codevira 2.1.1__tar.gz → 2.1.2__tar.gz

{codevira-2.1.1 → codevira-2.1.2}/CHANGELOG.md

@@ -11,6 +11,212 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 
 ## [Unreleased]
 
+## [2.1.2] — 2026-05-19 — Trust recovery + QoL
+
+Trust-recovery release based on **four independent field-test reports** that
+converged on "trust" as the gap (not capability). Full plan:
+[docs/plans/v2.1.2.md](docs/plans/v2.1.2.md).
+
+### Added — Smart similarity threshold (Item 1)
+
+- `search_decisions` now applies a per-project, self-calibrating similarity
+  threshold before RRF fusion. Gibberish queries (`"zzzzzz xqzv9"`,
+  `"how to make a cake"`, `""`) return zero results with
+  `retrieval: "semantic-no-results-above-threshold"` instead of the
+  v2.1.1 regression where they surfaced the "least bad" matches.
+- New `codevira calibrate` CLI command for manual threshold re-fit.
+  Auto-recalibration runs in a daemon thread every ~10 decisions added.
+- Per-project `<data_dir>/calibration.json` (search threshold + hook
+  threshold + positive-sample count + ISO timestamp).
+- Cross-session hook injection (`CrossSessionConsistency`) applies the
+  stricter `hook` threshold (search − 0.10). Commit-message-shaped
+  prompts (`feat(api):` / `fix:` / etc.) skipped entirely.
+
+### Added — Honest cleanup (Item 3)
+
+- `codevira reset --vectors / --graph / --all` — destructive operations
+  split out of `codevira heal` (whose name implied fix-in-place).
+- Auto-export of decisions + outcomes + preferences + learned_rules to
+  `<data_dir>/exports/<ts>-pre-<target>.json` BEFORE any wipe of `graph/`.
+  Pass `--no-backup` to skip.
+- Typed confirmation: user must type `reset` / `graph` / `vectors` /
+  `all` (not just `y`) to proceed. `--yes` skips for scripts.
+- `codevira heal --vectors / --graph / --all` deprecation cycle:
+  forwards to `cmd_reset` with a one-time warning. Removal planned v2.2.
+- New `codevira export decisions [--format json|sql] [--out PATH]`
+  standalone backup command. Closes Report 1 §7 gap.
+- New `confirm_typed(...)` helper in `_prompts.py`.
+
+### Added — Proactive correctness
+
+- **Item 20**: `check_conflict(decision_text, file_path?)` MCP tool detects
+  duplicates and conflicts vs `do_not_revert=True` decisions. Uses Item 1's
+  calibrated threshold. `record_decision` runs it automatically pre-write
+  and surfaces `_conflict_warning` in the response (suppressible with
+  `force=True`).
+- **Item 26**: `supersede_decision(old_id, new_decision, reason)` retires
+  a prior decision with auditable history. Schema auto-migrates with
+  `is_superseded INTEGER + superseded_by INTEGER`. `list_decisions` filters
+  superseded rows by default; `include_superseded=True` opts back in.
+
+### Added — Enumeration + filtering
+
+- **Item 11**: `list_decisions(limit, since_date, file_pattern,
+  protected_only, session_id, tags, include_superseded, full)` MCP tool.
+  Closes Report 3 "remembers but can't list" gap.
+- **Item 27 (partial)**: `tags=[...]` on `record_decision`; `list_tags()`
+  MCP tool; tag filter on `list_decisions`. `decision_tags` table
+  auto-migrated.
+- **Item 25**: `since="YYYY-MM-DD"` (or ISO 8601) filter on
+  `search_decisions`, `get_history`, `get_session_context`. SQL-layer
+  for BM25, post-filter for semantic results.
+
+### Added — Batch APIs (Items 23 + 24)
+
+- `record_decisions([...])` and `write_session_logs([...])` cut
+  memory-dump sessions from ~26 separate round trips to 1. Returns
+  `{count, recorded:[ids], errors:[{idx, error}]}` with per-item
+  partial-failure surfacing.
+
