From ae1c3e3b05140588d5e03ae7828f24566fb0078c Mon Sep 17 00:00:00 2001 From: teernisse Date: Wed, 18 Feb 2026 23:59:11 -0500 Subject: [PATCH] chore: update beads tracking Sync beads issue database to reflect current project state. --- .beads/issues.jsonl | 2 ++ .beads/last-touched | 2 +- crates/lore-tui/src/state/who.rs | 12 ++++++++++++ 3 files changed, 15 insertions(+), 1 deletion(-) diff --git a/.beads/issues.jsonl b/.beads/issues.jsonl index ae87d97..b1a966f 100644 --- a/.beads/issues.jsonl +++ b/.beads/issues.jsonl @@ -247,6 +247,7 @@ {"id":"bd-3qm","title":"[CP1] Final validation - tests, smoke tests, integrity checks","description":"Run all tests and perform data integrity checks.\n\nValidation steps:\n1. Run all unit tests (vitest)\n2. Run all integration tests\n3. Run ESLint\n4. Run TypeScript strict check\n5. Manual smoke tests per PRD table\n6. Data integrity SQL checks:\n - Issue count matches GitLab\n - Every issue has raw_payload\n - Labels in junction exist in labels table\n - sync_cursors has entry per project\n - Re-run fetches 0 new items\n - Discussion count > 0\n - Every discussion has >= 1 note\n - individual_note=true has exactly 1 note\n\nFiles: All CP1 files\nDone when: All gate criteria from Definition of Done pass","status":"tombstone","priority":2,"issue_type":"task","created_at":"2026-01-25T15:20:51.994183Z","created_by":"tayloreernisse","updated_at":"2026-01-25T15:21:35.152852Z","closed_at":"2026-01-25T15:21:35.152852Z","deleted_at":"2026-01-25T15:21:35.152849Z","deleted_by":"tayloreernisse","delete_reason":"delete","original_type":"task","compaction_level":0,"original_size":0} {"id":"bd-3qn6","title":"Rewrite who --path to use mr_file_changes for authorship signal","description":"## Problem\n\nwho --path currently only queries DiffNote records (notes.position_new_path), so it only finds people who left inline review comments on that exact file. This is highly misleading -- it reports 'no experts' for files that have been actively authored and reviewed, just without inline comments on that specific path.\n\n## Solution\n\nRewrite query_expert() to incorporate mr_file_changes as a primary signal source:\n\n1. MR authorship signal: JOIN mr_file_changes to find MR authors who touched the file (strongest signal)\n2. MR reviewer signal: JOIN mr_file_changes + merge_request_reviewers to find reviewers of MRs that touched the file (even without DiffNotes on that file)\n3. DiffNote signal: Keep existing DiffNote query as a supplementary signal (inline comments show deep familiarity)\n\n### Scoring weights (to tune):\n- MR author who touched the file: 15 points per MR\n- MR reviewer of MR touching the file: 10 points per MR\n- DiffNote reviewer on that file: 20 points per MR + 1 per note (existing)\n- DiffNote MR author: 12 points per MR (existing)\n\n### Path matching:\n- Reuse build_path_query() but extend DB probes to also check mr_file_changes.new_path\n- For prefix matching, LIKE on mr_file_changes.new_path\n\n### Also fix:\n- build_path_query() probes should check mr_file_changes in addition to notes, so path resolution works even when no DiffNotes exist\n\n## Acceptance Criteria\n- who --path returns results for files touched in MRs even without DiffNotes\n- Existing DiffNote-based scoring still contributes\n- build_path_query probes mr_file_changes for path existence\n- Tests cover: MR-only authorship, DiffNote-only, combined scoring\n- Robot mode JSON output unchanged (same schema)","status":"closed","priority":2,"issue_type":"task","created_at":"2026-02-08T18:16:41.991344Z","created_by":"tayloreernisse","updated_at":"2026-02-08T18:34:25.704024Z","closed_at":"2026-02-08T18:34:25.703965Z","close_reason":"Rewrote query_expert() and query_overlap() in who.rs to incorporate mr_file_changes + mr_reviewers as signal sources alongside existing DiffNote data. Uses 4-branch UNION ALL with COUNT(DISTINCT CASE) for proper deduplication across signal types. 8 new tests, all 397 pass.","compaction_level":0,"original_size":0,"labels":["cli","phase-b","who"],"dependencies":[{"issue_id":"bd-3qn6","depends_on_id":"bd-2yo","type":"blocks","created_at":"2026-02-12T19:34:59Z","created_by":"import"}]} {"id":"bd-3qs","title":"Implement lore generate-docs CLI command","description":"## Background\nThe generate-docs CLI command is the user-facing wrapper around the document regeneration pipeline. It has two modes: incremental (default, processes dirty_sources queue only) and full (seeds dirty_sources with ALL entities, then drains). Both modes use the same regenerator codepath to avoid logic divergence. Full mode uses keyset pagination (WHERE id > last_id) for seeding to avoid O(n^2) OFFSET degradation on large tables.\n\n## Approach\nCreate `src/cli/commands/generate_docs.rs` per PRD Section 2.4.\n\n**Core function:**\n```rust\npub fn run_generate_docs(\n config: &Config,\n full: bool,\n project_filter: Option<&str>,\n) -> Result\n```\n\n**Full mode seeding (keyset pagination):**\n```rust\nconst FULL_MODE_CHUNK_SIZE: usize = 2000;\n\n// For each source type (issues, MRs, discussions):\nlet mut last_id: i64 = 0;\nloop {\n let tx = conn.transaction()?;\n let inserted = tx.execute(\n \"INSERT INTO dirty_sources (source_type, source_id, queued_at, ...)\n SELECT 'issue', id, ?, 0, NULL, NULL, NULL\n FROM issues WHERE id > ? ORDER BY id LIMIT ?\n ON CONFLICT(source_type, source_id) DO NOTHING\",\n params![now_ms(), last_id, FULL_MODE_CHUNK_SIZE],\n )?;\n if inserted == 0 { tx.commit()?; break; }\n // Advance keyset cursor...\n tx.commit()?;\n}\n```\n\n**After draining (full mode only):**\n```sql\nINSERT INTO documents_fts(documents_fts) VALUES('optimize')\n```\n\n**CLI args:**\n```rust\n#[derive(Args)]\npub struct GenerateDocsArgs {\n #[arg(long)]\n full: bool,\n #[arg(long)]\n project: Option,\n}\n```\n\n**Output:** Human-readable table + JSON robot mode.\n\n## Acceptance Criteria\n- [ ] Default mode (no --full): processes only existing dirty_sources entries\n- [ ] --full mode: seeds dirty_sources with ALL issues, MRs, and discussions\n- [ ] Full mode uses keyset pagination (WHERE id > last_id, not OFFSET)\n- [ ] Full mode chunk size is 2000\n- [ ] Full mode does FTS optimize after completion\n- [ ] Both modes use regenerate_dirty_documents() (same codepath)\n- [ ] Progress bar shown in human mode (via indicatif)\n- [ ] JSON output in robot mode with GenerateDocsResult\n- [ ] GenerateDocsResult has issues/mrs/discussions/total/truncated/skipped counts\n- [ ] `cargo build` succeeds\n\n## Files\n- `src/cli/commands/generate_docs.rs` — new file\n- `src/cli/commands/mod.rs` — add `pub mod generate_docs;`\n- `src/cli/mod.rs` — add GenerateDocsArgs, wire up generate-docs subcommand\n- `src/main.rs` — add generate-docs command handler\n\n## TDD Loop\nRED: Integration test with seeded DB\nGREEN: Implement run_generate_docs with seeding + drain\nVERIFY: `cargo build && cargo test generate_docs`\n\n## Edge Cases\n- Empty database (no issues/MRs/discussions): full mode seeds nothing, returns all-zero counts\n- --project filter in full mode: only seed dirty_sources for entities in that project\n- Interrupted