rUv
f79fd39f94
feat(brain): expand to 48 categories + update reclassify prompt
...
Add 13 more categories:
- Robotics & Embodied: robotics, autonomous
- Data & Knowledge: natural_language, computer_vision, knowledge_representation, data_engineering
- Crypto & Privacy: cryptography, privacy
- Math & Physics: mathematics, physics
- Human & Social: education, ai_safety, open_source
Total: 48 categories (was 35). Updated reclassify prompt with full list.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-26 00:25:26 +00:00
rUv
b0347ce1a8
fix(brain): fix reclassify prompt to output bare category names
...
Gemini was returning "applied: biomedical" instead of "biomedical".
Updated prompt to list categories as flat values without group prefixes.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-26 00:24:18 +00:00
rUv
8e974a69fb
feat(brain): add /v1/reclassify endpoint for Gemini-powered category migration
...
Add POST /v1/reclassify that uses Gemini Flash to reclassify memories
from generic categories (solution, pattern, debug) into the expanded
35-category taxonomy. Processes memories in batches of up to 200.
- Gemini classifies based on title, content preview, and tags
- Directive prompt prefers specific categories over generic ones
- Persists changes to both DashMap cache and Firestore
- Returns detailed change log with old→new mappings
- store.update_category() method for atomic category+persist
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-26 00:12:43 +00:00
rUv
e61b36880c
feat(brain): expand BrainCategory from 8 to 35 categories
...
Previous categories (architecture, pattern, solution, convention, security,
performance, tooling, debug) were too generic — every discovery was just
"debug associated_with architecture" noise.
New categories span practical to exotic:
- Research: sota, discovery, hypothesis, cross_domain
- AI/ML: neural_architecture, compression, self_learning, reinforcement_learning, graph_intelligence
- Systems: distributed_systems, edge_computing, hardware_acceleration
- Frontier: quantum, neuromorphic, bio_computing, cognitive_science, formal_methods
- Applied: geopolitics, climate, biomedical, space, finance
- Meta: meta_cognition, benchmark
Backward compatible — serde snake_case, existing memories still deserialize.
Custom(String) still accepted for any unlisted category.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 22:54:18 +00:00
rUv
8631ce4b92
fix(brain): dramatically raise gist quality bar — real innovations only
...
Problem: gists still publishing recycled "X associated_with Y" noise.
Threshold changes:
- MIN_NEW_INFERENCES: 5 → 10
- MIN_EVIDENCE: 500 → 1000
- MIN_STRANGE_LOOP_SCORE: 0.05 → 0.1
- MIN_PROPOSITIONS: 10 → 20
- MIN_SONA_PATTERNS: 0 → 1 (require SONA learning)
- MIN_PARETO_GROWTH: 2 → 3
- MIN_INFERENCE_CONFIDENCE: 0.60 → 0.70
- New: MIN_UNIQUE_CATEGORIES = 4 (prevent recycling same domains)
- Rate limit: 24h → 72h (3 days between gists)
- Cross-domain similarity: 0.45 → 0.55
Quality filters:
- Reject ALL "may be associated with", "co-occurs with", "similar_to"
- Reject inferences < 50 chars
- Require 3+ strong inferences, 5+ strong propositions, 4+ unique categories
- Kill co_occurs_with and similar_to entirely from publishable set
Target: ~1 gist per week, only for genuinely novel cross-domain discoveries.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 22:26:55 +00:00
rUv
63b88fdb50
feat(brain): improve Gemini Chat prompt — detailed answers with citations
...
- Expand search context from 300 to 600 chars per memory
- Include tags in search results
- Directive prompt: speak as the brain, cite memories by title,
synthesize across results, add Google Search context
- Increase max output from 1024 to 2048 tokens
- Increase truncation limit from 1500 to 3000 chars
- Add "Ask me about..." follow-up suggestions
- Temperature 0.4 → 0.5 for more engaging responses
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 21:56:41 +00:00
rUv
7aa1722d14
feat(brain): Gemini Flash conversational Chat handler with brain tools
...