+### Added — Trust + correctness fixes
+
+- **Item 2**: `get_node` / `get_impact` / `query_graph` / `update_node`
+  return `not_indexed: True` + null counts instead of misleading 0 for
+  un-indexed paths.
+- **Item 4**: New `PostEditGraphRefresh` policy refreshes graph nodes in
+  a daemon thread after Edit/Write/MultiEdit so subsequent
+  `get_node` / `get_impact` calls see fresh data.
+- **Item 9**: `global_db.get_rules()` strict-language match by default
+  (was `language = ? OR language IS NULL`). Prevents Go-project rules
+  with NULL language from leaking into Python projects. Pass
+  `strict_language=False` for legacy behavior.
+- **Item 17**: Rule extractor noise filter — stopword filter + minimum
+  content-density gate + substring suppression in `_find_common_phrases`.
+  Pre-code projects (0 indexed source files) skip
+  `_infer_decision_pattern_rules` entirely.
+- **Item 18**: `add_phase()` silently replaces the bootstrap
+  "Getting Started" placeholder when called with the SAME number (and
+  the placeholder is pristine — status=pending, no changesets, default
+  description).
+- **Item 19**: Regression test for `file_path` serialization round-trip
+  through `get_session_context`'s `recent_decisions`.
+- **Item 22**: `write_session_log` / `log_session` auto-suffix
+  `session_id` on content collision (was: silent `INSERT OR REPLACE`).
+  Same id + same summary remains idempotent; different summary returns
+  the new suffixed id with `collision_resolved: True`.
+- **Item 33**: Hook commit-message pre-filter suppresses injection on
+  prompts matching `^(feat|fix|chore|docs|refactor|test|style|perf|build|ci|revert)(\(.*\))?:`.
+
+### Added — Roadmap workflow
+
+- **Item 10**: `complete_phase(backfill=True, completed_at='YYYY-MM-DD')`
+  for retroactive phase completion (current / upcoming / synthetic
+  cases).
+- **Item 12**: `complete_phase(git_ref="...")` links a commit sha or PR
+  reference to the completion entry.
+- **Item 29**: `bulk_import_phases([...])` for adopting codevira on a
+  project that already shipped N phases in git. Idempotent.
+
+### Added — QoL
+
+- **Item 5**: `do_not_revert` int→bool coercion at SQLite read boundary
+  (`search_decisions`, missing-rows fetch path). API contract now
+  matches schema.
+- **Item 6**: Smart truncation in `top_signals.rules` (word-boundary +
+  path-aware, 160-char limit).
+- **Item 7**: `summary` derived from first 80 chars of decision text
+  instead of `"ad-hoc record_decision"` placeholder.
+- **Item 8**: `get_session_context` returns `confidence_note` instead of
+  `confidence=null` on fresh projects.
+- **Item 28**: `summary_only=True` mode on `search_decisions` returns
+  id + summary + score + do_not_revert only — ~70% smaller payload for
+  AI triage queries.
+- **Item 30**: `record_decision` input-coerced echo — when
+  `do_not_revert` is passed as a non-bool (int 1, string "true"),
+  response carries `_input_coerced_warning`.
+- **Item 31**: Bundled non-Python playbooks (TypeScript / Go / generic)
+  in `mcp_server/data/rules/coding-standards-<lang>.md`. Auto-selected
+  by detected project language. Closes Report 1 §3.5.
+- **Items 13 + 14**: `clean --orphans` catches bare global.db rows (no
+  data dir + path missing on disk). `clean --ghosts` catches truly-
+  empty data dirs (<10 KB, status='stale').
+
+### Added — Plan + governance (Item 16)
+
+- `docs/plans/v2.1.2.md` mirrors the master plan (33 items + 4 deferred
+  v2.2-class items). Establishes release-planning discipline: every
+  vX.Y.Z release with 3+ items gets its own `docs/plans/` doc.