full mode: dirty_sources entries persist (ON CONFLICT DO NOTHING), resume by re-running\n- FTS optimize on empty FTS table: no-op (safe)","status":"closed","priority":2,"issue_type":"task","created_at":"2026-01-30T15:25:55.226666Z","created_by":"tayloreernisse","updated_at":"2026-01-30T17:49:23.397157Z","closed_at":"2026-01-30T17:49:23.397098Z","close_reason":"Implemented generate-docs command with incremental + full mode, keyset pagination seeding, FTS optimize, project filter, human + JSON output. Builds clean.","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-3qs","depends_on_id":"bd-1u1","type":"blocks","created_at":"2026-02-12T19:34:59Z","created_by":"import"},{"issue_id":"bd-3qs","depends_on_id":"bd-221","type":"blocks","created_at":"2026-02-12T19:34:59Z","created_by":"import"}]} +{"id":"bd-3rjw","title":"Implement entity cache for near-instant detail view reopens","status":"open","priority":2,"issue_type":"task","created_at":"2026-02-19T04:52:57.031699Z","created_by":"tayloreernisse","updated_at":"2026-02-19T04:53:03.010166Z","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-3rjw","depends_on_id":"bd-3t6r","type":"blocks","created_at":"2026-02-19T04:53:03.010140Z","created_by":"tayloreernisse"}]} {"id":"bd-3rl","title":"Epic: Gate C - Sync MVP","description":"## Background\nGate C adds the sync orchestrator and queue infrastructure that makes the search pipeline incremental and self-maintaining. It introduces dirty source tracking (change detection during ingestion), the discussion fetch queue, and the unified lore sync command that orchestrates the full pipeline. Gate C also adds integrity checks and repair paths.\n\n## Gate C Deliverables\n1. Orchestrated lore sync command with incremental doc regen + re-embedding\n2. Integrity checks + repair paths for FTS/embeddings consistency\n\n## Bead Dependencies (execution order, after Gate A)\n1. **bd-mem** — Shared backoff utility (no deps, shared with Gate B)\n2. **bd-38q** — Dirty source tracking (blocked by bd-36p, bd-hrs, bd-mem)\n3. **bd-1je** — Discussion queue (blocked by bd-hrs, bd-mem)\n4. **bd-1i2** — Integrate dirty tracking into ingestion (blocked by bd-38q)\n5. **bd-1x6** — Sync CLI (blocked by bd-38q, bd-1je, bd-1i2, bd-3qs, bd-2sx)\n\n## Acceptance Criteria\n- [ ] `lore sync` runs full pipeline: ingest -> generate-docs -> embed\n- [ ] `lore sync --full` does full re-sync + regeneration\n- [ ] `lore sync --no-embed` skips embedding stage\n- [ ] Dirty tracking: upserted entities automatically marked for regeneration\n- [ ] Queue draining: dirty_sources fully drained in bounded batch loop\n- [ ] Backoff: failed items use exponential backoff with jitter\n- [ ] `lore stats --check` detects inconsistencies\n- [ ] `lore stats --repair` fixes FTS/embedding inconsistencies","status":"closed","priority":1,"issue_type":"task","created_at":"2026-01-30T15:25:13.494698Z","created_by":"tayloreernisse","updated_at":"2026-01-30T18:05:52.121666Z","closed_at":"2026-01-30T18:05:52.121619Z","close_reason":"All Gate C sub-beads complete: backoff utility, dirty tracking, discussion queue, ingestion integration, sync CLI, stats CLI","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-3rl","depends_on_id":"bd-1x6","type":"blocks","created_at":"2026-02-12T19:34:59Z","created_by":"import"},{"issue_id":"bd-3rl","depends_on_id":"bd-pr1","type":"blocks","created_at":"2026-02-12T19:34:59Z","created_by":"import"}]} {"id":"bd-3sez","title":"Create surgical.rs core module with preflight fetch, ingest functions, and TOCTOU guards","description":"## Background\n\nThe surgical sync pipeline needs a core module (`src/ingestion/surgical.rs`) that fetches a single issue or MR by IID from GitLab and ingests it into the local SQLite database. This replaces the bulk pagination path (`ingest_issues`/`ingest_merge_requests`) for targeted, on-demand sync of specific entities.\n\nKey constraints:\n- `process_single_issue` (issues.rs:143) and `process_single_mr` (merge_requests.rs:144) are private functions. This bead wraps them with pub(crate) entry points that add TOCTOU guard logic and dirty marking.\n- `updated_at` is a `String` (ISO 8601) in `GitLabIssue`/`GitLabMergeRequest` but stored as `INTEGER` (ms-epoch) in the DB. The TOCTOU guard must parse the ISO string to ms-epoch for comparison.\n- `ProcessMrResult` (merge_requests.rs:138) is a private struct. The MR ingest wrapper returns its own result type or re-exports the needed fields.\n- `SyncRunRecorder` has `succeed()` and `fail()` that consume `self`. Not needed here since surgical.rs is called from the orchestrator which owns the recorder.\n\n## Approach\n\nCreate `src/ingestion/surgical.rs` with:\n\n1. **`preflight_fetch`** (async): Takes `&GitLabClient`, `gitlab_project_id`, and a list of `(entity_type, iid)` targets. Calls `client.get_issue_by_iid()` and `client.get_mr_by_iid()` (from bd-159p). Returns `PreflightResult { issues: Vec, merge_requests: Vec, failures: Vec }`.\n\n2. **`ingest_issue_by_iid`** (sync): Takes `&Connection`, `&Config`, `project_id`, `&GitLabIssue`. Applies TOCTOU guard (compare payload `updated_at` parsed to ms-epoch vs DB `updated_at`), then calls `process_single_issue` (requires making it `pub(crate)` in bd-1sc6), marks dirty via `dirty_tracker::mark_dirty(conn, SourceType::Issue, local_issue_id)`, and returns `IngestIssueResult { upserted: bool, labels_created: usize, skipped_stale: bool, dirty_source_keys: Vec<(SourceType, i64)> }`.\n\n3. **`ingest_mr_by_iid`** (sync): Same pattern for MRs. Calls `process_single_mr` (requires `pub(crate)` in bd-1sc6), returns `IngestMrResult { upserted: bool, labels_created: usize, assignees_linked: usize, reviewers_linked: usize, skipped_stale: bool, dirty_source_keys: Vec<(SourceType, i64)> }`.\n\n4. **TOCTOU guard**: `fn is_stale(payload_updated_at: &str, db_updated_at_ms: Option) -> Result`. Parses ISO 8601 string to ms-epoch using `chrono::DateTime::parse_from_rfc3339`. Returns `true` if `payload_ms <= db_ms` (payload is same age or older than what we already have).\n\nWire the module in `src/ingestion/mod.rs`.