Replace raw search fallback with Gemini Flash + Google Grounding for
non-command messages. Gemini receives:
- Brain context (memory count, edges, drift)
- Semantic search results from the query
- Recent brain activity
- Google Search grounding for real-world context
Synthesizes conversational HTML responses for Google Chat cards.
Falls back to raw search if Gemini is unavailable.
25s timeout to stay within Chat's 30s limit.
Slash commands (status, drift, search, recent, help) still use
direct handlers for instant response.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 21:38:07 +00:00
rUv
fdddd5315f
fix(brain): handle Add-on event format — event nested under body.chat
...
Google Workspace Add-ons wrap the Chat event differently than legacy Chat API:
- Add-on: { "chat": { "messagePayload": { "message": {...} } } }
- Legacy: { "type": "MESSAGE", "message": {...} }
The handler now detects which format is used and parses accordingly.
Also handles appCommandPayload for slash commands.
Response uses confirmed correct format:
{ "hostAppDataAction": { "chatDataAction": { "createMessageAction": { "message": {...} } } } }
Ref: https://developers.google.com/workspace/add-ons/chat/quickstart-http
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 21:11:57 +00:00
rUv
70de68ef7b
fix(brain): correct Google Chat Add-on response format — chatDataAction
...
The correct Add-ons envelope uses `chatDataAction` (NOT `chatDataActionMarkup`):
{ "hostAppDataAction": { "chatDataAction": { "createMessageAction": { "message": {...} } } } }
Previous attempts:
1. Plain Message → 200 OK but "not responding" (wrong format for Add-ons)
2. chatDataActionMarkup → 200 OK but "not responding" (wrong field name)
3. chatDataAction → this should work per quickstart-http docs
Ref: https://developers.google.com/workspace/add-ons/chat/quickstart-http
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 21:00:42 +00:00
rUv
5b0057f5b9
fix(brain): revert to plain Message format + add raw payload logging
...
Revert DataActions wrapper — HTTP endpoint Chat apps should return
plain Message objects. Added raw payload logging to debug why Google
Chat shows "not responding" despite 200 OK responses.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 20:45:45 +00:00
rUv
b8b90e891c
fix(brain): wrap Google Chat responses in Add-ons DataActions envelope
...
Google Workspace Add-ons expect responses wrapped in:
{ "hostAppDataAction": { "chatDataActionMarkup": { "createMessageAction": { "message": {...} } } } }
Returning a raw Message object causes Google Chat to show "not responding"
even though the HTTP status is 200. The endpoint was receiving requests
correctly (confirmed via Cloud Run logs) but responses were being silently
dropped by the Add-ons framework.
Ref: https://developers.google.com/workspace/add-ons/chat/build
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 20:27:59 +00:00
rUv
03ebc7d753
docs: ADR-127 gist deep research loop architecture
...
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 17:40:38 +00:00
rUv
929ee40daf
fix(brain): overhaul gist quality — deep research loop, strict novelty gates
...
Problems fixed:
- Every gist was "X shows weak co-occurrence with Y (confidence: 50%)"
- Same generic cluster labels (debug, architecture, geopolitics) recycled
- Novelty thresholds too low (2 inferences, 100 evidence, 0.008 strange loop)
- Rate limit too permissive (4 hours = 6 gists/day of noise)
- No content-level dedup
Changes:
- Raise novelty thresholds: 5 inferences, 500 evidence, 0.05 strange loop
- Add MIN_INFERENCE_CONFIDENCE (60%) — filter out weak signals before publishing
- Add strong_inferences() / strong_propositions() quality filters
- Raise cross-domain similarity threshold from 0.3 to 0.45 at source
- Raise predicate thresholds (may_influence: 0.75, associated_with: 0.55)
- Rate limit: 24 hours between gists (was 4 hours)
- Content-based dedup (category + dominant inference, not just title)
- 3-pass research loop: (1) Gemini grounded research on topics,
(2) brain memory search for internal context, (3) Gemini synthesis
- Deleted all 45 old repetitive gists
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 17:39:40 +00:00
github-actions[bot]
9a55778bad
chore: Update NAPI-RS binaries for all platforms
...