+- `ROADMAP.md` v2.1.2 section.
+- `CONTRIBUTING.md` Release planning + Documentation discipline.
+
+### Fixed
+
+- **Item 21**: Multi-language `get_signature` / `get_code` confirmed
+  working in v2.1.1 (15+ languages via tree-sitter-language-pack). No
+  new code needed; doc fix only.
+- **Item 32**: All 42 pre-existing mypy errors cleared via real fixes
+  (type narrowing, missing imports, `Counter` / `dict[str, Any]`
+  annotations, AST isinstance gating) and targeted
+  `# type: ignore[code]` for invariant pre-existing patterns. mypy is
+  now a hard pre-commit gate.
+
+### Late additions (caught by post-tag smoke testing)
+
+These three patches landed AFTER the initial v2.1.2 release commit but
+BEFORE shipping the wheel. They're all part of the v2.1.2 line:
+
+- **bulk_import_phases placeholder fix**: importing `phase=1` on a
+  fresh project was silently SKIPPING phase 1 because the bootstrap
+  "Getting Started" placeholder occupies that number. Adopters
+  migrating multi-phase git history (Report 3 #5 — the exact use case
+  Item 29 exists for) would hit this. Fixed by applying Item 18's
+  placeholder-recognition logic to bulk_import too.
+- **calibrate doc range fix**: `codevira calibrate --help` said
+  "Clamped to [0.20, 0.55]" but actual code clamps to [0.35, 0.80]
+  (the empirically-tuned values from Item 1 after measuring
+  all-MiniLM-L6-v2's distance distribution on real query/decision
+  pairs). Doc string corrected.
+- **Issue #10 — Antigravity sandbox + torch dlopen**: graceful
+  degradation across 3 tiers. (1) Removed `prewarm_embedding_model()`
+  from MCP server startup — torch loads lazily on first
+  `search_codebase` / `search_decisions` call. MCP `initialize` and
+  `tools/list` complete instantly without touching torch. All
+  non-search tools work in Antigravity. (2) `_decisions_collection_or_none()`
+  traps `OSError` (macOS dlopen errors arrive as OSError, not
+  ImportError) and surfaces `_semantic_warning` in `search_decisions`
+  responses with a clear explanation + issue link.
+  (3) `docs/troubleshooting/antigravity.md` documents the root cause
+  and four user-side workarounds. Closes
+  [#10](https://github.com/sachinshelke/codevira/issues/10).
+
+### Tests
+
+- 2401/2401 unit tests pass + 4/4 e2e cross-tool universality.
+- Replaced: `test_log_session_replaces_on_duplicate` → idempotent +
+  auto-suffix variants (Item 22).
+- Renamed: `test_8_evaluation_under_5ms_p95` → `_50ms_p95` (semantic
+  gate is inherently slower than BM25-only).
+- Updated: all `test_default_heroes_*` / `test_*_default_policies_*`
+  acceptance tests to expect `post_edit_graph_refresh` in the default
+  set; `test_dispatch_complete_phase` (×2) + `test_dispatch_get_history`
+  for new kwarg defaults.
+- New positive tests: `test_get_node_not_indexed`,
+  `test_get_impact_not_indexed`,
+  `test_gibberish_query_returns_zero_above_threshold`,
+  `test_session_context_recent_decisions_preserve_file_path`,
+  `test_add_phase_replaces_pristine_placeholder`,
+  `test_log_session_idempotent_on_same_content`,
+  `test_log_session_auto_suffixes_on_different_content`,
+  `test_language_filter_strict_excludes_null_language`,
+  `test_language_filter_loose_includes_null_language`.
+
+### Deferred to v2.1.3 / v2.2
+
+- Full README rewrite with animated 60-second demo GIF (Item 15) — pair
+  with v2.2 launch / benchmark publishing once benchmark suite ships.
+- Bundled `coding-standards-<lang>.md` for Rust / Java / etc. — extend
+  the per-language playbook system as adopters request.
+
 ## [2.1.1] — 2026-05-17 — Hybrid decision search
 
