claude-memory-layer 1.0.27 → 1.0.28

package/docs/MEMORY_USEFULNESS_AUDIT.md

@@ -0,0 +1,371 @@
+# Memory Usefulness Audit — Real Scenario Test
+
+Date: 2026-05-05
+Target: `claude-memory-layer` built CLI (`dist/cli/index.js`)
+Isolation: temporary `HOME` and temporary project directories; no real `~/.claude` or `~/.claude-code/memory` was touched.
+Raw evidence: [`MEMORY_USEFULNESS_AUDIT_RAW.json`](./MEMORY_USEFULNESS_AUDIT_RAW.json)
+
+## 0. Follow-up improvements applied and re-verified
+
+After the first audit exposed precision/UX issues, the following improvements were implemented and the same real scenario was rerun:
+
+1. Query-time command artifact guard
+   - Queries such as `local-command-stdout command-name opus` now return zero memories.
+2. Technical identifier lexical guard
+   - Out-of-domain project-scoped queries such as `DuckDB legacy storage migrate` in the alpha project now return zero memories instead of loosely related semantic matches.
+   - The same query in the beta project still returns the beta DuckDB memory, proving useful exact matches are preserved.
+3. Score cliff cutoff
+   - The FTS query now returns the two actually relevant memories instead of including an unrelated dashboard provenance third result.
+4. Transformer warning suppression
+   - Known benign HuggingFace warnings (`Unknown model class "eurobert"`, `dtype not specified`) no longer appear in CLI import/stats/search output.
+5. Disclosure reason taxonomy cleanup
+   - Keyword-only disclosure now reports `keyword_match` without `semantic_match` when `vector=no`.
+
+The raw evidence file was regenerated after these improvements.
+
+## 1. Test goal
+
+This audit tested whether the memory layer is useful in the way a coding assistant actually needs it:
+
+1. It can import real Claude-style JSONL conversation history.
+2. It retrieves durable engineering decisions when asked later with different wording.
+3. It keeps project memories scoped, so unrelated project decisions do not leak.
+4. It filters low-value command artifacts from imported sessions.
+5. The progressive `search -> expand -> source` workflow gives enough provenance to trust and inspect a memory.
+6. The shipped CLI works after build, not only through source-level tests.
+
+## 2. Scenario design
+
+Two temporary projects were created:
+
+- `alpha-commerce-ai`: current/refactor project memories.
+- `beta-legacy-duckdb`: unrelated project with a deliberately conflicting storage decision.
+
+The crafted Claude JSONL sessions contained the following durable memories.
+
+### Alpha memories
+
+1. **Retrieval disclosure lifecycle rule**
+   - `expand` / `source` drill-down routes must stay lightweight.
+   - They should not call full `MemoryService.initialize()` because that can start embedders, vector workers, or shared promotion machinery.
+
+2. **SQLite FTS rebuild fix**
+   - The `no such column: T.event_id` failure is fixed by making `events_fts` an internal FTS5 table with `content` and `event_id UNINDEXED`.
+   - Rebuild by dropping/recreating FTS and triggers.
+
+3. **Shared dashboard provenance decision**
+   - Shared results should render as `shared_troubleshooting` provenance.
+   - Show `sourceProjectHash`, `sourceEntryId`, `topics`, `rootCause`, `solution`, and state that no local raw event exists.
+
+4. **Noise artifact**
+   - `<command-name>/model</command-name>` + `<local-command-stdout>opus</local-command-stdout>` was included to verify command artifacts are not stored as useful user prompts.
+
+### Beta memory
+
+- A conflicting legacy decision: beta should keep DuckDB and not migrate to SQLite.
+- This tests project scoping against alpha queries.
+
+## 3. Commands executed
+
+All commands used a temporary `HOME`.