Benchmarks / Rust Benchmarks (push) Waiting to run
Benchmarks / SQL Benchmarks (push) Waiting to run
Benchmarks / Compare with Baseline (push) Blocked by required conditions
Build Native Modules / Build darwin-arm64 (push) Waiting to run
Build Native Modules / Build linux-arm64-gnu (push) Waiting to run
Build Native Modules / Build darwin-x64 (push) Waiting to run
Build Native Modules / Build win32-x64-msvc (push) Waiting to run
Build Native Modules / Build linux-x64-gnu (push) Waiting to run
Build Native Modules / Commit Built Binaries (push) Blocked by required conditions
WASM Dedup Check / check-wasm-dedup (push) Waiting to run
RuvLLM Benchmarks / macOS ARM64 Benchmarks (M-series) (push) Has been cancelled
RuvLLM Benchmarks / Linux Benchmarks (NEON baseline) (push) Has been cancelled
RuvLTRA-Small Tests / Unit Tests (ubuntu-latest) (push) Has been cancelled
RuvLTRA-Small Tests / Unit Tests (windows-latest) (push) Has been cancelled
RuvLTRA-Small Tests / Unit Tests (macos-latest) (push) Has been cancelled
RuvLTRA-Small Tests / E2E Tests (macos-latest) (push) Has been cancelled
RuvLTRA-Small Tests / E2E Tests (ubuntu-latest) (push) Has been cancelled
RuvLTRA-Small Tests / Apple Silicon Tests (push) Has been cancelled
RuvLTRA-Small Tests / Quantization Accuracy (push) Has been cancelled
RuvLTRA-Small Tests / Test Coverage (push) Has been cancelled
RuvLTRA-Small Tests / Thread Safety (push) Has been cancelled
RuvLTRA-Small Tests / Performance Benchmarks (push) Has been cancelled
RuvLTRA-Small Tests / Stress Tests (push) Has been cancelled
RuvLTRA-Small Tests / Code Quality (push) Has been cancelled
RuvLLM Benchmarks / Compare Benchmarks (push) Has been cancelled
RuvLTRA-Small Tests / Test Summary (push) Has been cancelled
Built from commit 7acf1800a9🤖 Generated by GitHub Actions
2026-03-25 14:00:10 +00:00
rUv
7acf1800a9
Merge pull request #297 from ruvnet/claude/turboquant-kv-cache-P3oo2
...
feat(ruvllm): TurboQuant KV cache & vector compression
2026-03-25 09:49:01 -04:00
rUv
3e0b5723da
feat(ruvllm): add optimized inner product + comprehensive TurboQuant benchmarks
...
- Add rotated-domain inner product (skip inverse Hadamard via orthogonal
invariance: <Hq,Hk> = <q,k>), ~2x faster for attention computation
- Add batch-optimized variant that rotates query once across all keys
- Add Criterion benchmark suite: compression, decompression, inner product,
KV cache ops, embedding store, dimension scaling, memory efficiency
- 5 new tests verifying optimized methods match original results
- All 18 TurboQuant tests passing
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 13:48:50 +00:00
rUv
962672c81f
style(ruvllm): fix rustfmt formatting in turbo_quant and kv_cache
...
Resolve Code Quality CI failure by applying cargo fmt.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 13:43:36 +00:00
github-actions[bot]
ae473f31f3
chore: Update NAPI-RS binaries for all platforms
...
