claude_memory 0.9.1 → 0.11.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b6df0a3f58a88c1bbec82ec20e26789d51ad2712408d058337a196c5eac90654
-  data.tar.gz: beb9c2ef59ef6a45430eeb03466e37f6b1f741ef1745b5303a1443b02a7c84b4
+  metadata.gz: c2164011e2c50c7fdb0bcad468a25814f372384c3a49fa4c9414313ab3975e00
+  data.tar.gz: 3e2843979d9b9e0d4a21bfa3650f6cd6843ce18d2a95af884e303572259bca62
 SHA512:
-  metadata.gz: '06905bca1f77df5642caf0846cde7394ba9a1baf3c954138383ac39927fcaae2ef097ff79dd3c866e6930fa0eac0d0fb958366bded54a0616d8e356a316e616c'
-  data.tar.gz: 9a8e3c455c20ae616bc239b766e1d4e2aa4c6e5448f494294d9c6a646a8a613428e9b63218624c5cae7e30f389704dd3bee6b788e97a369cb719b115abffddd7
+  metadata.gz: 6c074b607c1e4f13743de36bb2074495d0ad24d0c826b62b49e0e827f311e3424bc881f42236db22a92dd2d5281e6ef13ca450966b1d9438ac1b36ceaa3ab2ce
+  data.tar.gz: 4e06c8fed9c323974ee4d7e5b41386ee4682ba5ba88b67797ac6864bbdf03663e5b74cb33497a371a8263eff4c24d405708a80e4862c4f578b221286bf40b236

data/.claude/skills/dashboard/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: dashboard
+description: Launch a local web dashboard for ClaudeMemory debugging and observability
+---
+
+# Dashboard
+
+Launch the ClaudeMemory debugging dashboard to visualize memory system health, activity, and efficacy.
+
+## Task
+
+Start the dashboard web server so the user can inspect what's happening behind the scenes.
+
+## Steps
+
+1. Run the dashboard command:
+
+```bash
+claude-memory dashboard
+```
+
+This starts a local web server (default port 3377) and opens it in the browser.
+
+## What the Dashboard Shows
+
+- **Health Status**: Database health, hook configuration, vector index status
+- **Overview**: Fact/entity/content counts, top predicates, entity type distribution, 30-day activity timeline
+- **Activity**: Live event log of hook executions (ingest, context, sweep), memory recalls, and store extractions with timing and details
+- **Facts**: Searchable fact explorer with status filtering, predicate/object search
+- **Efficacy**: Recall hit rate, total results served, average results per query, top queries by result count
+
+## Options
+
+- `--port PORT` - Use a different port (default: 3377)
+- `--no-open` - Don't auto-open the browser
+
+## Notes
+
+- Dashboard auto-refreshes every 30 seconds
+- Activity events are recorded by hooks and MCP tools into the `activity_events` table
+- The dashboard reads from both global and project databases
+- Press Ctrl+C to stop the server

data/.claude-plugin/marketplace.json

@@ -7,7 +7,7 @@
   "plugins": [
     {
       "name": "claude-memory",
-      "version": "0.9.1",
+      "version": "0.11.0",
       "source": "./",
       "description": "Long-term memory for Claude Code. Recalls architecture, conventions, and decisions across sessions — so Claude explains your codebase without file traversal, follows your patterns, and never re-asks what it already learned.",
       "repository": "https://github.com/codenamev/claude_memory"

data/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-memory",
-  "version": "0.9.1",
+  "version": "0.11.0",
   "description": "Long-term memory for Claude Code. Recalls architecture, conventions, and decisions across sessions — so Claude explains your codebase without file traversal, follows your patterns, and never re-asks what it already learned.",
   "author": {
     "name": "Valentino Stoll",

data/CHANGELOG.md

@@ -4,6 +4,136 @@ All notable changes to this project will be documented in this file.
 