\n\n## Acceptance Criteria\n\n- [ ] `preflight_fetch` calls GitLabClient by-IID methods and collects successes + failures\n- [ ] `ingest_issue_by_iid` wraps `process_single_issue` with TOCTOU guard and dirty marking\n- [ ] `ingest_mr_by_iid` wraps `process_single_mr` with TOCTOU guard and dirty marking\n- [ ] TOCTOU guard correctly parses ISO 8601 String to ms-epoch for comparison with DB i64\n- [ ] Stale payloads (payload updated_at <= DB updated_at) are skipped, not ingested\n- [ ] `dirty_source_keys` returned include the `(SourceType, source_id)` tuples for downstream scoped doc regen\n- [ ] Module registered in `src/ingestion/mod.rs`\n- [ ] All tests from bd-x8oq pass\n\n## Files\n\n- `src/ingestion/surgical.rs` (NEW)\n- `src/ingestion/mod.rs` (add `pub(crate) mod surgical;`)\n- `src/ingestion/issues.rs` (change `process_single_issue` to `pub(crate)` — done in bd-1sc6)\n- `src/ingestion/merge_requests.rs` (change `process_single_mr` and `ProcessMrResult` to `pub(crate)` — done in bd-1sc6)\n\n## TDD Anchor\n\nTests live in bd-x8oq (`src/ingestion/surgical_tests.rs`), referenced via `#[cfg(test)] #[path = \"surgical_tests.rs\"] mod tests;` in surgical.rs. Key tests that validate this bead:\n\n- `test_ingest_issue_by_iid_upserts_and_marks_dirty` — verifies full issue ingest path + dirty marking\n- `test_ingest_mr_by_iid_upserts_and_marks_dirty` — verifies full MR ingest path + dirty marking\n- `test_toctou_skips_stale_issue` — inserts issue with updated_at=T1, calls ingest with payload updated_at=T1, asserts skipped_stale=true\n- `test_toctou_skips_stale_mr` — same for MRs\n- `test_toctou_allows_newer_issue` — payload T2 > DB T1, asserts upserted=true\n- `test_is_stale_parses_iso8601` — unit test for the ISO 8601 to ms-epoch parsing\n- `test_is_stale_handles_none_db_value` — first ingest (no existing row), should return false (not stale)\n- `test_preflight_fetch_returns_issues_and_mrs` — wiremock test for successful preflight\n- `test_preflight_fetch_collects_failures` — wiremock 404 returns failure, not error\n\n## Edge Cases\n\n- ISO 8601 with timezone offset (GitLab returns `+00:00` not `Z`) must parse correctly\n- First-ever ingest of an IID: no existing DB row, TOCTOU guard must treat as \"not stale\" (db_updated_at is None)\n- GitLab returns 404 for a deleted issue/MR during preflight: failure, not hard error\n- Concurrent surgical syncs for same IID: `process_single_issue` uses `unchecked_transaction()` with UPSERT, so last-writer-wins is safe\n- `process_single_mr` returns `ProcessMrResult` which is private: either make it `pub(crate)` in bd-1sc6 or replicate needed fields\n\n## Dependency Context\n\n- **Blocked by bd-159p**: `get_issue_by_iid` and `get_mr_by_iid` on GitLabClient (preflight needs these)\n- **Blocked by bd-1sc6**: Visibility changes to `process_single_issue`, `process_single_mr`, `ProcessMrResult` (must be `pub(crate)`)\n- **Blocks bd-1i4i**: Orchestration function calls `preflight_fetch` + `ingest_issue_by_iid` / `ingest_mr_by_iid`\n- **Blocks bd-kanh**: Dependent helpers are called after ingest to fetch discussions, resource events, etc.\n- **Blocks bd-wcja**: SyncResult surgical fields depend on return types from this module\n- **Co-depends with bd-x8oq**: Tests for this code live in that bead's test file","status":"open","priority":2,"issue_type":"task","created_at":"2026-02-17T19:14:19.449695Z","created_by":"tayloreernisse","updated_at":"2026-02-17T20:02:01.692160Z","compaction_level":0,"original_size":0,"labels":["surgical-sync"],"dependencies":[{"issue_id":"bd-3sez","depends_on_id":"bd-1i4i","type":"blocks","created_at":"2026-02-18T17:42:00Z","created_by":"import"},{"issue_id":"bd-3sez","depends_on_id":"bd-3jqx","type":"blocks","created_at":"2026-02-18T17:42:00Z","created_by":"import"},{"issue_id":"bd-3sez","depends_on_id":"bd-kanh","type":"blocks","created_at":"2026-02-18T17:42:00Z","created_by":"import"},{"issue_id":"bd-3sez","depends_on_id":"bd-wcja","type":"blocks","created_at":"2026-02-18T17:42:00Z","created_by":"import"},{"issue_id":"bd-3sez","depends_on_id":"bd-x8oq","type":"blocks","created_at":"2026-02-18T17:42:00Z","created_by":"import"}]} {"id":"bd-3sh","title":"Add 'lore count events' command with robot mode","description":"## Background\nNeed to verify event ingestion and report counts by type. The existing count command (src/cli/commands/count.rs) handles issues, mrs, discussions, notes with both human and robot output. This adds 'events' as a new count subcommand.\n\n## Approach\nExtend the existing count command in src/cli/commands/count.rs:\n\n1. Add CountTarget::Events variant (or string match) in the count dispatcher\n2. Query each event table with GROUP BY entity type:\n```sql\nSELECT \n CASE WHEN issue_id IS NOT NULL THEN 'issue' ELSE 'merge_request' END as entity_type,\n COUNT(*) as count\nFROM resource_state_events\nGROUP BY entity_type;\n-- (repeat for label and milestone events)\n```\n\n3. Human output: table format\n```\nEvent Type Issues MRs Total\nState events 1,234 567 1,801\nLabel events 2,345 890 3,235\nMilestone events 456 123 579\nTotal 4,035 1,580 5,615\n```\n\n4. Robot JSON:\n```json\n{\n \"ok\": true,\n \"data\": {\n \"state_events\": {\"issue\": 1234, \"merge_request\": 567, \"total\": 1801},\n \"label_events\": {\"issue\": 2345, \"merge_request\": 890, \"total\": 3235},\n \"milestone_events\": {\"issue\": 456, \"merge_request\": 123, \"total\": 579},\n \"total\": 5615\n }\n}\n```\n\n5. Register in CLI: add \"events\" to count's entity_type argument in src/cli/mod.rs\n\n## Acceptance Criteria\n- [ ] `lore count events` shows correct counts by event type and entity type\n- [ ] Robot JSON matches the schema above\n- [ ] Works with empty tables (all zeros)\n- [ ] Does not error if migration 011 hasn't been applied (graceful degradation or \"no event tables\" message)\n\n## Files\n- src/cli/commands/count.rs (add events counting logic)\n- src/cli/mod.rs (add \"events\" to count's accepted entity types)\n\n## TDD Loop\nRED: tests/count_tests.rs (or extend existing):\n- `test_count_events_empty_tables` - verify all zeros on fresh DB\n- `test_count_events_with_data` - seed state + label events, verify correct counts\n- `test_count_events_robot_json` - verify JSON structure\n\nGREEN: Add the events branch to count command\n\nVERIFY: `cargo test count -- --nocapture`\n\n## Edge Cases\n- Tables don't exist if user hasn't run migrate — check table existence first or catch the error\n- COUNT with GROUP BY returns no rows for empty tables — need to handle missing entity types as 0","status":"closed","priority":3,"issue_type":"task","created_at":"2026-02-02T21:31:57.379702Z","created_by":"tayloreernisse","updated_at":"2026-02-03T16:21:21.408874Z","closed_at":"2026-02-03T16:21:21.408806Z","close_reason":"Added 'events' to count CLI parser, run_count_events function, print_event_count (table format) and print_event_count_json (structured JSON). Wired into handle_count in main.rs.","compaction_level":0,"original_size":0,"labels":["cli","gate-1","phase-b"],"dependencies":[{"issue_id":"bd-3sh","depends_on_id":"bd-2zl","type":"parent-child","created_at":"2026-02-12T19:34:59Z","created_by":"import"},{"issue_id":"bd-3sh","depends_on_id":"bd-hu3","type":"blocks","created_at":"2026-02-12T19:34:59Z","created_by":"import"}]} @@ -267,6 +268,7 @@ {"id":"bd-9dd","title":"Implement 'lore trace' command with human and robot output","description":"## Background\n\nThe trace command is Gate 5's capstone CLI. It answers 'Why was this code introduced?' by building file -> MR -> issue -> discussion chains.\n\n**Spec reference:** `docs/phase-b-temporal-intelligence.md` Section 5.3.