Built from commit cd96526da2🤖 Generated by GitHub Actions
2026-03-25 13:42:58 +00:00
rUv
cd96526da2
Merge pull request #296 from ruvnet/feat/resend-email-brain-integration
...
feat(brain): Resend email integration with pixel tracking
2026-03-25 09:38:15 -04:00
rUv
eabb43ac7e
feat(brain): add enhanced cognitive loop, gist publisher, and symbolic reasoning
...
Add autonomous Gist publishing for novel discoveries with novelty gates,
enhanced cognitive tick loop (60s lightweight + 5min full cycle), expanded
symbolic reasoning with cross-domain inference, and dashboard UI improvements.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 13:37:26 +00:00
Claude
8e6cd062f4
docs(research): add TurboQuant KV cache compression research document
...
Comprehensive research document covering TurboQuant (ICLR 2026) and its
mapping to ruvLLM. Covers algorithm details, performance results,
integration architecture, PiQ3 comparison, risks/mitigations, and
implementation summary.
https://claude.ai/code/session_011ogX2uc7Zf8d8aQ3UAbNcd
2026-03-25 12:14:17 +00:00
Claude
ecc6f3eec7
feat(ruvllm): implement TurboQuant KV cache & vector compression
...
Implement data-oblivious KV cache and embedding compression based on
TurboQuant (ICLR 2026). Two-stage pipeline: PolarQuant (Hadamard
rotation + scalar quantization) + QJL residual correction (1-bit),
achieving ~3.5 bits per value with geometry-preserving compression.
New modules:
- turbo_quant.rs: Core TurboQuantCompressor with compress/decompress,
TurboQuantCacheTier for KV cache, TurboQuantEmbeddingStore for
RuVector integration, asymmetric inner product for attention
- TurboQuantKvCache: Three-tier cache (FP16 hot + TurboQuant cold)
integrated into kv_cache.rs with auto-migration
Key features:
- 2.5/3.0/3.5/4.0 bit configurations with QJL residual toggle
- ~6x memory reduction on cold tier, preserves inner product geometry
- Bitstream packing handles non-byte-aligned bit widths
- Embedding store with batch build, search, and nearest-neighbor
- 13 passing tests covering roundtrip, compression, inner products,
batch ops, KV cache tier, eviction, and embedding search
https://claude.ai/code/session_011ogX2uc7Zf8d8aQ3UAbNcd
2026-03-25 12:13:06 +00:00
rUv
c48e2d6f75
fix(brain): add text fallback + resilient parsing for Google Chat
...
- Add 'text' field to all Chat card responses (required for HTTP endpoint mode)
- Parse Chat events from raw bytes for resilience against unknown fields
- Log raw payload on parse failure for debugging
- Return helpful fallback text on malformed events
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-25 00:08:23 +00:00
rUv
0ce919a846
feat(brain): add Google Chat bot handler with Cards V2 (ADR-126)
...
- Add POST /v1/chat/google endpoint for Google Chat webhook
- Handle ADDED_TO_SPACE (welcome), MESSAGE (commands), REMOVED_FROM_SPACE
- Commands: search, status, drift, recent, help + free-text auto-search
- Rich Cards V2 responses with header, key-value widgets, and links
- Service account pi-brain-chat created with Cloud Run invoker role
- ADR-126 documents architecture, marketplace config, deployment steps
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 23:04:45 +00:00
rUv
d3d78258ac
feat(brain): add inbound email webhook + Cloudflare MX for Resend
...
- Add POST /v1/email/inbound webhook handler for Resend inbound emails
- Parse email subjects for commands: search, status, help, drift, etc
- Semantic search via email: reply with "search <query>" to get results
- Remove "coming soon" label from email commands on website
- MX record updated: ruv.io -> inbound-smtp.resend.com (priority 10)
- Webhook registered: pi.ruv.io/v1/email/inbound (ID: 55c6592c)
- Old GoDaddy MX records removed from Cloudflare
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 22:59:57 +00:00
rUv
60102c75f0
feat(brain): add email subscribe/unsubscribe + website integration
...