 ## [Unreleased]
 
+## [0.11.0] - 2026-04-30
+
+Theme: **Trust & Cost** — five user-visible signals that answer "is memory still worth it?" with numbers a skeptical user can read in <30 seconds.
+
+### Added
+
+- **Token budget telemetry** — every successful SessionStart context injection now records an estimated `context_tokens` count on its `activity_events` row. Surfaced three ways:
+  - Dashboard Trust panel emits a `token_budget` block with p50/p95/avg/sample_size over the last 30 days, so the JSON dashboard endpoint and any downstream consumer answer "what does memory cost per session?"
+  - `claude-memory digest` includes a "Context cost" subsection between activity and new-knowledge so the weekly report shows the price tag next to the value.
+  - `claude-memory stats --tokens [--since DAYS]` reports total sessions, p50/p95/avg/min/max, and a histogram across <500 / 500-1k / 1-2k / 2-5k / 5k+ buckets.
+- Pure additive — no schema migration. Historical events written before this release simply contribute zero samples until new injections accumulate.
+- First 0.11.0 milestone item from the 1.0 punchlist (Trust & Cost). Closes the "what % of my SessionStart token budget does memory consume?" gap.
+- **Hallucination rate metric** — the dashboard now quantifies how clean the fact base is, not just how full it is. `Distill::BareConclusionDetector` is the production-side mirror of the SessionStart prompt's reason-clause requirement (decision/convention facts must embed "because…" / "so that…" / "to avoid…"). Surfaced two ways:
+  - Dashboard Trust panel emits a `quality_score` block aggregating across project + global active facts: `suspect_count` (predicate=reference, retagged by ReferenceMaterialDetector), `bare_conclusion_count`, percentages, and an overall 0–100 score (higher = cleaner). Returns 100 on empty stores so fresh installs aren't penalized.
+  - `claude-memory digest` includes a "Quality" section showing the score breakdown plus the in-window rejection rate ("of facts created in the last 7 days, X% have been rejected since"), so calibration drift is visible.
+- Second 0.11.0 milestone item. Pairs with token-budget telemetry to answer "is memory still worth its cost?" via two skeptic-friendly numbers.
+- **`claude-memory show`** — new CLI command prints what memory would inject at the next SessionStart in plain Markdown. Runs the exact `Hook::ContextInjector` path real sessions use, so output matches what Claude actually receives. Footer reports fact count, ~token estimate, and char count so users see the SessionStart cost at a glance.
+  - Default suppresses the raw-transcript "Pending Knowledge Extraction" dump (intended for LLM distillation, not human reading); pass `--pending` to include it.
+  - `--source SOURCE` (startup/resume/clear) simulates each fresh-session entrypoint so users can preview which sections would appear.
+- Third 0.11.0 milestone item. Closes the inspectability gap — trust requires being able to see what memory will inject, the same way `cat CLAUDE.md` works.
+- **First-week ROI nudge** — at SessionEnd, memory now prints `memory contributed N facts this session, %used = X` for the first 10 sessions, then quiets. New users get user-visible proof memory is doing work for them without having to know about the dashboard. Once trust is established (or it isn't), the nudge gets out of the way.
+  - New `claude-memory hook nudge` subcommand + `Hook::Handler#nudge`. SessionEnd config now wires `[ingest, sweep, nudge]` in order.
+  - Silent on `CLAUDE_MEMORY_NO_NUDGE=1` opt-out, missing session_id, n=0 contributions, and after MAX_NUDGES emissions. The empty-session silent path doesn't burn a slot — quiet sessions don't count toward the 10.
+  - Activity event `roi_nudge` records `{n, used, pct, prior_count}` per emission so a future migration could change the threshold without re-counting from raw events.
+- Fourth 0.11.0 milestone item. Cold-start trust signal that pairs with #47 (token cost) and #48 (quality) to make the first-week answer to "is this worth it?" visible without effort.
+- **Harm benchmark prototype** — `spec/benchmarks/dataset/harm_scenarios.yml` + `spec/benchmarks/e2e/harm_bench_spec.rb`. Three hand-written cases spanning the riskiest harm classes (stale_tech, mismatched_scope, superseded_undetected). The first ClaudeMemory benchmark that measures whether memory can make Claude *wrong* — every other benchmark only measures whether memory helps.
+  - Structure validation (regex compile, fact loadability, harm-class coverage) runs in stub mode as part of `:benchmark` tag.
+  - Real-mode runner: `EVAL_MODE=real bundle exec rspec spec/benchmarks/e2e/harm_bench_spec.rb` — needs `claude` CLI on PATH, ~$2-8 per run. Reports harm rate; doesn't enforce a threshold yet (that's the 0.12 release gate).
+- 0.11.0 risk-de-risking item. If even one of these three surfaces a harm now, the full 10-15-case benchmark planned for 0.12 will likely reveal a fundamental issue — better to learn that at 0.11 than at 0.12. **Real-mode prototype run on 2026-04-30 reported 0/3 harm** — green light to expand to the full corpus in 0.12.
+
+### Changed
+
