v1.7.0

1.7.0 (2026-02-21)

Features

• 02-03: implement keyword-index symbol reference lookup (ccfc564)
• 02-03: register get_symbol_references MCP tool (6f6bc3a)
• 03-01: add frozen controlled eval fixture and local codebase (46736ed)
• 03-03: add multi-codebase eval runner command (b065042)
• 03-03: centralize eval harness scoring logic (5c5319b)
• 04-01: add curated grammar manifest, sync script, and publish inclusion (908f39a)
• 04-01: update tree-sitter loader to resolve packaged grammars and fail closed (458520f)
• 04-02: add manifest-driven grammar CI test with fail-closed fallback (2559405)
• 05-01: create AST-aligned chunking engine with symbol tree builder (f865abc)
• 05-01: wire AST-aligned chunker into GenericAnalyzer with 21 unit tests (68a2d6d)
• 05-02: add scope-aware prefix generation to AST chunks (3dbd43e)
• 06-01: add index format metadata and headers (a216c6d)
• 06-01: gate index consumers on IndexMeta validation (6a52c0d)
• 06-02: implement staging directory build and atomic swap for full rebuild (d719801)
• AST indexing: Implement relationship index (#38) (5b05092)
• expose all 10 MCP tools via CLI + document them (#42) (7581fba)
• references confidence, remove get_component_usage, ranked search hints (#39) (33616aa)
• rework decision-card to make it based on AST parsing (#41) (ac4389d)
• symbol ranking, smart snippets, and edit decision card (#40) (03964b3)
• use tree-sitter symbols in generic analyzer (b470709)

Bug Fixes

• 02-01: fall back when tree-sitter parse has errors (8a7cd92)
• 02-tree-sitter-02: prevent symbol-aware chunk merging (fd02625)
• 03-02: add regression guardrails for extraction and large-file safety (a1c71de)
• 03-02: harden tree-sitter extraction against byte-offset and parser failures (375a48f)

v1.6.2

[1.6.2] - 2026-02-17

Stripped it down for token efficiency, moved CLI code out of the protocol layer, and cleared structural debt.

Changed

• Search output: trend: "Stable" is no longer emitted (only Rising/Declining carry signal). Added a compact type field (service:data) merging componentType and layer into 2 tokens. Removed lastModified considered noise.
• searchQuality: now includes hint (for next-step suggestion) when status is low_confidence, so agents get actionable guidance without a second tool call.
• Tool description: shortened to 2 actionable sentences, removed reference to editPreflight (which didn't exist in output). intent parameter is now discoverable on first scan.
• CLI extraction: handleMemoryCli moved from src/index.ts to src/cli.ts. Protocol file is routing only.
• Angular self-registration: registerComplementaryPatterns('reactivity', ...) moved from src/index.ts into AngularAnalyzer constructor. Framework patterns belong in their analyzer.

Added

• AGENTS.md Lessons Learned section - captures behavioral findings from the 0216 eval: AI fluff loop, self-eval bias, static data as noise, agents don't read past first line.
• Release Checklist in AGENTS.md: CHANGELOG + README + capabilities.md + tests before any version bump.

v1.6.1

1.6.1 (2026-02-15)

Bug Fixes

• guard null chunk.content crash + docs rewrite for v1.6.1 (6b89778)

v1.6.0

1.6.0 (2026-02-11)

Features

• v1.6.0 search quality improvements (#26) (8207787)

v1.5.1

1.5.1 (2026-02-08)

Bug Fixes

• use cosine distance for vector search scoring (b41edb7)

v1.5.0

1.5.0 (2026-02-08)

Added

• Preflight evidence lock: search_codebase edit/refactor/migrate intents now return risk-aware preflight guidance with evidence lock scoring, impact candidates, preferred/avoid patterns, and related memories. (#21)
• Trust-aware memory handling: Git-aware memory pattern support and confidence decay so stale or malformed evidence is surfaced as lower-confidence context instead of trusted guidance. (#21)

Changed

• Search ranking: Removed framework-specific anchor/query promotion heuristics from core ranking flow to keep retrieval behavior generic across codebases. (#22)
• Search transparency: search_codebase now returns searchQuality with confidence and diagnostic signals when retrieval looks ambiguous. (#22)
• Incremental indexing state: Persist indexing counters to indexing-stats.json and restore them on no-op incremental runs to keep status reporting accurate on large codebases. (#22)
• Docs: Updated README performance section to reflect shipped incremental refresh mode (incrementalOnly).

Fixed

• No-op incremental stats drift: Fixed under-reported indexedFiles and totalChunks after no-change incremental refreshes by preferring persisted stats over capped index snapshots. (#22)
• Memory date validation: Invalid memory timestamps now degrade to stale evidence rather than being surfaced as semi-trusted data. (#21)

v1.4.1

1.4.1 (2026-01-29)

Bug Fixes

• lint: disable no-explicit-any rule for AST manipulation code (41547da)