- Add Email tab to Encyclopedia Galactica modal with subscribe form
- Add email subscription CTA in "Ready to connect" section
- Add Subscribe link in footer navigation
- Add POST /v1/notify/subscribe (public) — sends welcome email
- Add POST /v1/notify/unsubscribe (public) — handles opt-out
- Mark inbound email commands as "coming soon" (Resend webhooks TBD)
- Add subscribeEmail() JS with fallback to mailto
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 22:52:29 +00:00
rUv
6ca58e5395
feat(brain): add Resend email integration with pixel tracking (ADR-125)
...
Wire pi@ruv.io as the brain's email identity via Resend.com for
notifications, discovery digests, and conversational interaction.
- Add src/notify.rs: Resend HTTP client with 11 rate-limited categories,
styled HTML templates, open tracking pixel, and unsubscribe links
- Add 8 new routes: test, status, send, welcome, help, digest, pixel, opens
- All /v1/notify/* endpoints gated by BRAIN_SYSTEM_KEY auth
- Cloud Scheduler job brain-daily-digest at 8 AM PT for discovery emails
- RESEND_API_KEY secret mounted on Cloud Run (ruvbrain-00133-r2t)
- 4 test emails verified delivered to ruv@ruv.net
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 22:37:01 +00:00
github-actions[bot]
0508b5e02a
chore: Update NAPI-RS binaries for all platforms
...
Benchmarks / Rust Benchmarks (push) Waiting to run
Benchmarks / SQL Benchmarks (push) Waiting to run
Benchmarks / Compare with Baseline (push) Blocked by required conditions
Build Native Modules / Build darwin-arm64 (push) Waiting to run
Build Native Modules / Build linux-arm64-gnu (push) Waiting to run
Build Native Modules / Build darwin-x64 (push) Waiting to run
Build Native Modules / Build win32-x64-msvc (push) Waiting to run
Build Native Modules / Build linux-x64-gnu (push) Waiting to run
Build Native Modules / Commit Built Binaries (push) Blocked by required conditions
WASM Dedup Check / check-wasm-dedup (push) Waiting to run
ruvector-verified CI / check (--features hnsw-proofs) (push) Has been cancelled
ruvector-verified CI / check (--features rvf-proofs) (push) Has been cancelled
ruvector-verified CI / check (--features serde) (push) Has been cancelled
ruvector-verified CI / check (--features ultra) (push) Has been cancelled
ruvector-verified CI / clippy (push) Has been cancelled
ruvector-verified CI / check () (push) Has been cancelled
ruvector-verified CI / check (--all-features) (push) Has been cancelled
ruvector-verified CI / check (--features all-proofs) (push) Has been cancelled
ruvector-verified CI / check (--features coherence-proofs) (push) Has been cancelled
ruvector-verified CI / test (push) Has been cancelled
ruvector-verified CI / bench (push) Has been cancelled
Built from commit 2ace80f59d🤖 Generated by GitHub Actions
2026-03-24 15:06:01 +00:00
rUv
2ace80f59d
chore: update Cargo.lock for sona 0.1.9
...
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 15:00:37 +00:00
github-actions[bot]
2eb86d56ba
chore: Update NAPI-RS binaries for all platforms
...
Built from commit bf4c4b1a9f🤖 Generated by GitHub Actions
2026-03-24 14:51:13 +00:00
rUv
bf4c4b1a9f
feat(brain): add 18 MCP tools — cognitive, LoRA, training, pipeline
...
Closes 64% MCP-to-REST parity gap (22→40 tools):
Cognitive & Symbolic (4): brain_cognitive_status, brain_propositions,
brain_reason, brain_ground
Consciousness Model (3): brain_voice_working, brain_voice_history,
brain_voice_goal
Federated Learning (2): brain_lora_latest, brain_lora_submit
Training & Optimization (3): brain_train, brain_train_enhanced,
brain_optimizer_status
Temporal & SONA (3): brain_temporal, brain_sona_stats, brain_midstream
Pipeline (3): brain_inject, brain_inject_batch, brain_pipeline_metrics
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 14:46:16 +00:00
rUv
aa18999753
docs: update ADR-117/124 to shipped status, bump sona to 0.1.9
...