+- **Hallucination-rate metric calibration** — `Dashboard::Trust#quality_score` now reports a windowed (last 30d) "live" score as the headline plus a "historical" block over all active facts. Production verification on 2026-04-30 (recorded in `docs/quality_review.md`) showed the unwindowed metric was technically correct but pragmatically misleading: 97% of bare-conclusion facts pre-dated the 2026-04-20 reason-clause prompt commit, and the entire 7-day rejection cluster was a single-class systemic failure (a `/study-repo` burst), not ongoing noise. The split makes the metric actionable: live score = ongoing extraction quality, historical = legacy data. The digest's "Quality" section uses the live score as the headline.
+
+### Fixed
+
+- Real-eval CLI runner now passes `allowed_tools` through explicitly so the harm benchmark and other real-mode benches can pre-allow MCP memory tools without per-test wiring.
+
+### Upgrade Notes
+
+- No schema migration. All new features ship purely additive.
+- Hooks run the installed gem from PATH, not the working tree. After upgrading, `bundle exec rake install` (or `gem install claude_memory`) is required for the new SessionEnd nudge, `claude-memory show` command, `--tokens` stats flag, and `context_tokens` activity-event field to actually fire on real hook events.
+- Existing `quality_score` consumers will see additional fields (`window_days`, `historical`) in the snapshot. The original keys (`score`, `total_active`, `suspect_count`, `bare_conclusion_count`, `suspect_pct`, `bare_pct`) remain at the top level and now reflect the 30-day live window — historical numbers move to the `historical` sub-hash.
+
+## [0.10.0] - 2026-04-28
+
+### Added
+
+**Dashboard — feed-first redesign with observability built in**
+
+- New feed-first dashboard UI with scope-aware moments, fact detail modal, query tester, and activity drilldown. Reuse, Trust, Knowledge, Conflicts, and Moments panels each backed by a dedicated module (`Dashboard::{Reuse, Trust, Knowledge, Conflicts, Moments}`) under unit tests, replacing the prior all-in-API-class layout.
+- 👍/👎 feedback on individual moments with persisted verdicts (schema v16, `moment_feedback` table). Trust panel surfaces a 30-day up/down ratio so the dashboard can answer "when memory surfaces something, are users marking it useful?".
+- Utilization ratio panel — of facts extracted in the last 30 days, how many has Claude actually used in a recall or context injection? Color-coded (green ≥40%, yellow ≥15%, red below). Hidden on fresh installs to avoid misleading zeros.
+- Conflict deduping at the display layer: identical (subject, predicate, object_pair) detections collapse into one row with a `×N` badge. Sidebar "Needs review" count now reflects distinct contradictions, not raw row count.
+- Activity events drilldown: each moment opens a payload modal with prettified JSONL, recall trigger correlation (which user prompt motivated this lookup), and linked-fact resolution scoped per database.
+- Vector index health threshold and clickable remediation hints in the health dashboard.
+
+**CLI — observability surfaces and one-shot cleanups**
+
+- `claude-memory digest [--since DAYS] [--output FILE]` — weekly markdown report. Sections: Activity, New knowledge by predicate, Utilization (extracted vs used), Conflicts, Feedback. No new schema; renders from existing aggregates.
+- `claude-memory census [--root DIR]` — privacy-safe cross-project vocabulary scan. Aggregates per-DB predicate × status counts, novel predicates, synonym candidates. Suppresses object literals, entity names, and paths; per-DB IDs are SHA256-prefixed.
+- `claude-memory dedupe-conflicts [--scope SCOPE] [--dry-run]` — one-shot cleanup for historical conflict-row duplication that predates the Resolver dedup fix (commit f571ba4). Groups by (subject, predicate, normalized object pair), keeps the earliest, migrates provenance to the keeper.
+- `claude-memory reclassify-references [--scope SCOPE] [--dry-run]` — retags active convention facts that the new `Distill::ReferenceMaterialDetector` flags as reference material (LOC counts, star counts, "X is a plugin..." templates, "by Firstname Lastname" attributions).
+
+**Memory quality**
+
+- Access-based staleness scoring (improvements.md #35). Schema v17 adds `last_recalled_at` to facts. `Sweep::RecallTimestampRefresher` derives the field periodically from activity_events; `claude-memory stats --stale [--stale-days N]` lists facts that haven't been recalled inside the threshold. Replaces the prior "active facts minus seen-in-recalls" approximation.
+- Auto-memory mirror (improvements.md #36). On fresh sessions, the SessionStart context hook scans `~/.claude/projects/<slug>/memory/*.md` and surfaces new or changed entries as extraction candidates so users can promote auto-memory observations into claude_memory without manual copy-paste.
+- Reasoning requirement enforced in distillation (improvements.md #34). The SessionStart prompt and the `/distill-transcripts` skill now require a why clause for `decision` and `convention` predicates ("because…", "so that…", etc.). Audit found ~75% of facts were bare conclusions before this change.
+- `Distill::ReferenceMaterialDetector` reclassifies convention facts whose object text matches reference patterns. New `reference` predicate registered in `PredicatePolicy` with its own `:references` snapshot section. Detector runs at write time in `ManagementHandlers#store_extraction` so mislabeling can't persist.
+- Predicate census command (#30) for cross-project vocabulary audits — see CLI section above.
+
+**Benchmarks and observability**
+