 ### Added

{codevira-2.1.1/codevira.egg-info → codevira-2.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: codevira
-Version: 2.1.1
+Version: 2.1.2
 Summary: Stop re-explaining your project to AI agents every session. Codevira gives Claude Code, Cursor, Windsurf, and Antigravity shared persistent memory of your codebase — locally, no signup, MIT-licensed. One install configures every AI tool.
 Author-email: Sachin Shelke <sachin.worldnet@gmail.com>
 License: MIT
@@ -92,6 +92,35 @@ Your AI agent reads the same 12 files every session before doing any actual work
 
 ---
 
+## What's new in v2.1.2 — trust recovery
+
+v2.1.1 shipped hybrid search (BM25 + semantic) but without a similarity floor, so off-topic prompts kept surfacing irrelevant decisions. v2.1.2 is a **trust-recovery release** based on four independent field-test reports: every fix restores confidence in something codevira already does.
+
+| Area | What changed |
+|---|---|
+| **Smart similarity threshold** | `search_decisions` self-calibrates a per-project distance threshold from your protected decisions. Gibberish queries return zero results, not "least bad" matches. `codevira calibrate` to manually re-fit. |
+| **Honest cleanup** | `codevira reset --vectors / --graph / --all` replaces destructive `heal` flags (which `rm -rf`'d decisions). Decisions auto-exported to `<data_dir>/exports/` before any wipe. Typed confirmation required (`reset` / `graph` / `vectors` / `all`). |
+| **Backup-first by default** | `codevira export decisions [--format json|sql]` — standalone backup any time. |
+| **Proactive conflict detection** | New `check_conflict(decision_text)` MCP tool flags duplicate or contradictory decisions BEFORE you write. `record_decision` runs it automatically and surfaces `_conflict_warning`. |
+| **Enumerate decisions** | New `list_decisions(limit, since_date, file_pattern, protected_only, session_id, tags)` MCP tool. Closes the "remembers but can't list" gap. |
+| **Batch APIs** | `record_decisions([…])` + `write_session_logs([…])` cut memory-dump sessions from ~26 round trips to 1. |
+| **Tags + supersede** | Decisions can carry tags (`record_decision(tags=[…])`); `list_tags()` enumerates. `supersede_decision(old_id, new_decision, reason)` retires a prior decision with auditable history. |
+| **since= filter** | `search_decisions`, `get_history`, `get_session_context` all accept `since="YYYY-MM-DD"` so "what's new since I was last here" is a one-call query. |
+| **Rule extractor noise filter** | `top_signals.rules` no longer emits sliding-window n-grams as fake patterns. Stopwords + density gate + substring suppression. Skipped entirely on pre-code projects. |
+| **Cross-project rules leak fix** | `language IS NULL` rules no longer fan out to every project. A Go-project rule stays in the Go project. |
+| **Post-edit graph refresh** | New PostToolUse policy refreshes graph nodes after Edit/Write/MultiEdit so `get_node` / `get_impact` see current data without `index --full`. |
+| **Auto-clear placeholder phase** | `add_phase(phase=1, …)` on a fresh project silently replaces the bootstrap "Getting Started" stub instead of refusing as duplicate. |
+| **`complete_phase` enhancements** | `backfill=True` + `completed_at` for retroactive completion; `git_ref` to link to a commit/PR. `bulk_import_phases([…])` for migrating multi-phase git history in one call. |
+| **Hook regex precision** | Commit-message-shaped prompts (`feat(api):` / `fix:` / etc.) no longer trigger context injection. |
+| **Bundled non-Python playbooks** | `coding-standards-typescript.md`, `coding-standards-go.md`, `coding-standards-generic.md` auto-selected by detected language. |
+| **session_id collision** | `write_session_log` auto-suffixes on conflict and returns the actual id (vs silent overwrite). |
+| **`do_not_revert` echo** | When passed as a non-bool (int 1, string "true"), the response carries `_input_coerced_warning` so you see what got stored. |
+| **mypy baseline** | All 42 pre-existing type errors cleared; mypy is now a hard gate. |
+
+Full plan + design rationale: [docs/plans/v2.1.2.md](docs/plans/v2.1.2.md).
+
+---
+
 ## What's new in v2.0
 
 > 30-second demo: **[docs/demo/codevira-demo.mp4](docs/demo/codevira-demo.mp4)**
@@ -229,20 +258,35 @@ summary: 14 pass · 0 warn · 0 fail
 
 ### Daily-use commands you'll actually run
 
-| Command | What it does |
-|---|---|
-| `codevira setup` | Re-sync IDE configs (after installing a new AI tool, etc.) |
-| `codevira doctor` | Health check |
-| `codevira projects` | List every project codevira knows about on this machine |
-| `codevira projects --ghosts-only` | Find half-initialised project dirs |
-| `codevira clean --ghosts` | Remove ghost dirs (preserves real ones) |
-| `codevira insights` | Stable + reverted decisions across past sessions |
-| `codevira replay` | Decisions timeline (terminal / markdown / html output) |
-| `codevira budget` | Per-session token usage |
-| `codevira hooks list` | Show installed Claude Code lifecycle hooks |
+| Command | What it does | Since |
+|---|---|---|
+| `codevira setup` | Re-sync IDE configs (after installing a new AI tool, etc.) | v2.0 |
+| `codevira doctor` | Health check | v2.0 |
+| `codevira projects` | List every project codevira knows about on this machine | v2.0 |
+| `codevira projects --ghosts-only` | Find half-initialised project dirs | v2.0 |
+| `codevira clean --ghosts` | Remove ghost dirs AND truly-empty data dirs | v2.0 (+ v2.1.2 #14) |
+| `codevira clean --orphans` | Remove orphan data dirs AND bare global.db rows | v2.0 (+ v2.1.2 #13) |
+| `codevira insights` | Stable + reverted decisions across past sessions | v2.0 |
+| `codevira replay` | Decisions timeline (terminal / markdown / html output) | v2.0 |
+| `codevira budget` | Per-session token usage | v2.0 |
+| `codevira hooks list` | Show installed Claude Code lifecycle hooks | v2.0 |
+| `codevira heal --decisions` | Backfill semantic embeddings for existing decisions | v2.1.0 |
+| `codevira reset --vectors/--graph/--all` | Destructive cleanup (auto-exports decisions first) | **v2.1.2** |
+| `codevira export decisions [--format json\|sql]` | Standalone backup of decisions / outcomes / preferences | **v2.1.2** |
+| `codevira calibrate` | Re-fit per-project similarity threshold | **v2.1.2** |
 
 Run `codevira --help` for the full subcommand list.
 