\n\n## Codebase Context\n\n- CLI pattern: same as file-history (Commands enum, handler in main.rs)\n- trace.rs (bd-2n4): run_trace() returns TraceResult with chains\n- Path parsing: support 'src/foo.rs:45' syntax (line number for future Tier 2)\n- merge_requests.merged_at exists (migration 006) — use COALESCE(merged_at, updated_at) for ordering\n\n## Approach\n\n### 1. TraceArgs (`src/cli/mod.rs`):\n```rust\n#[derive(Parser)]\npub struct TraceArgs {\n pub path: String, // supports :line suffix\n #[arg(short = 'p', long)] pub project: Option,\n #[arg(long)] pub discussions: bool,\n #[arg(long = \"no-follow-renames\")] pub no_follow_renames: bool,\n #[arg(short = 'n', long = \"limit\", default_value = \"20\")] pub limit: usize,\n}\n```\n\n### 2. Path parsing:\n```rust\nfn parse_trace_path(input: &str) -> (String, Option) {\n if let Some((path, line)) = input.rsplit_once(':') {\n if let Ok(n) = line.parse::() { return (path.to_string(), Some(n)); }\n }\n (input.to_string(), None)\n}\n```\nIf line present: warn 'Line-level tracing requires Tier 2. Showing file-level results.'\n\n### 3. Human output shows chains with MR -> issue -> discussion context\n\n### 4. Robot JSON:\n```json\n{\"ok\": true, \"data\": {\"path\": \"...\", \"resolved_paths\": [...], \"trace_chains\": [...]}, \"meta\": {\"tier\": \"api_only\", \"line_requested\": null}}\n```\n\n## Acceptance Criteria\n\n- [ ] `lore trace src/foo.rs` with human output\n- [ ] `lore --robot trace src/foo.rs` with JSON\n- [ ] :line suffix parses and emits Tier 2 warning\n- [ ] -p, --discussions, --no-follow-renames, -n all work\n- [ ] Rename-aware via resolve_rename_chain\n- [ ] meta.tier = 'api_only'\n- [ ] Added to VALID_COMMANDS and robot-docs\n- [ ] `cargo check --all-targets` passes\n\n## Files\n\n- `src/cli/mod.rs` (TraceArgs + Commands::Trace)\n- `src/cli/commands/trace.rs` (NEW)\n- `src/cli/commands/mod.rs` (re-export)\n- `src/main.rs` (handler + VALID_COMMANDS + robot-docs)\n\n## TDD Loop\n\nRED:\n- `test_parse_trace_path_simple` - \"src/foo.rs\" -> (path, None)\n- `test_parse_trace_path_with_line` - \"src/foo.rs:42\" -> (path, Some(42))\n- `test_parse_trace_path_windows` - \"C:/foo.rs\" -> (path, None) — don't misparse drive letter\n\nGREEN: Implement CLI wiring and handlers.\n\nVERIFY: `cargo check --all-targets`\n\n## Edge Cases\n\n- Windows paths: don't misparse C: as line number\n- No MR data: friendly message with suggestion to sync\n- Very deep rename chain: bounded by resolve_rename_chain","status":"in_progress","priority":2,"issue_type":"task","created_at":"2026-02-02T21:34:32.788530Z","created_by":"tayloreernisse","updated_at":"2026-02-17T19:08:40.322237Z","compaction_level":0,"original_size":0,"labels":["cli","gate-5","phase-b"],"dependencies":[{"issue_id":"bd-9dd","depends_on_id":"bd-1ht","type":"parent-child","created_at":"2026-02-18T17:42:00Z","created_by":"import"},{"issue_id":"bd-9dd","depends_on_id":"bd-2n4","type":"blocks","created_at":"2026-02-18T17:42:00Z","created_by":"import"}]} {"id":"bd-9lbr","title":"lore explain: auto-generate issue/MR narrative","description":"## Background\nGiven an issue or MR, auto-generate a structured narrative of what happened: who was involved, what decisions were made, what changed, and what is unresolved. Template-based v1 (no LLM dependency), deterministic and reproducible.\n\n## Current Infrastructure (Verified 2026-02-12)\n- show.rs: IssueDetail (line 69) and MrDetail (line 14) — entity detail with discussions\n- timeline.rs: 5-stage pipeline SHIPPED — chronological event reconstruction\n- notes table: 282K rows with body, author, created_at, is_system, discussion_id\n- discussions table: links notes to parent entity (noteable_type, noteable_id), has resolved flag\n- resource_state_events table: state changes with created_at, user_username (src/core/events_db.rs)\n- resource_label_events table: label add/remove with created_at, user_username\n- entity_references table (src/core/references.rs): cross-references between entities (closing MRs, related issues). Column names: `source_entity_type`, `source_entity_id`, `target_entity_type`, `target_entity_id`, `target_project_path`, `target_entity_iid`, `reference_type`, `source_method`\n\n## Approach\nNew command: `lore explain issues N` / `lore explain mrs N`\n\n### Data Assembly (reuse existing internals as library calls)\n1. Entity detail: reuse show.rs query logic for IssueDetail/MrDetail\n2. Timeline events: reuse timeline pipeline with entity-scoped seed\n3. Discussion notes:\n```sql\nSELECT n.id, n.body, n.author_username, n.created_at\nFROM notes n\nJOIN discussions d ON n.discussion_id = d.id\nWHERE d.noteable_type = ? AND d.noteable_id = ?\n AND n.is_system = 0\nORDER BY n.created_at\n```\n4. Cross-references:\n```sql\nSELECT target_entity_type, target_entity_id, target_project_path,\n target_entity_iid, reference_type, source_method\nFROM entity_references\nWHERE (source_entity_type = ?1 AND source_entity_id = ?2)\nUNION ALL\nSELECT source_entity_type, source_entity_id, NULL,\n NULL, reference_type, source_method\nFROM entity_references\nWHERE (target_entity_type = ?1 AND target_entity_id = ?2)\n```\n\n### Key Decisions Heuristic\nNotes from assignees/author that follow state or label changes within 1 hour:\n```rust\nstruct StateOrLabelEvent {\n created_at: i64, // ms epoch\n user: String,\n description: String, // e.g. \"state: opened -> closed\" or \"label: +bug\"\n}\n\nfn extract_key_decisions(\n state_events: &[ResourceStateEvent],\n label_events: &[ResourceLabelEvent],\n notes: &[Note],\n) -> Vec {\n // Merge both event types into a unified chronological list\n let mut events: Vec = Vec::new();\n for e in state_events {\n events.push(StateOrLabelEvent {\n created_at: e.created_at,\n user: e.user_username.clone(),\n description: format!(\"state: {} -> {}\", e.from_state.as_deref().unwrap_or(\"?\"), e.to_state),\n });\n }\n for e in label_events {\n let action = if e.action == \"add\" { \"+\" } else { \"-\" };\n events.push(StateOrLabelEvent {\n created_at: e.created_at,\n user: e.user_username.clone(),\n description: format!(\"label: {}{}\", action, e.label_name.as_deref().unwrap_or(\"?\")),\n });\n }\n events.sort_by_key(|e| e.created_at);\n\n let mut decisions = Vec::new();\n let one_hour_ms: i64 = 60 * 60 * 1000;\n\n for event in &events {\n // Find notes by same actor within 60 min after the event\n for note in notes {\n if note.author_username == event.user\n && note.created_at >= event.created_at\n && note.created_at <= event.created_at + one_hour_ms\n {\n decisions.push(KeyDecision {\n timestamp: event.created_at,\n actor: event.user.clone(),\n action: event.description.clone(),\n context_note: truncate(¬e.body, 500),\n });\n break; // one note per event\n }\n }\n }\n decisions.truncate(10); // Cap at 10 key decisions\n decisions\n}\n```\n\n### Narrative Sections\n1. **Header**: title, author, opened date, state, assignees, labels, status_name\n2. **Description excerpt**: first 500 chars of description (or full if shorter)\n3. **Key decisions**: notes correlated with state/label changes (heuristic above)\n4. **Activity summary**: counts of state changes, label changes, notes, time range\n5. **Open threads**: discussions WHERE resolved = false\n6. **Related entities**: closing MRs (with state), related issues from entity_references\n7. **Timeline excerpt**: first 20 events from timeline pipeline\n\n## Robot Mode Output Schema\n```json\n{\n \"ok\": true,\n \"data\": {\n \"entity\": {\n \"type\": \"issue\", \"iid\": 3864, \"title\": \"...\", \"state\": \"opened\",\n \"author\": \"teernisse\", \"assignees\": [\"teernisse\"],\n \"labels\": [\"customer:BNSF\"], \"created_at\": \"...