+- Repeat-correction benchmark harness (improvements.md #32). `spec/benchmarks/e2e/repeat_correction_spec.rb` pre-loads a past correction as a memory fact, runs the prompt through real Claude under `EVAL_MODE=real`, and reports pass rate (no violation patterns matched). Starter set of 2 scenarios drawn from this project's recurring gotchas.
+- Relevance ratio metric (improvements.md #31). `Hook::ContextInjector#emitted_subjects` exposes the subjects injected at SessionStart; `BenchmarkHelpers::RelevanceMetrics` measures whether they appear in Claude's response. Trend signal for memory-application quality, integrated into `devmemeval_spec.rb`.
+- MCP server embeds the V=R/C ("Verify before Recommend / Correct") mental model in agent instructions so memory recommendations come with built-in verification cues.
+
+**Schema v15 → v17 (additive only, automatic on first run)**
+
+- Migration 015: adds `activity_events` table for hook/recall/context/sweep telemetry. Powers the dashboard timeline, moments feed, and efficacy reports.
+- Migration 016: adds `moment_feedback` table (unique on event_id) for the dashboard 👍/👎 surface.
+- Migration 017: adds nullable `facts.last_recalled_at` for access-based staleness scoring.
+
+**1.0 readiness track**
+
+- New `docs/1_0_punchlist.md` opens the path to 1.0: token-budget telemetry, hallucination-rate metric, negative-fact harm benchmark, CLAUDE.md baseline publication, `claude-memory show`, benchmark scoreboard. Ten entries (#47-56) added to `docs/improvements.md` with concrete file:line plumbing notes.
+
+### Changed
+
+- `Resolver#apply_conflict` no longer creates a duplicate disputed fact + conflict row when the same contradicting value is re-extracted. Looks up disputed facts in the same (subject, predicate) slot and reinforces with provenance instead.
+- `Resolver` no longer treats the distiller's `scope_hint` as a scope override. `scope_hint` is advisory metadata; `fact.scope` must match the DB the row lives in. Earlier behavior caused scope leakage where global-hinted distillations landed in the project DB.
+- `Hook::ContextInjector` adds `emitted_fact_ids` and `emitted_subjects` accessors so benchmark harnesses can attribute injection contributions per session.
+- `SQLiteStore` decomposed via module inclusion: `LLMCache` and `MetricsAggregator` extracted into `lib/claude_memory/store/`. SQLiteStore back under 600 LOC.
+- `Dashboard::API` decomposed: `FactPresenter`, `Conflicts`, `Efficacy::Reporter`, `Timeline`, `Health` extracted into dedicated classes following the boundary pattern. API now routes/delegates rather than aggregating.
+- Dashboard releases DB connections after each HTTP request (was holding connections open for the lifetime of the WEBrick session).
+- `Sweep::Maintenance` gains `dedupe_open_conflicts` and `reclassify_references` for the one-shot CLI commands above.
+- Round-trip migration specs from v12, v13, v14 → v17 (per-version migrations covered by `spec/claude_memory/store/migrations/`). Codifies the release-blocker convention: any schema bump must round-trip from each prior major-release boundary back ~3 releases.
+
+### Fixed
+
+- Dashboard surfaces an actionable hint when Recall hits FTS5 corruption (run `claude-memory compact` rather than a generic error).
+- Dashboard query tester unwraps the nested Recall result shape rather than printing the raw envelope.
+- Dashboard health checks correctly detect the claude-memory hook installation across the two-level Claude Code hooks structure (was reporting false negatives when hooks were installed under a matcher block).
+- Dashboard Efficacy "this session" correlation falls back to a time window when the recall event has no `session_id` (MCP tool calls don't thread session_id).
+- Bulk-reject in the Conflicts modal now retries with an actionable message when the server-side state is stale.
+
+### Upgrade Notes
+
+**Schema bump v14 → v17.** Three migrations run automatically on first launch after upgrade. All three are additive (no existing data is rewritten):
+
+1. Migration 015 creates `activity_events` (hook/recall telemetry).
+2. Migration 016 creates `moment_feedback` (dashboard verdicts).
+3. Migration 017 adds `facts.last_recalled_at` (NULL by default; `Sweep::RecallTimestampRefresher` populates it on the next sweep cycle from existing activity_events).
+
+The migration delta has round-trip spec coverage in `spec/claude_memory/store/migrations/`. Forward-compatibility: 0.10.0 databases cannot be opened by 0.9.x or earlier. Downgrade is destructive — back up `~/.claude/memory.sqlite3` and `.claude/memory.sqlite3` before downgrading.
+
+**Optional historical cleanups.** Two new admin commands address data tails left by earlier bugs that have since been fixed at the source:
+
+```bash
+claude-memory dedupe-conflicts --dry-run   # preview duplicate conflict rows
+claude-memory dedupe-conflicts             # consolidate them
+claude-memory reclassify-references --dry-run   # preview reference-material mislabels
+claude-memory reclassify-references             # retag them
+```
+
+Both are opt-in. Neither runs in the regular sweep cycle. Use `--scope global` to clean the global DB.
+
+**Telemetry footprint.** The `activity_events` table grows with hook activity. The dashboard surfaces this by default and powers the timeline/moments/efficacy panels. Retention pruning is not yet automatic (planned for a follow-up); manual cleanup via `DELETE FROM activity_events WHERE occurred_at < ?` is safe — the dashboard tolerates missing history.
+
 ## [0.9.1] - 2026-04-16
 