+### What's production-stable vs best-effort
+
+| Production-stable | Best-effort / coming soon |
+|---|---|
+| Cross-tool decision memory (search_decisions, get_session_context) | Multi-language code graph for languages OTHER than Python / TypeScript / Go / Rust / Java / C# / Ruby / C++ / Kotlin / Swift / PHP / JS — extend via tree-sitter language pack |
+| do_not_revert guarding via Decision Lock + Anti-Regression hero | Animated demo GIF (coming v2.2 launch) |
+| Hybrid BM25 + semantic search with self-calibrating threshold | Native MCP Apps UI (`ui://` URIs) — when MCP SDK exposes the scheme |
+| Per-project + cross-project preferences via global.db | Real-time multi-machine sync — local-first is by design; if you need it, export/import is the path |
+| All MCP tools (graph, roadmap, changesets, learning, decisions) | Web UI for browsing decisions (use the `codevira://decisions` MCP resource in Claude Desktop today) |
+
 ### Customizing what's indexed
 
 By default codevira indexes every common source / config / docs extension

{codevira-2.1.1 → codevira-2.1.2}/README.md

@@ -45,6 +45,35 @@ Your AI agent reads the same 12 files every session before doing any actual work
 
 ---
 
+## What's new in v2.1.2 — trust recovery
+
+v2.1.1 shipped hybrid search (BM25 + semantic) but without a similarity floor, so off-topic prompts kept surfacing irrelevant decisions. v2.1.2 is a **trust-recovery release** based on four independent field-test reports: every fix restores confidence in something codevira already does.
+
+| Area | What changed |
+|---|---|
+| **Smart similarity threshold** | `search_decisions` self-calibrates a per-project distance threshold from your protected decisions. Gibberish queries return zero results, not "least bad" matches. `codevira calibrate` to manually re-fit. |
+| **Honest cleanup** | `codevira reset --vectors / --graph / --all` replaces destructive `heal` flags (which `rm -rf`'d decisions). Decisions auto-exported to `<data_dir>/exports/` before any wipe. Typed confirmation required (`reset` / `graph` / `vectors` / `all`). |
+| **Backup-first by default** | `codevira export decisions [--format json|sql]` — standalone backup any time. |
+| **Proactive conflict detection** | New `check_conflict(decision_text)` MCP tool flags duplicate or contradictory decisions BEFORE you write. `record_decision` runs it automatically and surfaces `_conflict_warning`. |
+| **Enumerate decisions** | New `list_decisions(limit, since_date, file_pattern, protected_only, session_id, tags)` MCP tool. Closes the "remembers but can't list" gap. |
+| **Batch APIs** | `record_decisions([…])` + `write_session_logs([…])` cut memory-dump sessions from ~26 round trips to 1. |
+| **Tags + supersede** | Decisions can carry tags (`record_decision(tags=[…])`); `list_tags()` enumerates. `supersede_decision(old_id, new_decision, reason)` retires a prior decision with auditable history. |
+| **since= filter** | `search_decisions`, `get_history`, `get_session_context` all accept `since="YYYY-MM-DD"` so "what's new since I was last here" is a one-call query. |
+| **Rule extractor noise filter** | `top_signals.rules` no longer emits sliding-window n-grams as fake patterns. Stopwords + density gate + substring suppression. Skipped entirely on pre-code projects. |
+| **Cross-project rules leak fix** | `language IS NULL` rules no longer fan out to every project. A Go-project rule stays in the Go project. |
+| **Post-edit graph refresh** | New PostToolUse policy refreshes graph nodes after Edit/Write/MultiEdit so `get_node` / `get_impact` see current data without `index --full`. |
+| **Auto-clear placeholder phase** | `add_phase(phase=1, …)` on a fresh project silently replaces the bootstrap "Getting Started" stub instead of refusing as duplicate. |
+| **`complete_phase` enhancements** | `backfill=True` + `completed_at` for retroactive completion; `git_ref` to link to a commit/PR. `bulk_import_phases([…])` for migrating multi-phase git history in one call. |
+| **Hook regex precision** | Commit-message-shaped prompts (`feat(api):` / `fix:` / etc.) no longer trigger context injection. |
+| **Bundled non-Python playbooks** | `coding-standards-typescript.md`, `coding-standards-go.md`, `coding-standards-generic.md` auto-selected by detected language. |
+| **session_id collision** | `write_session_log` auto-suffixes on conflict and returns the actual id (vs silent overwrite). |
+| **`do_not_revert` echo** | When passed as a non-bool (int 1, string "true"), the response carries `_input_coerced_warning` so you see what got stored. |
+| **mypy baseline** | All 42 pre-existing type errors cleared; mypy is now a hard gate. |
+
+Full plan + design rationale: [docs/plans/v2.1.2.md](docs/plans/v2.1.2.md).
+
+---
+
 ## What's new in v2.0
 