ADR-117: All 3 tiers shipped (exact, tree packing, dynamic)
ADR-124: All 8 gaps closed, deployment through ruvbrain-00130
ruvector-mincut: canonical feature docs updated
sona: 0.1.8→0.1.9 (threshold optimization)
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 14:46:15 +00:00
github-actions[bot]
29d7c81629
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 81405fb598🤖 Generated by GitHub Actions
2026-03-24 13:43:19 +00:00
rUv
81405fb598
fix(brain): persist LoRA consensus to Firestore after auto-submission
...
LoRA weights were computed in-memory but never persisted after
auto-submission from SONA patterns. Added fire-and-forget Firestore
persistence in train_enhanced_endpoint so weights survive deploys.
Also deferred sparsifier build on startup for >100K-edge graphs
to avoid 4-min health check timeout on Cloud Run.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 13:38:49 +00:00
github-actions[bot]
4307ae455e
chore: Update NAPI-RS binaries for all platforms
...
Benchmarks / Rust Benchmarks (push) Waiting to run
Benchmarks / SQL Benchmarks (push) Waiting to run
Benchmarks / Compare with Baseline (push) Blocked by required conditions
Build Native Modules / Build darwin-arm64 (push) Waiting to run
Build Native Modules / Build linux-arm64-gnu (push) Waiting to run
Build Native Modules / Build darwin-x64 (push) Waiting to run
Build Native Modules / Build win32-x64-msvc (push) Waiting to run
Build Native Modules / Build linux-x64-gnu (push) Waiting to run
Build Native Modules / Commit Built Binaries (push) Blocked by required conditions
ruvector-verified CI / check (--features rvf-proofs) (push) Waiting to run
ruvector-verified CI / check (--features serde) (push) Waiting to run
ruvector-verified CI / check (--features ultra) (push) Waiting to run
ruvector-verified CI / test (push) Blocked by required conditions
ruvector-verified CI / bench (push) Blocked by required conditions
ruvector-verified CI / clippy (push) Waiting to run
ruvector-verified CI / check (--features hnsw-proofs) (push) Waiting to run
ruvector-verified CI / check () (push) Waiting to run
ruvector-verified CI / check (--all-features) (push) Waiting to run
ruvector-verified CI / check (--features all-proofs) (push) Waiting to run
ruvector-verified CI / check (--features coherence-proofs) (push) Waiting to run
WASM Dedup Check / check-wasm-dedup (push) Waiting to run
Validate Package Lock File / validate-lockfile (push) Has been cancelled
Built from commit c2f1e9700c🤖 Generated by GitHub Actions
2026-03-24 12:35:01 +00:00
rUv
c2f1e9700c
fix(brain): defer sparsifier build on startup for large graphs
...
Sparsifier build on 1M+ edges exceeds Cloud Run's 4-min startup probe.
Skip on startup for graphs > 100K edges, defer to rebuild_graph job.
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 12:29:52 +00:00
github-actions[bot]
b0dbd81fcf
chore: Update NAPI-RS binaries for all platforms
...
Built from commit bd385c9565🤖 Generated by GitHub Actions
2026-03-24 12:07:57 +00:00
rUv
bd385c9565
feat(brain): close all remaining gaps — sparsified MinCut, Hopfield recall, LoRA auto-submit
...