+
+```bash
+node dist/cli/index.js import --session <alpha-session.jsonl> --project <alpha-project> --verbose
+node dist/cli/index.js import --session <beta-session.jsonl> --project <beta-project> --verbose
+node dist/cli/index.js stats --project <alpha-project>
+node dist/cli/index.js search "disclosure expand source initialize vector workers lightweight" --project <alpha-project> --top-k 5 --min-score 0.1
+node dist/cli/index.js search "T.event_id FTS rebuild internal table trigger event_id" --project <alpha-project> --top-k 5 --min-score 0.1
+node dist/cli/index.js search "shared_troubleshooting rootCause solution sourceProjectHash" --project <alpha-project> --top-k 5 --min-score 0.1
+node dist/cli/index.js search "local-command-stdout command-name opus" --project <alpha-project> --top-k 5 --min-score 0.1
+node dist/cli/index.js search "DuckDB legacy storage migrate" --project <alpha-project> --top-k 5 --min-score 0.1
+node dist/cli/index.js search "DuckDB legacy storage migrate" --project <beta-project> --top-k 5 --min-score 0.1
+node dist/cli/index.js search "T.event_id FTS rebuild internal table" --project <alpha-project> --top-k 3 --min-score 0.1 --disclosure --strategy fast
+node dist/cli/index.js expand <first-disclosure-result-id> --project <alpha-project> --window-size 2
+node dist/cli/index.js source <first-disclosure-result-id> --project <alpha-project>
+```
+
+## 4. Verified working behavior
+
+### 4.1 Import works and filters command-artifact noise
+
+Alpha import result:
+
+- Total messages: 7
+- Imported prompts: 3
+- Imported responses: 3
+- Skipped duplicates/noise: 1
+- Embeddings queued: 6
+
+This is exactly expected: the three real user prompts and three assistant durable responses were imported, while the local-command artifact was skipped.
+
+Beta import result:
+
+- Total messages: 2
+- Imported prompts: 1
+- Imported responses: 1
+- Embeddings queued: 2
+
+### 4.2 Project-scoped markdown mirror writes to the target project
+
+The audit verified markdown mirrors were written under each temporary target project, not under the `claude-memory-layer` repository working directory.
+
+Examples:
+
+- `<alpha-project>/memory/_index.md`
+- `<alpha-project>/memory/agent_response/uncategorized/2026-05-05.md`
+- `<alpha-project>/memory/user_prompt/uncategorized/2026-05-05.md`
+
+`repo_memory_exists = false`, so the previous accidental `memory/` artifact in the repository did not recur.
+
+### 4.3 Stats reflect imported memory and vectors
+
+Alpha stats:
+
+- Total Events: 6
+- Vector Count: 6
+- Memory Levels: `L0: 6`
+
+This proves import, SQLite storage, embedding queue processing, and vector count all reached a coherent state.
+
+### 4.4 Retrieval finds the right durable decisions
+
+#### Query: lifecycle rule for disclosure expand/source
+
+Top result:
+
+- `agent_response`
+- Score: `1.000`
+- Correct memory: lightweight drill-down; do not call full `MemoryService.initialize()` for expand/source.
+
+This is highly useful: it recovers a nuanced architectural constraint from a later query.
+
+#### Query: SQLite FTS `T.event_id` fix
+
+Top result:
+
+- `agent_response`
+- Score: `0.978`
+- Correct memory: internal FTS5 table with `event_id UNINDEXED`, rebuild by dropping/recreating FTS and triggers.
+
+Second result:
+
+- Original user question, score `0.905`.
+
+This is also useful. It retrieves both the answer and the originating question.
+
+#### Query: dashboard shared provenance
+
+Top and only result:
+
+- `agent_response`
+- Score: `1.000`
+- Correct memory: `shared_troubleshooting`, `sourceProjectHash`, `sourceEntryId`, `topics`, `rootCause`, `solution`.
+
+This is excellent for product/UX decision recall.
+
+### 4.5 Project scoping works for cross-project conflict
+
+Alpha query for `DuckDB legacy storage migrate` did **not** return the beta DuckDB memory and, after the technical-identifier guard, returned **zero** alpha-project false positives.
+
+Beta query for the same phrase returned the beta DuckDB prompt/answer with high scores:
+
+- `user_prompt`, score `1.000`
+- `agent_response`, score `0.922`
+
+So strict project isolation is working at the storage/retrieval boundary.