 > 30-second demo: **[docs/demo/codevira-demo.mp4](docs/demo/codevira-demo.mp4)**
@@ -182,20 +211,35 @@ summary: 14 pass · 0 warn · 0 fail
 
 ### Daily-use commands you'll actually run
 
-| Command | What it does |
-|---|---|
-| `codevira setup` | Re-sync IDE configs (after installing a new AI tool, etc.) |
-| `codevira doctor` | Health check |
-| `codevira projects` | List every project codevira knows about on this machine |
-| `codevira projects --ghosts-only` | Find half-initialised project dirs |
-| `codevira clean --ghosts` | Remove ghost dirs (preserves real ones) |
-| `codevira insights` | Stable + reverted decisions across past sessions |
-| `codevira replay` | Decisions timeline (terminal / markdown / html output) |
-| `codevira budget` | Per-session token usage |
-| `codevira hooks list` | Show installed Claude Code lifecycle hooks |
+| Command | What it does | Since |
+|---|---|---|
+| `codevira setup` | Re-sync IDE configs (after installing a new AI tool, etc.) | v2.0 |
+| `codevira doctor` | Health check | v2.0 |
+| `codevira projects` | List every project codevira knows about on this machine | v2.0 |
+| `codevira projects --ghosts-only` | Find half-initialised project dirs | v2.0 |
+| `codevira clean --ghosts` | Remove ghost dirs AND truly-empty data dirs | v2.0 (+ v2.1.2 #14) |
+| `codevira clean --orphans` | Remove orphan data dirs AND bare global.db rows | v2.0 (+ v2.1.2 #13) |
+| `codevira insights` | Stable + reverted decisions across past sessions | v2.0 |
+| `codevira replay` | Decisions timeline (terminal / markdown / html output) | v2.0 |
+| `codevira budget` | Per-session token usage | v2.0 |
+| `codevira hooks list` | Show installed Claude Code lifecycle hooks | v2.0 |
+| `codevira heal --decisions` | Backfill semantic embeddings for existing decisions | v2.1.0 |
+| `codevira reset --vectors/--graph/--all` | Destructive cleanup (auto-exports decisions first) | **v2.1.2** |
+| `codevira export decisions [--format json\|sql]` | Standalone backup of decisions / outcomes / preferences | **v2.1.2** |
+| `codevira calibrate` | Re-fit per-project similarity threshold | **v2.1.2** |
 
 Run `codevira --help` for the full subcommand list.
 
+### What's production-stable vs best-effort
+
+| Production-stable | Best-effort / coming soon |
+|---|---|
+| Cross-tool decision memory (search_decisions, get_session_context) | Multi-language code graph for languages OTHER than Python / TypeScript / Go / Rust / Java / C# / Ruby / C++ / Kotlin / Swift / PHP / JS — extend via tree-sitter language pack |
+| do_not_revert guarding via Decision Lock + Anti-Regression hero | Animated demo GIF (coming v2.2 launch) |
+| Hybrid BM25 + semantic search with self-calibrating threshold | Native MCP Apps UI (`ui://` URIs) — when MCP SDK exposes the scheme |
+| Per-project + cross-project preferences via global.db | Real-time multi-machine sync — local-first is by design; if you need it, export/import is the path |
+| All MCP tools (graph, roadmap, changesets, learning, decisions) | Web UI for browsing decisions (use the `codevira://decisions` MCP resource in Claude Desktop today) |
+
 ### Customizing what's indexed
 
 By default codevira indexes every common source / config / docs extension

{codevira-2.1.1 → codevira-2.1.2/codevira.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: codevira
-Version: 2.1.1
+Version: 2.1.2
 Summary: Stop re-explaining your project to AI agents every session. Codevira gives Claude Code, Cursor, Windsurf, and Antigravity shared persistent memory of your codebase — locally, no signup, MIT-licensed. One install configures every AI tool.
 Author-email: Sachin Shelke <sachin.worldnet@gmail.com>
 License: MIT
@@ -92,6 +92,35 @@ Your AI agent reads the same 12 files every session before doing any actual work
 