 ### Fixed

data/CLAUDE.md

@@ -163,7 +163,7 @@ New MCP tools `memory.undistilled` and `memory.mark_distilled` support the pipel
   - Each command is a separate class (HelpCommand, DoctorCommand, etc.)
   - All commands inherit from BaseCommand
   - Dependency injection for I/O (stdout, stderr, stdin)
-  - 28 commands total, each focused on single responsibility
+  - 34 commands total, each focused on single responsibility
 
 - **`Configuration`**: Centralized ENV access (`configuration.rb`)
   - Single source of truth for paths and environment variables
@@ -208,6 +208,9 @@ New MCP tools `memory.undistilled` and `memory.mark_distilled` support the pipel
 - **`Distill`**: Fact extraction interface (`distill/`)
   - Pluggable distiller design (current: NullDistiller stub)
   - Extracts entities, facts, scope hints from content
+  - `ReferenceMaterialDetector`: classifies "X is a plugin/library/tool" templates, LOC counts, "by Firstname Lastname" attributions as reference material. Runs in `ManagementHandlers#store_extraction` so mislabeling can't persist
+  - `BareConclusionDetector` (0.11.0+): production-side mirror of the SessionStart prompt's reason-clause requirement. Pure function — flags `decision` / `convention` facts whose object lacks a reason-clause signal ("because", "so that", "to avoid", etc.). Powers the `quality_score` metric on the Trust panel and the digest's Quality section.
+  - SessionStart distillation prompt enforces reason clauses ("because…", "so that…") for `decision` and `convention` predicates — bare conclusions are explicitly disallowed
 
 - **`Resolve`**: Truth maintenance and conflict resolution (`resolve/`)
   - Determines equivalence, supersession, or conflicts
@@ -226,7 +229,7 @@ New MCP tools `memory.undistilled` and `memory.mark_distilled` support the pipel
   - Modes: shared (repo), local (uncommitted), home (user directory)
 
 - **`MCP`**: Model Context Protocol server and tools (`mcp/`)
-  - Exposes memory tools to Claude Code (24 tools total)
+  - Exposes memory tools to Claude Code (25 tools total)
   - `Telemetry`: Records tool invocations to `mcp_tool_calls` table for usage stats
   - Dual content/structuredContent responses with compact mode
 
@@ -234,6 +237,7 @@ New MCP tools `memory.undistilled` and `memory.mark_distilled` support the pipel
   - Reads stdin JSON from Claude Code hooks
   - Routes to ingest/sweep/publish commands
   - `DistillationRunner`: Manages context hook injection with undistilled content for LLM extraction
+  - `AutoMemoryMirror` (0.10.0): On fresh sessions, scans `~/.claude/projects/<slug>/memory/*.md` for new/changed entries and surfaces them as extraction candidates in the SessionStart context. State diffed by md5 in `.claude/auto_memory_mirror.json`; bounded to 5 candidates per session, 1500 chars each.
 
