbrain check-update --json(tell user, never auto-install) - Dream cycle (nightly): read
docs/guides/cron-schedule.mdfor the full protocol. Entity sweep, citation fixes, memory consolidation, plus (v0.23+) overnight conversation synthesis and cross-session pattern detection. 8 phases, one cron-friendly command. This is what makes the brain compound. Do not skip it. - Weekly:
gbrain doctor --json && gbrain embed --stale
Step 8: Integrations
Run gbrain integrations list. Each recipe in ~/gbrain/recipes/ is a self-contained
installer. It tells you what credentials to ask for, how to validate, and what cron
to register. Ask the user which integrations they want (email, calendar, voice, Twitter).
Verify: gbrain integrations doctor (after at least one is configured)
Step 9: Verify
Read docs/GBRAIN_VERIFY.md and run all 7 verification checks. Check #4 (live sync
actually works) is the most important.
Upgrade
cd ~/gbrain && git pull origin master && bun install
gbrain init # apply schema migrations (idempotent)
gbrain post-upgrade # show migration notes for the version range
Then read ~/gbrain/skills/migrations/v<NEW_VERSION>.md (and any intermediate
versions you skipped) and run any backfill or verification steps it lists. Skipping
this is how features ship in the binary but stay dormant in the user's brain.
v0.32.3 search modes (one-time upgrade prompt): if the user's brain was
created before v0.32.3, gbrain post-upgrade prints a banner including the
9-cell cost matrix (mode × downstream model) preceded by [AGENT] markers.
Do NOT silently move past the banner. Present the matrix to the operator
verbatim, ask which mode they want (recommended default: tokenmax to preserve
v0.31.x retrieval shape), then run gbrain config set search.mode <mode>. See
Step 3.5 above for the full ask-the-user protocol — the upgrade path uses the
same matrix and same default.
For v0.12.0+ specifically: if your brain was created before v0.12.0, run
gbrain extract links --source db && gbrain extract timeline --source db to
backfill the new graph layer (see Step 4.5 above).
For v0.12.2+ specifically: if your brain is Postgres- or Supabase-backed and
predates v0.12.2, the v0_12_2 migration runs gbrain repair-jsonb
automatically during gbrain post-upgrade to fix the double-encoded JSONB
columns. PGLite brains no-op. If wiki-style imports were truncated by the old
splitBody bug, run gbrain sync --full after upgrading to rebuild
compiled_truth from source markdown.