 ---
 
+## What's new in v2.1.2 — trust recovery
+
+v2.1.1 shipped hybrid search (BM25 + semantic) but without a similarity floor, so off-topic prompts kept surfacing irrelevant decisions. v2.1.2 is a **trust-recovery release** based on four independent field-test reports: every fix restores confidence in something codevira already does.
+
+| Area | What changed |
+|---|---|
+| **Smart similarity threshold** | `search_decisions` self-calibrates a per-project distance threshold from your protected decisions. Gibberish queries return zero results, not "least bad" matches. `codevira calibrate` to manually re-fit. |
+| **Honest cleanup** | `codevira reset --vectors / --graph / --all` replaces destructive `heal` flags (which `rm -rf`'d decisions). Decisions auto-exported to `<data_dir>/exports/` before any wipe. Typed confirmation required (`reset` / `graph` / `vectors` / `all`). |
+| **Backup-first by default** | `codevira export decisions [--format json|sql]` — standalone backup any time. |
+| **Proactive conflict detection** | New `check_conflict(decision_text)` MCP tool flags duplicate or contradictory decisions BEFORE you write. `record_decision` runs it automatically and surfaces `_conflict_warning`. |
+| **Enumerate decisions** | New `list_decisions(limit, since_date, file_pattern, protected_only, session_id, tags)` MCP tool. Closes the "remembers but can't list" gap. |
+| **Batch APIs** | `record_decisions([…])` + `write_session_logs([…])` cut memory-dump sessions from ~26 round trips to 1. |
+| **Tags + supersede** | Decisions can carry tags (`record_decision(tags=[…])`); `list_tags()` enumerates. `supersede_decision(old_id, new_decision, reason)` retires a prior decision with auditable history. |
+| **since= filter** | `search_decisions`, `get_history`, `get_session_context` all accept `since="YYYY-MM-DD"` so "what's new since I was last here" is a one-call query. |
+| **Rule extractor noise filter** | `top_signals.rules` no longer emits sliding-window n-grams as fake patterns. Stopwords + density gate + substring suppression. Skipped entirely on pre-code projects. |
+| **Cross-project rules leak fix** | `language IS NULL` rules no longer fan out to every project. A Go-project rule stays in the Go project. |
+| **Post-edit graph refresh** | New PostToolUse policy refreshes graph nodes after Edit/Write/MultiEdit so `get_node` / `get_impact` see current data without `index --full`. |
+| **Auto-clear placeholder phase** | `add_phase(phase=1, …)` on a fresh project silently replaces the bootstrap "Getting Started" stub instead of refusing as duplicate. |
+| **`complete_phase` enhancements** | `backfill=True` + `completed_at` for retroactive completion; `git_ref` to link to a commit/PR. `bulk_import_phases([…])` for migrating multi-phase git history in one call. |
+| **Hook regex precision** | Commit-message-shaped prompts (`feat(api):` / `fix:` / etc.) no longer trigger context injection. |
+| **Bundled non-Python playbooks** | `coding-standards-typescript.md`, `coding-standards-go.md`, `coding-standards-generic.md` auto-selected by detected language. |
+| **session_id collision** | `write_session_log` auto-suffixes on conflict and returns the actual id (vs silent overwrite). |
+| **`do_not_revert` echo** | When passed as a non-bool (int 1, string "true"), the response carries `_input_coerced_warning` so you see what got stored. |
+| **mypy baseline** | All 42 pre-existing type errors cleared; mypy is now a hard gate. |
+
+Full plan + design rationale: [docs/plans/v2.1.2.md](docs/plans/v2.1.2.md).
+
+---
+
 ## What's new in v2.0
 
 > 30-second demo: **[docs/demo/codevira-demo.mp4](docs/demo/codevira-demo.mp4)**
@@ -229,20 +258,35 @@ summary: 14 pass · 0 warn · 0 fail
 