\", \"updated_at\": \"...\",\n \"url\": \"...\", \"status_name\": \"In progress\"\n },\n \"description_excerpt\": \"First 500 chars of description...\",\n \"key_decisions\": [{\n \"timestamp\": \"2026-01-15T...\",\n \"actor\": \"teernisse\",\n \"action\": \"state: opened -> in_progress\",\n \"context_note\": \"Starting work on the BNSF throw time integration...\"\n }],\n \"activity\": {\n \"state_changes\": 3, \"label_changes\": 5, \"notes\": 42,\n \"first_event\": \"2026-01-10T...\", \"last_event\": \"2026-02-12T...\"\n },\n \"open_threads\": [{\n \"discussion_id\": \"abc123\",\n \"started_by\": \"cseiber\",\n \"started_at\": \"2026-02-01T...\",\n \"note_count\": 5,\n \"last_note_at\": \"2026-02-10T...\"\n }],\n \"related\": {\n \"closing_mrs\": [{ \"iid\": 200, \"title\": \"...\", \"state\": \"merged\" }],\n \"related_issues\": [{ \"iid\": 3800, \"title\": \"Rail Break Card\", \"relation\": \"related\" }]\n },\n \"timeline_excerpt\": [{ \"timestamp\": \"...\", \"event_type\": \"...\", \"actor\": \"...\", \"summary\": \"...\" }]\n },\n \"meta\": { \"elapsed_ms\": 350 }\n}\n```\n\n## Clap Registration\n```rust\n// In src/main.rs Commands enum, add:\nExplain {\n /// Entity type: \"issues\" or \"mrs\"\n entity_type: String,\n /// Entity IID\n iid: i64,\n /// Scope to project (fuzzy match)\n #[arg(short, long)]\n project: Option,\n},\n```\n\n## TDD Loop\nRED: Tests in src/cli/commands/explain.rs:\n- test_explain_issue_basic: insert issue + notes + state events, run explain, assert all sections present (entity, description_excerpt, key_decisions, activity, open_threads, related, timeline_excerpt)\n- test_explain_key_decision_heuristic: insert state change event + note by same author within 30 min, assert note appears in key_decisions\n- test_explain_key_decision_ignores_unrelated_notes: insert note by different author, assert it does NOT appear in key_decisions\n- test_explain_open_threads: insert 2 discussions (1 resolved, 1 unresolved), assert only unresolved in open_threads\n- test_explain_no_notes: issue with zero notes produces header + description + empty sections\n- test_explain_mr: insert MR with merged_at, assert entity includes type=\"merge_request\"\n- test_explain_activity_counts: insert 3 state events + 2 label events + 10 notes, assert counts match\n\nGREEN: Implement explain command with section assembly\n\nVERIFY:\n```bash\ncargo test explain:: && cargo clippy --all-targets -- -D warnings\ncargo run --release -- -J explain issues 3864 | jq '.data | keys'\n# Should include: entity, description_excerpt, key_decisions, activity, open_threads, related, timeline_excerpt\n```\n\n## Acceptance Criteria\n- [ ] lore explain issues N produces structured output for any synced issue\n- [ ] lore explain mrs N produces structured output for any synced MR\n- [ ] Robot mode returns all 7 sections\n- [ ] Human mode renders readable narrative with headers and indentation\n- [ ] Key decisions heuristic: captures notes within 60 min of state/label changes by same actor\n- [ ] Works fully offline (no API calls, no LLM)\n- [ ] Performance: <500ms for issue with 50 notes\n- [ ] Command registered in main.rs and robot-docs\n- [ ] key_decisions capped at 10, timeline_excerpt capped at 20 events\n\n## Edge Cases\n- Issue with empty description: description_excerpt = \"(no description)\"\n- Issue with 500+ notes: timeline_excerpt capped at 20, key_decisions capped at 10\n- Issue not found in local DB: exit code 17 with suggestion to sync\n- Ambiguous project: exit code 18 with suggestion to use -p flag\n- MR with no review activity: activity section shows zeros\n- Cross-project references: show as unresolved with project path hint\n- Notes that are pure code blocks: include in key_decisions if correlated with events (they may contain implementation decisions)\n- ResourceStateEvent/ResourceLabelEvent field names: check src/core/events_db.rs for exact struct definitions before implementing\n\n## Dependency Context\n- **bd-2g50 (data gaps)**: BLOCKER. Provides `closed_at` field on IssueDetail for the header section. Without it, explain can still show state=\"closed\" but won't have the exact close timestamp.\n\n## Files to Create/Modify\n- NEW: src/cli/commands/explain.rs\n- src/cli/commands/mod.rs (add pub mod explain; re-export)\n- src/main.rs (register Explain subcommand in Commands enum, add handle_explain fn)\n- Reuse: show.rs queries, timeline pipeline, notes/discussions/resource_events queries from src/core/events_db.rs","status":"open","priority":2,"issue_type":"feature","created_at":"2026-02-12T15:46:41.386454Z","created_by":"tayloreernisse","updated_at":"2026-02-12T16:31:34.538422Z","compaction_level":0,"original_size":0,"labels":["cli-imp","intelligence"],"dependencies":[{"issue_id":"bd-9lbr","depends_on_id":"bd-13lp","type":"parent-child","created_at":"2026-02-12T19:34:59Z","created_by":"import"},{"issue_id":"bd-9lbr","depends_on_id":"bd-2g50","type":"blocks","created_at":"2026-02-12T19:34:59Z","created_by":"import"}]} {"id":"bd-9wl5","title":"NOTE-2G: Parent metadata change propagation to note documents","description":"## Background\nNote documents inherit labels and title from parent issue/MR. When parent metadata changes, note documents become stale. The existing pipeline already marks discussion documents dirty on parent changes — note documents need the same treatment.\n\n## Approach\nFind where ingestion detects parent entity changes and marks discussion documents dirty. The dirty marking for discussions happens in:\n- src/ingestion/discussions.rs line 127: mark_dirty_tx(&tx, SourceType::Discussion, local_discussion_id)\n- src/ingestion/mr_discussions.rs line 162 and 362: mark_dirty_tx(&tx, SourceType::Discussion, local_discussion_id)\n\nThese fire when a discussion is upserted (which happens when parent entity is re-ingested). For note documents, we need to additionally mark all non-system notes of that discussion as dirty:\n\nAfter each mark_dirty_tx for Discussion, add:\n // Mark child note documents dirty (they inherit parent metadata)\n let note_ids: Vec = tx.prepare(\"SELECT id FROM notes WHERE discussion_id = ? AND is_system = 0\")?\n .query_map([local_discussion_id], |r| r.get(0))?\n .collect::, _>>()?;\n for note_id in note_ids {\n dirty_tracker::mark_dirty_tx(&tx, SourceType::Note, note_id)?;\n }\n\nAlternative (more efficient, set-based):\n INSERT INTO dirty_sources (source_type, source_id, queued_at)\n SELECT 'note', n.id, ?1\n FROM notes n\n WHERE n.discussion_id = ?2 AND n.is_system = 0\n ON CONFLICT(source_type, source_id) DO UPDATE SET queued_at = excluded.queued_at, attempt_count = 0\n\nUse the set-based approach for better performance with large discussions.\n\n## Files\n- MODIFY: src/ingestion/discussions.rs (add note dirty marking after line 127)\n- MODIFY: src/ingestion/mr_discussions.rs (add note dirty marking after lines 162 and 362)\n\n## TDD Anchor\nRED: test_parent_title_change_marks_notes_dirty — change issue title, re-ingest discussions, assert note documents appear in dirty_sources.