 ### Database Schema
 
@@ -246,16 +250,19 @@ Key tables (defined in `sqlite_store.rb`):
 - `fact_links`: Supersession and conflict relationships
 - `conflicts`: Open contradictions
 - `mcp_tool_calls`: MCP server tool invocation telemetry (schema v13)
+- `activity_events`: Hook/recall/context/sweep/nudge telemetry (schema v15) — powers the dashboard timeline, moments feed, efficacy reports. Event types: `hook_ingest`, `hook_context` (carries `context_tokens` since 0.11.0), `hook_sweep`, `hook_publish`, `recall`, `store_extraction`, `roi_nudge` (since 0.11.0).
+- `moment_feedback`: Per-moment 👍/👎 verdicts with optional notes (schema v16) — unique on event_id, repeat clicks upsert
 
 Facts include:
 - `scope`: "global" or "project" (determines applicability)
 - `project_path`: Set for project-scoped facts
 - `valid_from`/`valid_to`: Temporal validity window
+- `last_recalled_at` (schema v17): Set by `Sweep::RecallTimestampRefresher` from activity_events; powers `claude-memory stats --stale` and the dashboard's "stale" needs-review count
 
 ### Scope System
 
 Facts are scoped to control where they apply:
-- **project**: Current project only (e.g., "this app uses PostgreSQL")
+- **project**: Current project only (e.g., "claude_memory uses SQLite for storage")
 - **global**: All projects (e.g., "I prefer 4-space indentation")
 
 Distiller detects signals like "always", "in all projects", "my preference" and sets `scope_hint: "global"`. Users can manually promote facts via `claude-memory promote <fact_id>` or the `memory.promote` MCP tool.
@@ -325,7 +332,7 @@ Also update `SECTION_MAP` if the predicate should appear in a specific snapshot
 
 - `lib/claude_memory.rb`: Main module, requires, database path helpers
 - `lib/claude_memory/cli.rb`: Thin command router (41 lines)
-- `lib/claude_memory/commands/`: Individual command classes (28 commands)
+- `lib/claude_memory/commands/`: Individual command classes (34 commands)
 - `lib/claude_memory/configuration.rb`: Centralized configuration and ENV access
 - `lib/claude_memory/domain/`: Domain models (Fact, Entity, Provenance, Conflict)
 - `lib/claude_memory/core/`: Value objects and null objects
@@ -340,14 +347,14 @@ Also update `SECTION_MAP` if the predicate should appear in a specific snapshot
 
 The gem includes an MCP server (`claude-memory serve-mcp`) that exposes memory operations as tools. Configuration should be in `.mcp.json` at project root.
 
-Available MCP tools (24 total):
+Available MCP tools (25 total):
 - **Query & Recall**: `memory.recall`, `memory.recall_index`, `memory.recall_details`, `memory.recall_semantic`, `memory.search_concepts`
 - **Provenance**: `memory.explain`, `memory.fact_graph`
 - **Shortcuts**: `memory.decisions`, `memory.conventions`, `memory.architecture`
 - **Context**: `memory.facts_by_tool`, `memory.facts_by_context`
 - **Management**: `memory.promote`, `memory.reject_fact`, `memory.store_extraction`
 - **Distillation**: `memory.undistilled`, `memory.mark_distilled`
-- **Monitoring**: `memory.status`, `memory.stats`, `memory.changes`, `memory.conflicts`
+- **Monitoring**: `memory.status`, `memory.stats`, `memory.changes`, `memory.conflicts`, `memory.activity`
 - **Maintenance**: `memory.sweep_now`
 - **Discovery**: `memory.check_setup`, `memory.list_projects`
 
@@ -367,8 +374,25 @@ ClaudeMemory integrates with Claude Code via hooks in `.claude/settings.json`:
   - Runs time-bounded maintenance on both databases
   - Cleans up vec0 entries for superseded/expired facts
 
+- **Nudge hook** (0.11.0+): Triggers on SessionEnd, fires after ingest+sweep
+  - Calls `claude-memory hook nudge`
+  - For the first 10 sessions only, prints "memory contributed N facts this session, %used = X" to stdout so new users see ROI inline before they discover the dashboard
+  - Records `roi_nudge` activity_events; quiets after `MAX_NUDGES` emissions
+  - Opt out with `CLAUDE_MEMORY_NO_NUDGE=1` (no event recorded on opt-out)
+  - Empty sessions (n=0) silently no-op so quiet sessions don't burn nudge slots
+
 Hook commands read JSON payloads from stdin for robustness. Supports `--async` flag for non-blocking execution.
 