+
+### 4.6 Progressive disclosure is useful and inspectable
+
+Disclosure query for FTS returned:
+
+```text
+Meta: total=2 vector=no keyword=yes fallback=no
+1. [source] Agent response
+   id: event:<uuid>
+   score: 1.000
+   reasons: keyword_match, recent_relevance, continuity_link
+```
+
+`expand` on the first result returned surrounding turn context:
+
+- previous lifecycle decision
+- target FTS answer
+- neighboring dashboard provenance question/answer
+
+`source` returned raw event details:
+
+- sourceRef
+- sourceType: `imported_history`
+- eventIds
+- full raw event content
+- session id
+- canonical key
+
+This is a strong product surface: the model/user can inspect not just the snippet but why the memory exists and what conversation context surrounded it.
+
+## 5. Problems discovered
+
+### P0 — Built CLI initially failed because of duplicate `fileURLToPath`
+
+The first audit run found that `node dist/cli/index.js ...` failed before any memory command ran:
+
+```text
+SyntaxError: Identifier 'fileURLToPath' has already been declared
+```
+
+Cause:
+
+- `scripts/build.ts` injects an esbuild banner that declares `fileURLToPath`.
+- `src/apps/server/index.ts` also imported `fileURLToPath` under the same identifier.
+- Because CLI bundles server/dashboard code, the duplicate identifier broke the built CLI.
+
+Fix applied:
+
+- Changed server import to alias the identifier:
+  - `import { fileURLToPath as fileUrlToPath } from 'url';`
+  - `fileUrlToPath(import.meta.url)`
+
+Verification:
+
+- `npm run build`
+- `node dist/cli/index.js --help`
+- full memory audit rerun successfully.
+
+### P1 — HuggingFace/transformer warnings were noisy in normal CLI flows — fixed
+
+The first run emitted known benign transformer warnings on import/stats/search. The improved run no longer shows these warnings in the raw CLI outputs.
+
+Implemented:
+
+- Known benign warnings are suppressed around lazy `@huggingface/transformers` pipeline loading/initialization.
+
+Remaining recommendation:
+
+- Consider further reducing embedder initialization on pure stats/read paths, but the user-facing warning noise is fixed.
+
+### P1 — Search returned plausible but irrelevant results on no-match artifact queries — fixed
+
+Noise query:
+
+```bash
+search "local-command-stdout command-name opus" --project alpha --top-k 5 --min-score 0.1
+```
+
+Improved result:
+
+- `Confidence: none`
+- `Total local memories found: 0`
+
+Implemented:
+
+- Query-time command artifact guard for `local-command-stdout`, `local-command-stderr`, `command-name`, and `command-message` patterns.
+- Regression coverage in `tests/core/retriever-strategy-scope.test.ts`.
+
+### P1 — Out-of-domain project-scoped queries returned irrelevant in-project memories — fixed
+
+Alpha query:
+
+```bash
+search "DuckDB legacy storage migrate" --project alpha
+```
+
+Improved result:
+
+- `Confidence: none`
+- `Total local memories found: 0`
+
+Beta query for the same phrase still returns the correct beta DuckDB memory, so the guard improves precision without breaking positive technical-identifier recall.
+
+Implemented:
+
+- Technical identifier lexical guard for terms such as `DuckDB`, `T.event_id`, and `sourceProjectHash`.
+- Regression coverage proving false positives are filtered while exact technical matches are preserved.
+
+### P2 — Top-k included adjacent but not always relevant memories — improved
+
+For the FTS query, top 1 and top 2 were excellent, but the first run included an unrelated dashboard provenance third result.
+
+Improved result:
+
+- The same FTS query now returns only the two directly relevant memories.
+
+Implemented:
+
+- A conservative score-cliff cutoff after reranking/scope filtering.
+
+Remaining recommendation:
+
+- For prompt injection, continue to prefer `confidence=high` results and keep suggested results separated from injected context.
+
+### P2 — Progressive disclosure reason labels were misleading in keyword-only mode — fixed
+
+Disclosure meta says:
+
+```text
+vector=no keyword=yes
+```
+
+Improved result reasons now say:
+
+```text
+keyword_match, recent_relevance, continuity_link
+```
+
+Implemented:
+
+- Disclosure reason mapping omits `semantic_match` when vector/deep retrieval was not used.