\nGREEN: Add set-based INSERT INTO dirty_sources after discussion dirty marking.\nVERIFY: cargo test parent_title_change_marks_notes -- --nocapture\nTests: test_parent_label_change_marks_notes_dirty (modify issue labels, re-ingest, check dirty queue)\n\n## Acceptance Criteria\n- [ ] Discussion upsert for issue marks child non-system note documents dirty\n- [ ] Discussion upsert for MR marks child non-system note documents dirty (both call sites)\n- [ ] Only non-system notes marked dirty (is_system = 0 filter)\n- [ ] Set-based SQL (not per-note loop) for performance\n- [ ] Both tests pass\n\n## Dependency Context\n- Depends on NOTE-2D (bd-2ezb): dirty tracking infrastructure for notes must exist (dirty_sources accepts source_type='note', regenerator handles it)\n\n## Edge Cases\n- Discussion with 0 non-system notes: set-based INSERT is a no-op\n- Discussion with 100+ notes: set-based approach handles efficiently in one SQL statement\n- Concurrent discussion ingestion: ON CONFLICT DO UPDATE handles race safely","status":"closed","priority":2,"issue_type":"task","created_at":"2026-02-12T17:02:40.292874Z","created_by":"tayloreernisse","updated_at":"2026-02-12T18:13:15.717576Z","closed_at":"2026-02-12T18:13:15.717528Z","close_reason":"Implemented by agent swarm","compaction_level":0,"original_size":0,"labels":["per-note","search"]} +{"id":"bd-a6yb","title":"Implement responsive breakpoints for all TUI screens","status":"in_progress","priority":2,"issue_type":"task","created_at":"2026-02-19T04:52:55.561576Z","created_by":"tayloreernisse","updated_at":"2026-02-19T04:53:08.902955Z","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-a6yb","depends_on_id":"bd-3t6r","type":"blocks","created_at":"2026-02-19T04:53:02.566163Z","created_by":"tayloreernisse"}]} {"id":"bd-am7","title":"Implement embedding pipeline with chunking","description":"## Background\nThe embedding pipeline takes documents, chunks them (paragraph-boundary splitting with overlap), sends chunks to Ollama for embedding via async HTTP, and stores vectors in sqlite-vec + metadata. It uses keyset pagination, concurrent HTTP requests via FuturesUnordered, per-batch transactions, and dimension validation.\n\n## Approach\nCreate \\`src/embedding/pipeline.rs\\` per PRD Section 4.4. **The pipeline is async.**\n\n**Constants (per PRD):**\n```rust\nconst BATCH_SIZE: usize = 32; // texts per Ollama API call\nconst DB_PAGE_SIZE: usize = 500; // keyset pagination page size\nconst EXPECTED_DIMS: usize = 768; // nomic-embed-text dimensions\nconst CHUNK_MAX_CHARS: usize = 32_000; // max chars per chunk\nconst CHUNK_OVERLAP_CHARS: usize = 500; // overlap between chunks\n```\n\n**Core async function:**\n```rust\npub async fn embed_documents(\n conn: &Connection,\n client: &OllamaClient,\n selection: EmbedSelection,\n concurrency: usize, // max in-flight HTTP requests\n progress_callback: Option>,\n) -> Result\n```\n\n**EmbedSelection:** Pending | RetryFailed\n**EmbedResult:** { embedded, failed, skipped }\n\n**Algorithm (per PRD):**\n1. count_pending_documents(conn, selection) for progress total\n2. Keyset pagination loop: find_pending_documents(conn, DB_PAGE_SIZE, last_id, selection)\n3. For each page:\n a. Begin transaction\n b. For each doc: clear_document_embeddings(&tx, doc.id), split_into_chunks(&doc.content)\n c. Build ChunkWork items with doc_hash + chunk_hash\n d. Commit clearing transaction\n4. Batch ChunkWork texts into Ollama calls (BATCH_SIZE=32)\n5. Use **FuturesUnordered** for concurrent HTTP, cap at \\`concurrency\\`\n6. collect_writes() in per-batch transactions: validate dims (768), store LE bytes, write metadata\n7. On error: record_embedding_error per chunk (not abort)\n8. Advance keyset cursor\n\n**ChunkWork struct:**\n```rust\nstruct ChunkWork {\n doc_id: i64,\n chunk_index: usize,\n doc_hash: String, // SHA-256 of FULL document (staleness detection)\n chunk_hash: String, // SHA-256 of THIS chunk (provenance)\n text: String,\n}\n```\n\n**Splitting:** split_into_chunks(content) -> Vec<(usize, String)>\n- Documents <= CHUNK_MAX_CHARS: single chunk (index 0)\n- Longer: split at paragraph boundaries (\\\\n\\\\n), fallback to sentence/word, with CHUNK_OVERLAP_CHARS overlap\n\n**Storage:** embeddings as raw LE bytes, rowid = encode_rowid(doc_id, chunk_idx)\n**Staleness detection:** uses document_hash (not chunk_hash) because it's document-level\n\nAlso create \\`src/embedding/change_detector.rs\\` (referenced in PRD module structure):\n```rust\npub fn detect_embedding_changes(conn: &Connection) -> Result>;\n```\n\n## Acceptance Criteria\n- [ ] Pipeline is async (uses FuturesUnordered for concurrent HTTP)\n- [ ] concurrency parameter caps in-flight HTTP requests\n- [ ] progress_callback reports (processed, total)\n- [ ] New documents embedded, changed re-embedded, unchanged skipped\n- [ ] clear_document_embeddings before re-embedding (range delete vec0 + metadata)\n- [ ] Chunking at paragraph boundaries with 500-char overlap\n- [ ] Short documents (<32k chars) produce exactly 1 chunk\n- [ ] Embeddings stored as raw LE bytes in vec0\n- [ ] Rowids encoded via encode_rowid(doc_id, chunk_index)\n- [ ] Dimension validation: 768 floats per embedding (mismatch -> record error, not store)\n- [ ] Per-batch transactions for writes\n- [ ] Errors recorded in embedding_metadata per chunk (last_error, attempt_count)\n- [ ] Keyset pagination (d.id > last_id, not OFFSET)\n- [ ] Pending detection uses document_hash (not chunk_hash)\n- [ ] \\`cargo build\\` succeeds\n\n## Files\n- \\`src/embedding/pipeline.rs\\` — new file (async)\n- \\`src/embedding/change_detector.rs\\` — new file\n- \\`src/embedding/mod.rs\\` — add \\`pub mod pipeline; pub mod change_detector;\\` + re-exports\n\n## TDD Loop\nRED: Unit tests for chunking:\n- \\`test_short_document_single_chunk\\` — <32k produces [(0, full_content)]\n- \\`test_long_document_multiple_chunks\\` — >32k splits at paragraph boundaries\n- \\`test_chunk_overlap\\` — adjacent chunks share 500-char overlap\n- \\`test_no_paragraph_boundary\\` — falls back to char boundary\nIntegration tests need Ollama or mock.\nGREEN: Implement split_into_chunks, embed_documents (async)\nVERIFY: \\`cargo test pipeline\\`\n\n## Edge Cases\n- Empty document content_text: skip (don't embed)\n- No paragraph boundaries: split at CHUNK_MAX_CHARS with overlap\n- Ollama error for one batch: record error per chunk, continue with next batch\n- Dimension mismatch (model returns 512 instead of 768): record error, don't store corrupt data\n- Document deleted between pagination and embedding: skip gracefully","status":"closed","priority":2,"issue_type":"task","created_at":"2026-01-30T15:26:34.093701Z","created_by":"tayloreernisse","updated_at":"2026-01-30T17:58:58.908585Z","closed_at":"2026-01-30T17:58:58.908525Z","close_reason":"Implemented embedding pipeline: chunking at paragraph boundaries with 500-char overlap, change detector (keyset pagination, hash-based staleness), async embed via Ollama with batch processing, dimension validation, per-chunk error recording, LE byte vector storage. 