+## Dashboard
+
+Local web UI for inspecting memory state. Started via `claude-memory dashboard` (default port 3377). Reads from both global and project databases; no write side effects from page loads.
+
+The dashboard is a thin web layer over the same `Recall`/`Conflicts`/`Trust`/`Moments`/`Knowledge`/`Reuse`/`Health`/`Timeline` classes the MCP server uses. Each panel is backed by a dedicated module under `lib/claude_memory/dashboard/`; `Dashboard::API` holds HTTP-shape glue and per-endpoint formatting (delegating non-trivial logic to the panel classes).
+
+Connections are released after each request — never holds a WAL writer lock open across page loads.
+
+See [docs/dashboard.md](docs/dashboard.md) for the user-facing guide (panels, common workflows, related CLI commands).
+
 ## Code Style
 
 This project uses [Standard Ruby](https://github.com/standardrb/standard) for linting. Run `bundle exec rake standard:fix` before committing.

data/README.md

@@ -140,6 +140,69 @@ File-searchable questions ("what version is this?") and one-shot code generation
 - **Claude-Powered**: Uses Claude's intelligence to extract facts (no API key needed)
 - **Token Efficient**: 10x reduction in memory queries with progressive disclosure
 - **Database Maintenance**: Compact, export, and backup commands
+- **Built-in Observability** (0.10.0+): `claude-memory dashboard` opens a local web UI with a moments feed, trust panel (token budget, quality score, utilization, feedback), conflicts dedup, knowledge index, and 👍/👎 feedback. See **[Dashboard guide →](docs/dashboard.md)**. `claude-memory digest` writes a weekly markdown report (Activity, Context cost, Quality, New knowledge, Utilization, Conflicts, Feedback); `claude-memory show` prints what would be injected next SessionStart; `claude-memory census` audits the predicate vocabulary across projects.
+
+## What's New in 0.11.0
+
+Five user-visible signals so you can answer "is memory still worth it?" with
+numbers, not vibes:
+
+- **Token budget telemetry** — every SessionStart context injection now
+  records its estimated `context_tokens`. `claude-memory stats --tokens
+  [--since DAYS]` reports p50/p95/avg/min/max plus a histogram across
+  <500 / 500-1k / 1-2k / 2-5k / 5k+ buckets so you can see the per-session
+  cost at a glance. The dashboard's Trust panel and `claude-memory digest`
+  surface the same numbers.
+- **Hallucination-rate metric** — the dashboard now scores how *clean* the
+  fact base is, not just how full it is. `Distill::BareConclusionDetector`
+  flags `decision` / `convention` facts that skipped the reason-clause
+  requirement. Trust panel shows `quality_score` (live 30-day window with
+  historical baseline beneath). `claude-memory digest` adds a Quality
+  section with rejection rate.
+- **`claude-memory show`** — new command prints what memory *would* inject
+  at the next SessionStart in plain Markdown. Footer reports fact count,
+  ~token estimate, and char count so you see the cost at a glance. Default
+  hides the raw-transcript "Pending Knowledge" dump for readability;
+  `--pending` opts in. `--source startup|resume|clear` simulates each
+  fresh-session entrypoint.
+- **First-week ROI nudge** — at SessionEnd, memory now prints
+  `memory contributed N facts this session, %used = X` for the first 10
+  sessions, then quiets. Cold-start trust signal — you don't have to know
+  about the dashboard. Opt out with `CLAUDE_MEMORY_NO_NUDGE=1`.
+- **Harm benchmark prototype** — first ClaudeMemory benchmark that
+  measures whether memory can make Claude *wrong*. Three hand-written
+  cases (stale-tech, mismatched-scope, superseded-but-undetected) under
+  `spec/benchmarks/e2e/harm_bench_spec.rb`. Real-mode run on the 0.11
+  release reported 0/3 harm; the full 10-15-case corpus + release gate
+  lands in 0.12.
+
+## What's New in 0.10.0
+
+Three behavior changes worth knowing about — they affect what you'll see in
+extracted facts and SessionStart context, even if you don't change anything:
+
+- **Auto-memory mirror** — On fresh sessions, the SessionStart context hook
+  scans `~/.claude/projects/<slug>/memory/*.md` and surfaces new or changed
+  entries as candidates for extraction into ClaudeMemory. You'll see a
+  "Pending Knowledge Extraction" section in Claude's startup context citing
+  files from your auto-memory directory. Claude reviews these and calls
+  `memory.store_extraction` for the high-signal ones; you don't need to
+  copy-paste manually anymore.
+- **Why-clause enforcement** — When Claude distills `decision` and
+  `convention` facts, it's now required to embed a reason ("…because…",
+  "…so that…", "…to avoid…"). A bare conclusion is dead weight; a fact with
+  a reason stays useful when the situation changes. You'll see this
+  reflected in fact text being longer and more justified.
+- **Reference predicate** — Active facts that look like reference material
+  (LOC counts, "X is a plugin/library/tool" templates, "by Firstname
+  Lastname" attributions) are auto-tagged `predicate=reference` instead of
+  `convention`. Keeps the conventions list signal-rich. Browse them in the
+  dashboard's Knowledge → References section, or run
+  `claude-memory reclassify-references --dry-run` to see candidates.
+
+Plus: **staleness detection** (`claude-memory stats --stale`) lists active
+facts that haven't been recalled in N days, so you can prune dead weight
+explicitly. The dashboard's Trust → Needs review panel surfaces the count.
 