Sparsified MinCut (59x speedup):
- partition_via_mincut_full uses 19K sparsified edges instead of 1M
- Large-graph guard now uses sparsifier instead of skipping
Cognitive integration:
- Hopfield recall_k wired into search scoring (0.10 boost)
- Associative memory now contributes to result ranking
LoRA federation unblocked:
- Auto-submit weight deltas from SONA's 436 patterns
- min_submissions lowered from 3 to 1 for bootstrapping
Strange loop in training:
- Invoked during training cycle, scores quality/relevance
- Recommends actions when quality is low
Symbolic inference fix:
- Shared-argument fallback for cross-cluster derivation
- Case-insensitive predicate matching
Auto-vote cap: 50→200 (4x faster coverage convergence)
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 12:03:31 +00:00
github-actions[bot]
462536ef54
chore: Update NAPI-RS binaries for all platforms
...
Benchmarks / Rust Benchmarks (push) Waiting to run
Benchmarks / SQL Benchmarks (push) Waiting to run
Benchmarks / Compare with Baseline (push) Blocked by required conditions
Build Native Modules / Build darwin-arm64 (push) Waiting to run
Build Native Modules / Build linux-arm64-gnu (push) Waiting to run
Build Native Modules / Build darwin-x64 (push) Waiting to run
Build Native Modules / Build win32-x64-msvc (push) Waiting to run
Build Native Modules / Build linux-x64-gnu (push) Waiting to run
Build Native Modules / Commit Built Binaries (push) Blocked by required conditions
ruvector-verified CI / bench (push) Blocked by required conditions
ruvector-verified CI / clippy (push) Waiting to run
ruvector-verified CI / check (--features serde) (push) Waiting to run
ruvector-verified CI / check (--features ultra) (push) Waiting to run
ruvector-verified CI / test (push) Blocked by required conditions
ruvector-verified CI / check () (push) Waiting to run
ruvector-verified CI / check (--all-features) (push) Waiting to run
ruvector-verified CI / check (--features all-proofs) (push) Waiting to run
ruvector-verified CI / check (--features coherence-proofs) (push) Waiting to run
ruvector-verified CI / check (--features hnsw-proofs) (push) Waiting to run
ruvector-verified CI / check (--features rvf-proofs) (push) Waiting to run
WASM Dedup Check / check-wasm-dedup (push) Waiting to run
Built from commit a6b95a79f0🤖 Generated by GitHub Actions
2026-03-24 02:23:55 +00:00
rUv
a6b95a79f0
docs: ADR-124 post-optimization metrics from 15-agent swarm
...
Before → After (single session):
- Votes: 995 (47%) → 1,393 (65.2%)
- Knowledge velocity: 0 → 423
- Drift: no_data → drifting (active)
- GWT: 86% → 100%
- Memories: 2,112 → 2,137 (+25 diverse)
- Cross-domain transfers: 56/56 successful
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 02:19:31 +00:00
github-actions[bot]
9bc78f93b8
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 72e5ab60d4🤖 Generated by GitHub Actions
2026-03-24 02:19:11 +00:00
rUv
72e5ab60d4
feat(brain): AGI self-optimization — self-reflection, inference, adaptive SONA
...
Self-Reflective Training (Step 6):
- Knowledge imbalance detection (>40% in one category)
- Dynamic SONA threshold adaptation (lower on 0 patterns, raise on success)
- Vote coverage monitoring with auto-correction
Curiosity Feedback Loop (Step 7):
- Stagnation detection via delta_stream
- Auto-generates synthesis memories for under-represented categories
- Creates self-sustaining knowledge velocity
Auto-Reflection Memory (Step 8):
- Brain writes searchable self-reflections after each training cycle
- Persistent learning history enables meta-cognitive search
Symbolic Inference Engine:
- Forward-chaining Horn clause resolution with chain linking
- Transitive inference across propositions
- Self-loop prevention, confidence filtering
- 3 new tests passing
SONA Threshold Optimization:
- min_trajectories: 100→10 (primary blocker)
- k_clusters: 50→5, min_cluster_size: 2→1
- quality_threshold: 0.3→0.15
- Added runtime set_quality_threshold() API
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 02:15:08 +00:00
github-actions[bot]
05e3931cba
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 70effc8235🤖 Generated by GitHub Actions
2026-03-24 01:57:52 +00:00
rUv
70effc8235
fix(brain): close underutilized capability gaps — auto-voting, SONA, drift
...