7 chunking tests pass. 289 total tests.","compaction_level":0,"original_size":0,"dependencies":[{"issue_id":"bd-am7","depends_on_id":"bd-1y8","type":"blocks","created_at":"2026-02-12T19:34:59Z","created_by":"import"},{"issue_id":"bd-am7","depends_on_id":"bd-2ac","type":"blocks","created_at":"2026-02-12T19:34:59Z","created_by":"import"},{"issue_id":"bd-am7","depends_on_id":"bd-335","type":"blocks","created_at":"2026-02-12T19:34:59Z","created_by":"import"}]} {"id":"bd-apmo","title":"OBSERV: Create migration 014 for sync_runs enrichment","description":"## Background\nThe sync_runs table (created in migration 001) has columns id, started_at, heartbeat_at, finished_at, status, command, error, metrics_json but NOTHING writes to it. This migration adds columns for the observability correlation ID and aggregate counts, enabling queryable sync history.\n\n## Approach\nCreate migrations/014_sync_runs_enrichment.sql:\n\n```sql\n-- Migration 014: sync_runs enrichment for observability\n-- Adds correlation ID and aggregate counts for queryable sync history\n\nALTER TABLE sync_runs ADD COLUMN run_id TEXT;\nALTER TABLE sync_runs ADD COLUMN total_items_processed INTEGER DEFAULT 0;\nALTER TABLE sync_runs ADD COLUMN total_errors INTEGER DEFAULT 0;\n\n-- Index for correlation queries (find run by run_id from logs)\nCREATE INDEX IF NOT EXISTS idx_sync_runs_run_id ON sync_runs(run_id);\n```\n\nMigration naming convention: check migrations/ directory. Current latest is 013_resource_event_watermarks.sql. Next is 014.\n\nNote: SQLite ALTER TABLE ADD COLUMN is always safe -- it sets NULL for existing rows. DEFAULT 0 applies to new INSERTs only.\n\n## Acceptance Criteria\n- [ ] Migration 014 applies cleanly on a fresh DB (all migrations 001-014)\n- [ ] Migration 014 applies cleanly on existing DB with 001-013 already applied\n- [ ] sync_runs table has run_id TEXT column\n- [ ] sync_runs table has total_items_processed INTEGER DEFAULT 0 column\n- [ ] sync_runs table has total_errors INTEGER DEFAULT 0 column\n- [ ] idx_sync_runs_run_id index exists\n- [ ] Existing sync_runs rows (if any) have NULL run_id, 0 for counts\n- [ ] cargo clippy --all-targets -- -D warnings passes (no code changes, but verify migration is picked up)\n\n## Files\n- migrations/014_sync_runs_enrichment.sql (new file)\n\n## TDD Loop\nRED:\n - test_migration_014_applies: apply all migrations on fresh in-memory DB, query sync_runs schema\n - test_migration_014_idempotent: CREATE INDEX IF NOT EXISTS makes re-run safe; ALTER TABLE ADD COLUMN is NOT idempotent in SQLite (will error). Consider: skip this test or use IF NOT EXISTS workaround\nGREEN: Create migration file\nVERIFY: cargo test && cargo clippy --all-targets -- -D warnings\n\n## Edge Cases\n- ALTER TABLE ADD COLUMN in SQLite: NOT idempotent. Running migration twice will error \"duplicate column name.\" The migration system should prevent re-runs, but IF NOT EXISTS is not available for ALTER TABLE in SQLite. Rely on migration tracking.\n- Migration numbering conflict: if another PR adds 014 first, renumber to 015. Check before merging.\n- metrics_json already exists (from migration 001): we don't touch it. The new columns supplement it with queryable aggregates.","status":"closed","priority":2,"issue_type":"task","created_at":"2026-02-04T15:54:51.311879Z","created_by":"tayloreernisse","updated_at":"2026-02-04T17:34:05.309761Z","closed_at":"2026-02-04T17:34:05.309714Z","close_reason":"Created migration 014 adding run_id TEXT, total_items_processed INTEGER, total_errors INTEGER to sync_runs, with idx_sync_runs_run_id index","compaction_level":0,"original_size":0,"labels":["observability"],"dependencies":[{"issue_id":"bd-apmo","depends_on_id":"bd-3pz","type":"parent-child","created_at":"2026-02-12T19:34:59Z","created_by":"import"}]} {"id":"bd-arka","title":"Extend SyncRunRecorder with surgical mode lifecycle methods","description":"## Background\nThe existing `SyncRunRecorder` in `src/core/sync_run.rs` manages sync run lifecycle with three methods: `start()` (creates row, returns Self), `succeed(self, ...)` (consumes self, sets succeeded), and `fail(self, ...)` (consumes self, sets failed). Both `succeed()` and `fail()` take ownership of `self` — this is intentional to prevent double-finalization.\n\nSurgical sync needs additional lifecycle methods to:\n1. Set surgical-specific metadata (mode, phase, IIDs JSON) after `start()`\n2. Record per-entity results (increment counters, store entity-level outcomes)\n3. Cancel a run (distinct from failure — user-initiated or timeout)\n4. Update phase progression during the surgical pipeline\n\nThese methods operate on the columns added by migration 027 (bead bd-tiux).\n\n## Approach\n\n### Step 1: Add `set_surgical_metadata` method\n\nCalled once after `start()` to set the surgical mode columns:\n\n```rust\npub fn set_surgical_metadata(\n &self,\n conn: &Connection,\n mode: &str,\n phase: &str,\n iids_json: &str,\n) -> Result<()> {\n conn.execute(\n \"UPDATE sync_runs SET mode = ?1, phase = ?2, surgical_iids_json = ?3 WHERE id = ?4\",\n rusqlite::params![mode, phase, iids_json, self.row_id],\n )?;\n Ok(())\n}\n```\n\nTakes `&self` (not `self`) because the recorder continues to be used after metadata is set.\n\n### Step 2: Add `update_phase` method\n\nCalled as the surgical pipeline progresses through phases:\n\n```rust\npub fn update_phase(&self, conn: &Connection, phase: &str) -> Result<()> {\n conn.execute(\n \"UPDATE sync_runs SET phase = ?1, heartbeat_at = ?2 WHERE id = ?3\",\n rusqlite::params![phase, now_ms(), self.row_id],\n )?;\n Ok(())\n}\n```\n\n### Step 3: Add `record_entity_result` method\n\nCalled after each entity (issue or MR) is processed to increment counters:\n\n```rust\npub fn record_entity_result(\n &self,\n conn: &Connection,\n entity_type: &str,\n stage: &str,\n) -> Result<()> {\n let column = match (entity_type, stage) {\n (\"issue\", \"fetched\") => \"issues_fetched\",\n (\"issue\", \"ingested\") => \"issues_ingested\",\n (\"mr\", \"fetched\") => \"mrs_fetched\",\n (\"mr\", \"ingested\") => \"mrs_ingested\",\n (\"issue\" | \"mr\", \"skipped_stale\") => \"skipped_stale\",\n (\"doc\", \"regenerated\") => \"docs_regenerated\",\n (\"doc\", \"embedded\") => \"docs_embedded\",\n (_, \"warning\") => \"warnings_count\",\n _ => return Ok(()), // Unknown combinations are silently ignored\n };\n conn.execute(\n &format!(\"UPDATE sync_runs SET {column} = {column} + 1 WHERE id = ?1\"),\n rusqlite::params![self.row_id],\n )?;\n Ok(())\n}\n```\n\nNote: The column name comes from a hardcoded match, NOT from user input — no SQL injection risk.\n\n### Step 4: Add `cancel` method\n\nConsumes self (like succeed/fail) to finalize the run as cancelled:\n\n```rust\npub fn cancel(self, conn: &Connection, reason: &str) -> Result<()> {\n let now = now_ms();\n conn.execute(\n \"UPDATE sync_runs SET finished_at = ?1, cancelled_at = ?2, status = 'cancelled', error = ?3 WHERE id = ?4\",\n rusqlite::params![now, now, reason, self.row_id],\n )?;\n Ok(())\n}\n```\n\nTakes `self` (ownership) like `succeed()` and `fail()` — prevents further use after cancellation.