 ### Daily-use commands you'll actually run
 
-| Command | What it does |
-|---|---|
-| `codevira setup` | Re-sync IDE configs (after installing a new AI tool, etc.) |
-| `codevira doctor` | Health check |
-| `codevira projects` | List every project codevira knows about on this machine |
-| `codevira projects --ghosts-only` | Find half-initialised project dirs |
-| `codevira clean --ghosts` | Remove ghost dirs (preserves real ones) |
-| `codevira insights` | Stable + reverted decisions across past sessions |
-| `codevira replay` | Decisions timeline (terminal / markdown / html output) |
-| `codevira budget` | Per-session token usage |
-| `codevira hooks list` | Show installed Claude Code lifecycle hooks |
+| Command | What it does | Since |
+|---|---|---|
+| `codevira setup` | Re-sync IDE configs (after installing a new AI tool, etc.) | v2.0 |
+| `codevira doctor` | Health check | v2.0 |
+| `codevira projects` | List every project codevira knows about on this machine | v2.0 |
+| `codevira projects --ghosts-only` | Find half-initialised project dirs | v2.0 |
+| `codevira clean --ghosts` | Remove ghost dirs AND truly-empty data dirs | v2.0 (+ v2.1.2 #14) |
+| `codevira clean --orphans` | Remove orphan data dirs AND bare global.db rows | v2.0 (+ v2.1.2 #13) |
+| `codevira insights` | Stable + reverted decisions across past sessions | v2.0 |
+| `codevira replay` | Decisions timeline (terminal / markdown / html output) | v2.0 |
+| `codevira budget` | Per-session token usage | v2.0 |
+| `codevira hooks list` | Show installed Claude Code lifecycle hooks | v2.0 |
+| `codevira heal --decisions` | Backfill semantic embeddings for existing decisions | v2.1.0 |
+| `codevira reset --vectors/--graph/--all` | Destructive cleanup (auto-exports decisions first) | **v2.1.2** |
+| `codevira export decisions [--format json\|sql]` | Standalone backup of decisions / outcomes / preferences | **v2.1.2** |
+| `codevira calibrate` | Re-fit per-project similarity threshold | **v2.1.2** |
 
 Run `codevira --help` for the full subcommand list.
 
+### What's production-stable vs best-effort
+
+| Production-stable | Best-effort / coming soon |
+|---|---|
+| Cross-tool decision memory (search_decisions, get_session_context) | Multi-language code graph for languages OTHER than Python / TypeScript / Go / Rust / Java / C# / Ruby / C++ / Kotlin / Swift / PHP / JS — extend via tree-sitter language pack |
+| do_not_revert guarding via Decision Lock + Anti-Regression hero | Animated demo GIF (coming v2.2 launch) |
+| Hybrid BM25 + semantic search with self-calibrating threshold | Native MCP Apps UI (`ui://` URIs) — when MCP SDK exposes the scheme |
+| Per-project + cross-project preferences via global.db | Real-time multi-machine sync — local-first is by design; if you need it, export/import is the path |
+| All MCP tools (graph, roadmap, changesets, learning, decisions) | Web UI for browsing decisions (use the `codevira://decisions` MCP resource in Claude Desktop today) |
+
 ### Customizing what's indexed
 
 By default codevira indexes every common source / config / docs extension

{codevira-2.1.1 → codevira-2.1.2}/codevira.egg-info/SOURCES.txt

@@ -58,6 +58,8 @@ docs/heroes/10-ai-promotion.md
 docs/heroes/README.md
 docs/heroes/pillar-1-setup.md
 docs/internal/competitive-landscape.md
+docs/plans/v2.1.2.md
+docs/troubleshooting/antigravity.md
 graph/_schema.yaml
 indexer/__init__.py
 indexer/_dedupe_migration.py
@@ -84,7 +86,9 @@ mcp_server/auto_init.py
 mcp_server/cli.py
 mcp_server/cli_agents.py
 mcp_server/cli_budget.py
+mcp_server/cli_calibrate.py
 mcp_server/cli_configure.py
+mcp_server/cli_export.py
 mcp_server/cli_hooks_admin.py
 mcp_server/cli_insights.py
 mcp_server/cli_projects.py
@@ -119,6 +123,9 @@ mcp_server/data/hooks/pre_tool_use.sh
 mcp_server/data/hooks/session_start.sh
 mcp_server/data/hooks/stop.sh
 mcp_server/data/hooks/user_prompt_submit.sh
+mcp_server/data/rules/coding-standards-generic.md
+mcp_server/data/rules/coding-standards-go.md
+mcp_server/data/rules/coding-standards-typescript.md
 mcp_server/data/rules/coding-standards.md
 mcp_server/data/rules/engineering-excellence.md
 mcp_server/data/rules/git-cicd-governance.md
@@ -156,6 +163,7 @@ mcp_server/engine/policies/cross_session.py
 mcp_server/engine/policies/decision_lock.py
 mcp_server/engine/policies/intent_inference.py
 mcp_server/engine/policies/live_style.py
+mcp_server/engine/policies/post_edit_refresh.py
 mcp_server/engine/policies/scope_contract.py
 mcp_server/engine/policies/token_budget.py
 mcp_server/engine/wiring/__init__.py
@@ -164,6 +172,7 @@ mcp_server/engine/wiring/mcp_dispatch.py
 mcp_server/tools/__init__.py
 mcp_server/tools/_decision_embeddings.py
 mcp_server/tools/changesets.py
+mcp_server/tools/check_conflict.py
 mcp_server/tools/code_reader.py
 mcp_server/tools/graph.py
 mcp_server/tools/learning.py