+- Regression coverage in `tests/core/retrieval-disclosure-service.test.ts`.
+
+## 6. Remaining next improvements, prioritized
+
+The originally identified precision/UX items have mostly been addressed in this slice. Remaining useful follow-ups:
+
+### Priority 1 — Further reduce unnecessary embedder initialization
+
+Known warning noise is now suppressed, but read paths may still initialize the embedder.
+
+Improve:
+
+- `stats` should use a lightweight/read-only service path when possible.
+- `search --strategy fast` should avoid embedder initialization until deep/vector search is actually needed.
+
+Expected impact:
+
+- Faster stats/search commands.
+- Lower CPU/model-load overhead.
+
+### Priority 2 — Make prompt-injection policy stricter than CLI search
+
+CLI search can show suggested results, but prompt injection should be more conservative.
+
+Improve:
+
+- Inject only high-confidence memories by default.
+- Keep suggested results visible in CLI/dashboard but separate from automatic context injection.
+
+Expected impact:
+
+- Lower memory hallucination risk in real Claude hooks.
+
+### Priority 3 — Add more real-world benchmark scenarios
+
+This audit used crafted sessions. Add broader replay suites:
+
+- 20-50 actual anonymized coding sessions.
+- Known-answer queries and negative/no-match queries.
+- Precision@k / recall@k tracking across refactors.
+
+## 7. Overall verdict
+
+The memory layer is already useful for durable engineering recall:
+
+- It successfully remembered architectural constraints, bug-fix details, and UI provenance decisions.
+- It recovered the right memories from later, differently phrased queries.
+- Project scoping prevented a deliberately conflicting beta project memory from leaking into alpha search.
+- Progressive disclosure gave enough context and raw source provenance to trust a retrieved memory.
+
+After the follow-up fixes, the biggest remaining quality issue is no longer basic precision; it is **operational efficiency and broader benchmarking**:
+
+- Avoid unnecessary embedder/model initialization on pure read paths where possible.
+- Keep automatic prompt injection stricter than exploratory CLI/dashboard search.
+- Expand the benchmark from crafted scenarios to larger anonymized real-session replay suites.

package/docs/MEMORY_USEFULNESS_AUDIT_RAW.json

@@ -0,0 +1,80 @@
+{
+  "root": "/var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p",
+  "home": "/var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/home",
+  "project_a": "/var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai",
+  "project_b": "/var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/beta-legacy-duckdb",
+  "results": [
+    {
+      "label": "import alpha crafted Claude session",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js import --session /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/alpha-session.jsonl --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai --verbose",
+      "output": "\n⏳ Initializing memory service...\n  ✅ Ready (embedder: jinaai/jina-embeddings-v5-text-nano-text-matching)\n\n📥 Importing session: /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/alpha-session.jsonl\n   Target: /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai\n\n\n  📄 [1/...] 1 msgs | +1 imported, ~0 skipped Imported 3 prompts, 3 responses from /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/alpha-session.jsonl\n\n🧠 Processing embeddings...\n\n┌─────────────────────────────────┐\n│       ✅ Import Complete         │\n├─────────────────────────────────┤\n│  Sessions processed:         1 │\n│  Total messages:             7 │\n│  Imported prompts:           3 │\n│  Imported responses:         3 │\n│  Skipped duplicates:         1 │\n│  Embeddings queued:          6 │\n└─────────────────────────────────┘\n\n⏱️  Completed in 1.7s\n"
+    },
+    {
+      "label": "import beta conflicting project session",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js import --session /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/beta-session.jsonl --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/beta-legacy-duckdb --verbose",