 ## Privacy Control
 
@@ -241,7 +304,8 @@ The uninstall command removes:
 
 - 📖 [Getting Started](docs/GETTING_STARTED.md) - Step-by-step onboarding
 - 💡 [Examples](docs/EXAMPLES.md) - Use cases and workflows
-- 🔧 [Plugin Setup](docs/PLUGIN.md) - Claude Code integration
+- 📊 [Dashboard](docs/dashboard.md) - Local web UI for inspection and trust signals (0.10.0+)
+- 🔧 [Plugin Setup](docs/plugin.md) - Claude Code integration
 - 🏗️ [Architecture](docs/architecture.md) - Technical deep dive
 - 📝 [Changelog](CHANGELOG.md) - Release notes
 
@@ -292,7 +356,7 @@ The benchmark dataset draws from real CLAUDE.md patterns and is designed specifi
 
 - **Language:** Ruby 3.2+
 - **Storage:** SQLite3 (no external services)
-- **Testing:** 1477 examples (1375 unit/integration + 102 benchmarks/evals), 100% core coverage
+- **Testing:** 1964 examples (~1700 unit/integration + ~250 benchmarks/evals), 100% core coverage
 - **Code Style:** Standard Ruby
 
 ```bash

data/db/migrations/015_add_activity_events.rb

@@ -0,0 +1,26 @@
+# frozen_string_literal: true
+
+# Migration v15: Add activity_events table for debugging and observability
+# Tracks hook executions, memory recalls, context injections, and sweep operations.
+# Powers the dashboard timeline and efficacy reports.
+Sequel.migration do
+  up do
+    create_table?(:activity_events) do
+      primary_key :id
+      String :event_type, null: false    # "hook_ingest", "hook_context", "hook_sweep", "recall", "store_extraction"
+      String :session_id                 # Claude session that triggered the event
+      String :status, null: false        # "success", "skipped", "error"
+      Integer :duration_ms               # How long the operation took
+      String :detail_json, text: true    # Event-specific details (JSON)
+      String :occurred_at, null: false   # ISO 8601 timestamp
+    end
+
+    run "CREATE INDEX IF NOT EXISTS idx_activity_events_type ON activity_events(event_type)"
+    run "CREATE INDEX IF NOT EXISTS idx_activity_events_occurred_at ON activity_events(occurred_at)"
+    run "CREATE INDEX IF NOT EXISTS idx_activity_events_session ON activity_events(session_id)"
+  end
+
+  down do
+    drop_table?(:activity_events)
+  end
+end

data/db/migrations/016_add_moment_feedback.rb

@@ -0,0 +1,22 @@
+# frozen_string_literal: true
+
+# Migration v16: Per-moment feedback (improvements.md #43).
+# Tracks a single thumbs-up/down verdict (+ optional note) per activity_event
+# so the dashboard can surface a trust-calibration signal. Unique on event_id
+# so a given moment has at most one current verdict; repeat clicks upsert.
+Sequel.migration do
+  up do
+    create_table?(:moment_feedback) do
+      primary_key :id
+      Integer :event_id, null: false
+      String :verdict, null: false  # "up" | "down"
+      String :note, text: true      # optional freeform note
+      String :recorded_at, null: false
+      index :event_id, unique: true
+    end
+  end
+
+  down do
+    drop_table?(:moment_feedback)
+  end
+end

data/db/migrations/017_add_last_recalled_at.rb

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+# Migration v17: Access-based staleness scoring (improvements.md #35).
+# Records the last time a fact was surfaced via memory.recall or context
+# injection, derived periodically from activity_events. Sweep-derived rather
+# than per-call so we avoid WAL write contention on the recall hot path.
+Sequel.migration do
+  up do
+    add_column :facts, :last_recalled_at, String
+  end
+
+  down do
+    drop_column :facts, :last_recalled_at
+  end
+end