\n\n### Step 5: Expose `row_id` getter\n\nThe orchestrator (bd-1i4i) may need the row_id for logging/tracing:\n\n```rust\npub fn row_id(&self) -> i64 {\n self.row_id\n}\n```\n\n## Acceptance Criteria\n- [ ] `set_surgical_metadata(&self, conn, mode, phase, iids_json)` writes mode/phase/surgical_iids_json columns\n- [ ] `update_phase(&self, conn, phase)` updates phase and heartbeat_at\n- [ ] `record_entity_result(&self, conn, entity_type, stage)` increments the correct counter column\n- [ ] `record_entity_result` silently ignores unknown entity_type/stage combinations\n- [ ] `cancel(self, conn, reason)` consumes self, sets status='cancelled', finished_at, cancelled_at, error\n- [ ] `row_id()` returns the internal row_id\n- [ ] `succeed(self, ...)` still works after `set_surgical_metadata` + `record_entity_result` calls\n- [ ] `fail(self, ...)` still works after `set_surgical_metadata` + `update_phase` calls\n- [ ] `cargo check --all-targets` passes\n- [ ] `cargo clippy --all-targets -- -D warnings` passes\n- [ ] All existing sync_run tests continue to pass\n\n## Files\n- MODIFY: src/core/sync_run.rs (add methods to SyncRunRecorder impl block)\n- MODIFY: src/core/sync_run_tests.rs (add new tests)\n\n## TDD Anchor\nRED: Write tests in `src/core/sync_run_tests.rs`:\n\n```rust\n#[test]\nfn surgical_lifecycle_start_metadata_succeed() {\n let conn = setup_test_db();\n let recorder = SyncRunRecorder::start(&conn, \"sync\", \"surg001\").unwrap();\n let row_id = recorder.row_id();\n\n recorder.set_surgical_metadata(\n &conn, \"surgical\", \"preflight\", r#\"{\"issues\":[7,8],\"mrs\":[101]}\"#,\n ).unwrap();\n\n recorder.update_phase(&conn, \"ingest\").unwrap();\n recorder.record_entity_result(&conn, \"issue\", \"fetched\").unwrap();\n recorder.record_entity_result(&conn, \"issue\", \"fetched\").unwrap();\n recorder.record_entity_result(&conn, \"issue\", \"ingested\").unwrap();\n recorder.record_entity_result(&conn, \"mr\", \"fetched\").unwrap();\n recorder.record_entity_result(&conn, \"mr\", \"ingested\").unwrap();\n\n recorder.succeed(&conn, &[], 3, 0).unwrap();\n\n let (mode, phase, iids, issues_fetched, mrs_fetched, issues_ingested, mrs_ingested, status): (\n String, String, String, i64, i64, i64, i64, String,\n ) = conn.query_row(\n \"SELECT mode, phase, surgical_iids_json, issues_fetched, mrs_fetched, issues_ingested, mrs_ingested, status\n FROM sync_runs WHERE id = ?1\",\n [row_id],\n |r| Ok((r.get(0)?, r.get(1)?, r.get(2)?, r.get(3)?, r.get(4)?, r.get(5)?, r.get(6)?, r.get(7)?)),\n ).unwrap();\n\n assert_eq!(mode, \"surgical\");\n assert_eq!(phase, \"ingest\"); // Last phase set before succeed\n assert!(iids.contains(\"101\"));\n assert_eq!(issues_fetched, 2);\n assert_eq!(mrs_fetched, 1);\n assert_eq!(issues_ingested, 1);\n assert_eq!(mrs_ingested, 1);\n assert_eq!(status, \"succeeded\");\n}\n\n#[test]\nfn surgical_lifecycle_cancel() {\n let conn = setup_test_db();\n let recorder = SyncRunRecorder::start(&conn, \"sync\", \"cancel01\").unwrap();\n let row_id = recorder.row_id();\n\n recorder.set_surgical_metadata(&conn, \"surgical\", \"preflight\", \"{}\").unwrap();\n recorder.cancel(&conn, \"User requested cancellation\").unwrap();\n\n let (status, error, cancelled_at, finished_at): (String, Option, Option, Option) = conn.query_row(\n \"SELECT status, error, cancelled_at, finished_at FROM sync_runs WHERE id = ?1\",\n [row_id],\n |r| Ok((r.get(0)?, r.get(1)?, r.get(2)?, r.get(3)?)),\n ).unwrap();\n\n assert_eq!(status, \"cancelled\");\n assert_eq!(error.as_deref(), Some(\"User requested cancellation\"));\n assert!(cancelled_at.is_some());\n assert!(finished_at.is_some());\n}\n\n#[test]\nfn record_entity_result_ignores_unknown() {\n let conn = setup_test_db();\n let recorder = SyncRunRecorder::start(&conn, \"sync\", \"unk001\").unwrap();\n // Should not panic or error on unknown combinations\n recorder.record_entity_result(&conn, \"widget\", \"exploded\").unwrap();\n}\n\n#[test]\nfn record_entity_result_json_counters() {\n let conn = setup_test_db();\n let recorder = SyncRunRecorder::start(&conn, \"sync\", \"cnt001\").unwrap();\n let row_id = recorder.row_id();\n\n recorder.record_entity_result(&conn, \"doc\", \"regenerated\").unwrap();\n recorder.record_entity_result(&conn, \"doc\", \"regenerated\").unwrap();\n recorder.record_entity_result(&conn, \"doc\", \"embedded\").unwrap();\n recorder.record_entity_result(&conn, \"issue\", \"skipped_stale\").unwrap();\n\n let (docs_regen, docs_embed, skipped): (i64, i64, i64) = conn.query_row(\n \"SELECT docs_regenerated, docs_embedded, skipped_stale FROM sync_runs WHERE id = ?1\",\n [row_id],\n |r| Ok((r.get(0)?, r.get(1)?, r.get(2)?)),\n ).unwrap();\n\n assert_eq!(docs_regen, 2);\n assert_eq!(docs_embed, 1);\n assert_eq!(skipped, 1);\n}\n```\n\nGREEN: Add all methods to `SyncRunRecorder`.\nVERIFY: `cargo test surgical_lifecycle && cargo test record_entity_result`\n\n## Edge Cases\n- `succeed()` and `fail()` consume `self` — the compiler enforces that no methods are called after finalization. `cancel()` also consumes self for the same reason.\n- `set_surgical_metadata`, `update_phase`, and `record_entity_result` take `&self` — they can be called multiple times before finalization.\n- The `record_entity_result` match uses a hardcoded column name derived from known string constants, not user input. The `format!` is safe because the column name is always one of the hardcoded strings.\n- `record_entity_result` silently returns Ok(()) for unknown entity_type/stage combos rather than erroring — this avoids breaking the pipeline for non-critical telemetry.\n- Phase is NOT overwritten by `succeed()`/`fail()`/`cancel()` — the last phase set via `update_phase()` is preserved as the \"phase at completion\" for observability.\n\n## Dependency Context\nDepends on bd-tiux (migration 027) for the surgical columns to exist. Downstream beads bd-1i4i (orchestrator) and bd-3jqx (integration tests) use these methods.","status":"open","priority":2,"issue_type":"task","created_at":"2026-02-17T19:13:50.827946Z","created_by":"tayloreernisse","updated_at":"2026-02-17T20:04:15.562997Z","compaction_level":0,"original_size":0,"labels":["surgical-sync"],"dependencies":[{"issue_id":"bd-arka","depends_on_id":"bd-1i4i","type":"blocks","created_at":"2026-02-18T17:42:00Z","created_by":"import"},{"issue_id":"bd-arka","depends_on_id":"bd-3jqx","type":"blocks","created_at":"2026-02-18T17:42:00Z","created_by":"import"}]} diff --git a/.beads/last-touched b/.beads/last-touched index 540aa5f..93c7f1a 100644 --- a/.beads/last-touched +++ b/.beads/last-touched @@ -1 +1 @@ -bd-3l56 +bd-a6yb diff --git a/crates/lore-tui/src/state/who.rs b/crates/lore-tui/src/state/who.rs index 57b52d1..68f5d13 100644 --- a/crates/lore-tui/src/state/who.rs +++ b/crates/lore-tui/src/state/who.rs @@ -40,6 +40,18 @@ impl WhoMode { } } + /// Abbreviated 3-char label for narrow terminals. + #[must_use] + pub fn short_label(self) -> &'static str { + match self { + Self::Expert => "Exp", + Self::Workload => "Wkl", + Self::Reviews => "Rev", + Self::Active => "Act", + Self::Overlap => "Ovl", + } + } + /// Whether this mode requires a path input. #[must_use] pub fn needs_path(self) -> bool {