+      "output": "\n⏳ Initializing memory service...\n  ✅ Ready (embedder: jinaai/jina-embeddings-v5-text-nano-text-matching)\n\n📥 Importing session: /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/beta-session.jsonl\n   Target: /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/beta-legacy-duckdb\n\n\n  📄 [1/...] 1 msgs | +1 imported, ~0 skipped Imported 1 prompts, 1 responses from /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/beta-session.jsonl\n\n🧠 Processing embeddings...\n\n┌─────────────────────────────────┐\n│       ✅ Import Complete         │\n├─────────────────────────────────┤\n│  Sessions processed:         1 │\n│  Total messages:             2 │\n│  Imported prompts:           1 │\n│  Imported responses:         1 │\n│  Skipped duplicates:         0 │\n│  Embeddings queued:          2 │\n└─────────────────────────────────┘\n\n⏱️  Completed in 1.4s\n"
+    },
+    {
+      "label": "alpha stats",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js stats --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai",
+      "output": "\n📊 Memory Statistics\n\nTotal Events: 6\nVector Count: 6\n\nMemory Levels:\n  L0: █ 6\n"
+    },
+    {
+      "label": "Q1 lifecycle lightweight expand/source",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js search disclosure expand source initialize vector workers lightweight --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai --top-k 5 --min-score 0.1",
+      "output": "\n📚 Search Results\n\nConfidence: high\nTotal local memories found: 3\nShared memories found: 0\n\n---\n📌 agent_response (2026-05-05)\n   Score: 1.000\n   Session: alpha-se...\n   Content: Decision recorded: For progressive retrieval disclosure, expand/source drill-down routes must stay lightweight. Do not call full MemoryService.initialize for disclosure expand/source because it can...\n\n---\n📌 agent_response (2026-05-05)\n   Score: 0.829\n   Session: alpha-se...\n   Content: Dashboard provenance decision: shared disclosure results should be rendered as shared_troubleshooting provenance, showing sourceProjectHash, sourceEntryId, topics, rootCause, and solution. The UI m...\n\n---\n📌 user_prompt (2026-05-05)\n   Score: 0.773\n   Session: alpha-se...\n   Content: When adding retrieval disclosure API routes, what lifecycle rule should we remember?\n\n"
+    },
+    {
+      "label": "Q2 FTS T.event_id fix",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js search T.event_id FTS rebuild internal table trigger event_id --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai --top-k 5 --min-score 0.1",
+      "output": "\n📚 Search Results\n\nConfidence: high\nTotal local memories found: 2\nShared memories found: 0\n\n---\n📌 agent_response (2026-05-05)\n   Score: 0.978\n   Session: alpha-se...\n   Content: Bug fix recorded: SQLite FTS rebuild failure 'no such column: T.event_id' is fixed by making events_fts an internal FTS5 table with columns content and event_id UNINDEXED using porter unicode61 tok...\n\n---\n📌 user_prompt (2026-05-05)\n   Score: 0.905\n   Session: alpha-se...\n   Content: How did we fix the SQLite FTS rebuild T.event_id failure?\n\n"
+    },
+    {
+      "label": "Q3 shared provenance dashboard",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js search shared_troubleshooting rootCause solution sourceProjectHash --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai --top-k 5 --min-score 0.1",
+      "output": "\n📚 Search Results\n\nConfidence: high\nTotal local memories found: 1\nShared memories found: 0\n\n---\n📌 agent_response (2026-05-05)\n   Score: 1.000\n   Session: alpha-se...\n   Content: Dashboard provenance decision: shared disclosure results should be rendered as shared_troubleshooting provenance, showing sourceProjectHash, sourceEntryId, topics, rootCause, and solution. The UI m...\n\n"
+    },
+    {
+      "label": "Q4 noise command artifact should not retrieve",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js search local-command-stdout command-name opus --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai --top-k 5 --min-score 0.1",
