Merged
Conversation
v0.2.0: Context Packet Builder - POST /v1/context-packet: phase-aware semantic document replacing raw graph nodes (~800 token cap vs 4000+ for raw output) - 7-section packet: root summary, dep summaries, LLM insight, constraints, team status, quality gate, pattern hints, phase guidance - SDLC phase system (planning/development/testing/review/deployment) controls which sections are active per phase - Quality modes (quick/standard/enterprise) drive the quality gate checklist - Co-occurrence learner: POST /v1/decision logs agent work; Brain builds pattern hints from symmetric co-occurrence counts (no LLM, pure Go) - New HTTP endpoints: /v1/sdlc, /v1/sdlc/phase, /v1/sdlc/mode, /v1/decision, /v1/patterns - New CLI: brain sdlc, brain decisions, brain patterns - New SQLite tables: sdlc_config, context_patterns, decision_log - NullBrain extended with 6 new no-op methods - Full JSON tags on all HTTP request/response types v0.2.1: Correctness fixes - Extract shared ExtractJSON + Truncate into internal/llm/util.go; remove 4 duplicate copies from ingestor/enricher/guardian/orchestrator - Store pruneOldData: silent db.Exec errors now logged to stderr - Store GetSummaryWithTags, GetRecentDecisions: JSON unmarshal errors logged - LLMUsed bool added to enricher.Response, brain.EnrichResponse, brain.ContextPacket v0.3.0: Insight Cache + Quality Signal - insight_cache table: caches LLM insight per (node_id, phase), 6-hour TTL - Insight cache invalidation on re-ingest: UpsertSummary deletes stale cache - Builder is cache-first: checks insight_cache before calling Ollama; stores result after live call; LLMUsed=false on cache hits - violation_cache TTL prune added (7-day expiry at startup) - PacketQuality float64 (0.0-1.0) heuristic on every context packet - Reset() now clears insight_cache (bug fix) - INTELLIGENCE.md: comprehensive integration guide for Synapses core including 3 injection points, BrainClient design, 6 integration challenges, 7 planned improvements for v0.4.0 - Version bumped to 0.3.0 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
README.md — comprehensive developer and user guide: - Quick start (build → pull model → serve → health check) - Full configuration reference with all fields and defaults - Model tier selection guide (4GB → 16GB+) - Complete CLI reference: serve, status, ingest, summaries, sdlc, decisions, patterns, reset, version - HTTP API reference for all 12 endpoints with request/response examples - Go library usage with Brain interface summary - packet_quality interpretation table - Phase→sections matrix and SDLC workflow docs - Quality mode comparison table - brain.sqlite table inventory with TTL/pruning notes - Developer guide: package conventions and import rules CHANGELOG.md — full version history: - v0.0.1: initial scaffolding - v0.1.0: Ingest, Enrich, Guardian, Orchestrate, HTTP sidecar, CLI - v0.2.0: Context Packet, SDLC phases, quality modes, co-occurrence learning (context_patterns, decision_log, sdlc_config tables) - v0.3.0: insight cache (6h TTL), cache invalidation on re-ingest, PacketQuality, LLMUsed, shared llm/util.go, 6 new HTTP endpoints, 5 new CLI subcommands, Reset() fix, INTELLIGENCE.md Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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
1 participant
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.
No description provided.