Gap 1 - Vote coverage (47%→improving):
Auto-upvote under-observed memories based on content quality heuristics
(title>10, content>50, has tags). Capped at 50/cycle.
Gap 2 - SONA trajectory diversity:
Record SONA steps for brain_share/search/vote MCP tool calls.
Only end trajectories when results >= 3 (avoid trivial single-step).
Gap 3 - Drift detection:
Record search query embeddings as drift signal in search_memories().
Drift CV metric now accumulates real data from user queries.
Knowledge velocity confirmed working (temporal_deltas pipeline active).
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 01:53:22 +00:00
github-actions[bot]
51a355776e
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 79165e4e15🤖 Generated by GitHub Actions
2026-03-24 01:44:01 +00:00
rUv
79165e4e15
perf(mincut): flat capacity matrix + allocation reuse — 10-30% faster
...
Optimizations:
- Flat Vec<FixedWeight> (n*n) replaces Vec<Vec<...>> in Dinic's max-flow
and Gomory-Hu tree — single memcpy vs N heap allocations per st-cut
- Reuse BFS queue/level/iter arrays across Dinic's phases
- Swap-remove in Stoer-Wagner active_list — O(1) vs O(n) retain
- Fix benchmark compilation errors in optimization_bench.rs
Results (all 26 benchmarks improved, Criterion p < 0.05):
- Tree packing: up to -29.7% (deep clone elimination)
- Source-anchored: -10% to -24% (cache locality)
- Hash stability: -24.2%
- Dynamic incremental: ~unchanged (wrapper-dominated)
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 01:38:43 +00:00
github-actions[bot]
d5a7665fc2
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 3ecba7c218🤖 Generated by GitHub Actions
2026-03-24 01:19:18 +00:00
rUv
3ecba7c218
docs: update ADR-124 with measured benchmark results
...
Measured on pi.ruv.io (2,110 nodes, 992K edges):
- brain_partition MCP: >60s timeout → 459ms (>130x)
- Partition REST cached: <1ms (>300,000x)
- Enhanced training: 504 timeout → 127ms
- 110 tests pass across all tiers
Co-Authored-By: claude-flow <ruv@ruv.net>
2026-03-24 01:14:51 +00:00
github-actions[bot]
e99a4a6cfb
chore: Update NAPI-RS binaries for all platforms
...
Built from commit 34b56e4c8b🤖 Generated by GitHub Actions
2026-03-24 00:10:20 +00:00
rUv
34b56e4c8b
feat(mincut): implement Tier 2-3 dynamic MinCut (ADR-124) ( #291 )
...
Tier 2 — Tree Packing Fast Path:
- Gomory-Hu flow-equivalent tree via Gusfield's algorithm
- Global MinCut from tree in O(V) after O(V * T_maxflow) construction
- canonical_mincut_fast() integration entry point
- 14 unit tests including Stoer-Wagner correctness validation
Tier 3 — Dynamic/Incremental MinCut:
- DynamicMinCut struct with epoch-based mutation tracking
- add_edge(): skip recompute if edge doesn't cross current cut
- remove_edge(): skip recompute if edge not in cut set
- apply_batch(): bulk mutations with deferred recomputation
- Staleness detection with configurable threshold
- HashSet caches for O(1) cut-crossing checks
- 19 unit tests including 100-run determinism check
WASM FFI: dynamic_init/add_edge/remove_edge/compute/epoch/free
Benchmarks: tree_packing_vs_stoer_wagner, dynamic_add_edge, dynamic_batch
98 canonical tests pass, 12 WASM tests pass.
2026-03-23 20:05:45 -04:00