+      "output": "\n📚 Search Results\n\nConfidence: none\nTotal local memories found: 0\nShared memories found: 0\n\n"
+    },
+    {
+      "label": "Q5 project scoping negative DuckDB from alpha",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js search DuckDB legacy storage migrate --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai --top-k 5 --min-score 0.1",
+      "output": "\n📚 Search Results\n\nConfidence: none\nTotal local memories found: 0\nShared memories found: 0\n\n"
+    },
+    {
+      "label": "Q6 beta project positive DuckDB",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js search DuckDB legacy storage migrate --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/beta-legacy-duckdb --top-k 5 --min-score 0.1",
+      "output": "\n📚 Search Results\n\nConfidence: high\nTotal local memories found: 2\nShared memories found: 0\n\n---\n📌 user_prompt (2026-05-05)\n   Score: 1.000\n   Session: beta-ses...\n   Content: For the beta legacy storage project, should we migrate away from DuckDB?\n\n---\n📌 agent_response (2026-05-05)\n   Score: 0.922\n   Session: beta-ses...\n   Content: Legacy beta project decision: this old unrelated project should keep DuckDB and should not migrate to SQLite. This memory intentionally conflicts with alpha-commerce-ai and is used to test strict p...\n\n"
+    },
+    {
+      "label": "Q7 disclosure FTS query",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js search T.event_id FTS rebuild internal table --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai --top-k 3 --min-score 0.1 --disclosure --strategy fast",
+      "output": "\n🔎 Progressive Search Results\n\nMeta: total=2 vector=no keyword=yes fallback=no\n\n1. [source] Agent response\n   id: event:a5a01a44-67cb-4cef-b0e5-44c72925db9c\n   score: 1.000\n   reasons: keyword_match, recent_relevance, continuity_link\n   source: event:a5a01a44-67cb-4cef-b0e5-44c72925db9c\n   session: alpha-sessio...\n   snippet: Bug fix recorded: SQLite FTS rebuild failure 'no such column: T.event_id' is fixed by making events_fts an internal FTS5 table with columns content and event_id UNINDEXED using porter unicode61 tokenization. Rebuild by dropping and recre...\n\n2. [source] User prompt\n   id: event:eb14f3db-0aeb-424d-ae96-b2d6baefb731\n   score: 0.905\n   reasons: keyword_match, recent_relevance, continuity_link\n   source: event:eb14f3db-0aeb-424d-ae96-b2d6baefb731\n   session: alpha-sessio...\n   snippet: How did we fix the SQLite FTS rebuild T.event_id failure?\n\n"
+    },
+    {
+      "label": "Q8 expand first disclosure result",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js expand event:a5a01a44-67cb-4cef-b0e5-44c72925db9c --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai --window-size 2",
+      "output": "\n🧩 Expanded Retrieval Result\n\nTarget\n- [source] Agent response\n   id: event:a5a01a44-67cb-4cef-b0e5-44c72925db9c\n   score: 1.000\n   reasons: continuity_link\n   source: event:a5a01a44-67cb-4cef-b0e5-44c72925db9c\n   session: alpha-sessio...\n   snippet: Bug fix recorded: SQLite FTS rebuild failure 'no such column: T.event_id' is fixed by making events_fts an internal FTS5 table with columns content and event_id UNINDEXED using porter unicode61 tokenization. Rebuild by dropping and recre...\n\n\nSurrounding\n1. [source] Agent response\n   id: event:c0c2e795-eb98-4354-9ce0-cf453d967a87\n   score: 1.000\n   reasons: continuity_link\n   source: event:c0c2e795-eb98-4354-9ce0-cf453d967a87\n   session: alpha-sessio...\n   snippet: Decision recorded: For progressive retrieval disclosure, expand/source drill-down routes must stay lightweight. Do not call full MemoryService.initialize for disclosure expand/source because it can start embedders, vector workers, and sh...\n\n2. [source] User prompt\n   id: event:eb14f3db-0aeb-424d-ae96-b2d6baefb731\n   score: 1.000\n   reasons: continuity_link\n   source: event:eb14f3db-0aeb-424d-ae96-b2d6baefb731\n   session: alpha-sessio...\n   snippet: How did we fix the SQLite FTS rebuild T.event_id failure?\n\n3. [source] User prompt\n   id: event:34f59596-f65f-4520-9a88-6ba835b8018a\n   score: 1.000\n   reasons: continuity_link\n   source: event:34f59596-f65f-4520-9a88-6ba835b8018a\n   session: alpha-sessio...\n   snippet: For dashboard shared retrieval provenance, what should the UI show?\n\n4. [source] Agent response\n   id: event:9b376621-c598-42fc-826a-306b3603ba18\n   score: 1.000\n   reasons: continuity_link\n   source: event:9b376621-c598-42fc-826a-306b3603ba18\n   session: alpha-sessio...\n   snippet: Dashboard provenance decision: shared disclosure results should be rendered as shared_troubleshooting provenance, showing sourceProjectHash, sourceEntryId, topics, rootCause, and solution. The UI must state that there are no local raw ev...\n\n\nSources\n- event:c0c2e795-eb98-4354-9ce0-cf453d967a87 (imported_history) events=c0c2e795-eb98-4354-9ce0-cf453d967a87\n- event:eb14f3db-0aeb-424d-ae96-b2d6baefb731 (imported_history) events=eb14f3db-0aeb-424d-ae96-b2d6baefb731\n- event:a5a01a44-67cb-4cef-b0e5-44c72925db9c (imported_history) events=a5a01a44-67cb-4cef-b0e5-44c72925db9c\n- event:34f59596-f65f-4520-9a88-6ba835b8018a (imported_history) events=34f59596-f65f-4520-9a88-6ba835b8018a\n- event:9b376621-c598-42fc-826a-306b3603ba18 (imported_history) events=9b376621-c598-42fc-826a-306b3603ba18\n\nExpanded Context\n[agent_response] Decision recorded: For progressive retrieval disclosure, expand/source drill-down routes must stay lightweight. Do not call full MemoryService.initialize for disclosure expand/source because it can start embedders, vector workers, and shared promotion machinery. Use narrow SQLiteEventStore getEvent/getSessionEvents or shared-store lookup ports instead. API tests should assert initialize is not called for GET expand/source routes, including 404 paths.\n\n[user_prompt] How did we fix the SQLite FTS rebuild T.event_id failure?\n\n[agent_response] Bug fix recorded: SQLite FTS rebuild failure 'no such column: T.event_id' is fixed by making events_fts an internal FTS5 table with columns content and event_id UNINDEXED using porter unicode61 tokenization. Rebuild by dropping and recreating events_fts and then recreate triggers that write rowid, content, and event_id. Also cover deleteSessionEvents followed by rebuildFtsIndex.\n\n[user_prompt] For dashboard shared retrieval provenance, what should the UI show?\n\n[agent_response] Dashboard provenance decision: shared disclosure results should be rendered as shared_troubleshooting provenance, showing sourceProjectHash, sourceEntryId, topics, rootCause, and solution. The UI must state that there are no local raw events for a shared source instead of pretending shared memories are local event IDs. Escape all metadata before innerHTML rendering.\n\n"
+    },
+    {
+      "label": "Q9 source first disclosure result",
+      "exit": 0,
+      "cmd": "node /Users/namsangboy/workspace/claude-memory-layer/dist/cli/index.js source event:a5a01a44-67cb-4cef-b0e5-44c72925db9c --project /var/folders/vw/0ts5bq8n0k31vy_y7t0pd1nw0000gp/T/cml-usefulness-5q7j2p0p/projects/alpha-commerce-ai",
+      "output": "\n📎 Retrieval Source\n\nsourceRef: event:a5a01a44-67cb-4cef-b0e5-44c72925db9c\nsourceType: imported_history\neventIds: a5a01a44-67cb-4cef-b0e5-44c72925db9c\n\nRaw Events\n- a5a01a44-67cb-4cef-b0e5-44c72925db9c 2026-05-05T01:38:20.318Z\n  [agent_response] Bug fix recorded: SQLite FTS rebuild failure 'no such column: T.event_id' is fixed by making events_fts an internal FTS5 table with columns content and event_id UNINDEXED using porter unicode61 tokenization. Rebuild by dropping and recreating events_fts and then recreate triggers that write rowid, content, and event_id. Also cover deleteSessionEvents followed by rebuildFtsIndex.\n  session: alpha-session\n  canonicalKey: bug fix recorded sqlite fts rebuild failure no such column teventid is fixed by making eventsfts an internal fts5 table with columns content and eventid unindexed using porter unicode61 token_2e1a5fce\n\n"
+    }
+  ]
+}