agent-knowledge 1.5.2 → 1.5.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -2,7 +2,7 @@
2
2
  "id": "agent-knowledge",
3
3
  "name": "Knowledge",
4
4
  "icon": "psychology",
5
- "version": "1.5.1",
5
+ "version": "1.5.3",
6
6
  "description": "Knowledge base — entries, sessions, search, graph relationships",
7
7
  "ui": "./dist/ui/app.js",
8
8
  "css": "./dist/ui/styles.css",
package/docs/SETUP.md CHANGED
@@ -61,7 +61,17 @@ agent-knowledge works with any MCP client (stdio) or HTTP client (REST API). Pic
61
61
 
62
62
  ### Claude Code
63
63
 
64
- #### Register the MCP server
64
+ #### Quick setup (recommended)
65
+
66
+ From the agent-knowledge clone:
67
+
68
+ ```bash
69
+ node scripts/setup.js
70
+ ```
71
+
72
+ This detects Claude Code, registers the MCP server in `~/.claude.json`, wires all 4 hooks into `~/.claude/settings.json`, and grants `mcp__agent-knowledge__*` permission in one shot. Restart Claude Code afterwards to pick up the new config.
73
+
74
+ #### Register the MCP server (manual)
65
75
 
66
76
  ```bash
67
77
  claude mcp add agent-knowledge -s user \
@@ -170,15 +180,18 @@ curl -X PUT http://localhost:3423/api/knowledge/notes/my-note \
170
180
 
171
181
  ## Hooks
172
182
 
173
- Hooks announce the dashboard URL on session start. Support varies by client.
183
+ agent-knowledge ships **4 hook scripts** that wire into Claude Code's lifecycle events. `scripts/setup.js` installs them automatically; the block below shows the manual equivalent. Support varies by client.
174
184
 
175
- ### Claude Code Hooks
176
-
177
- #### SessionStart + SubagentStart (`scripts/hooks/session-start.js`)
185
+ | Hook | Event | Purpose |
186
+ | ------------------------ | ------------ | ------------------------------------------------------------- |
187
+ | `session-start.js` | SessionStart | Announces the knowledge dashboard URL |
188
+ | `precompact-flush.mjs` | PreCompact | Rich session summary via the compiled agent-knowledge library |
189
+ | `precompact-distill.mjs` | PreCompact | Lightweight text snapshot of recent user prompts |
190
+ | `sessionend-distill.mjs` | SessionEnd | Final summary (turn counts, tool uses, first 20 prompts) |
178
191
 
179
- Announces the knowledge dashboard URL on session start. Also fires for subagents via `SubagentStart`, ensuring spawned agents know about the knowledge base.
192
+ See [`docs/hooks.md`](hooks.md) for the full hook reference including environment variables and test coverage.
180
193
 
181
- Add to `~/.claude/settings.json`:
194
+ ### Claude Code Hooks
182
195
 
183
196
  ```json
184
197
  {
@@ -194,13 +207,29 @@ Add to `~/.claude/settings.json`:
194
207
  ]
195
208
  }
196
209
  ],
197
- "SubagentStart": [
210
+ "PreCompact": [
198
211
  {
199
212
  "hooks": [
200
213
  {
201
214
  "type": "command",
202
- "command": "node \"/path/to/agent-knowledge/scripts/hooks/session-start.js\"",
203
- "timeout": 5
215
+ "command": "node \"/path/to/agent-knowledge/scripts/hooks/precompact-flush.mjs\"",
216
+ "timeout": 10
217
+ },
218
+ {
219
+ "type": "command",
220
+ "command": "node \"/path/to/agent-knowledge/scripts/hooks/precompact-distill.mjs\"",
221
+ "timeout": 10
222
+ }
223
+ ]
224
+ }
225
+ ],
226
+ "SessionEnd": [
227
+ {
228
+ "hooks": [
229
+ {
230
+ "type": "command",
231
+ "command": "node \"/path/to/agent-knowledge/scripts/hooks/sessionend-distill.mjs\"",
232
+ "timeout": 10
204
233
  }
205
234
  ]
206
235
  }
package/docs/hooks.md ADDED
@@ -0,0 +1,116 @@
1
+ # Hooks (Claude Code)
2
+
3
+ agent-knowledge ships four hook scripts that integrate with Claude Code's
4
+ lifecycle events. They live under `scripts/hooks/` and are installed by
5
+ `scripts/setup.js` into `~/.claude/settings.json`.
6
+
7
+ All hooks fail open — any internal error is logged to stderr and the hook
8
+ returns an empty JSON object so the user is never blocked.
9
+
10
+ | Script | Event | Purpose |
11
+ | ------------------------ | ------------ | -------------------------------------------------------- |
12
+ | `session-start.js` | SessionStart | Announces the knowledge dashboard URL |
13
+ | `precompact-flush.mjs` | PreCompact | Rich session summary via the library |
14
+ | `precompact-distill.mjs` | PreCompact | Lightweight text snapshot of recent user prompts |
15
+ | `sessionend-distill.mjs` | SessionEnd | Final summary (turn counts, tool uses, first 20 prompts) |
16
+
17
+ ## session-start.js
18
+
19
+ Prints the dashboard URL (`http://localhost:3423` by default, override via
20
+ `AGENT_KNOWLEDGE_PORT`) and injects it as session context.
21
+
22
+ ## precompact-flush.mjs
23
+
24
+ Called right before the host compacts the transcript. Imports
25
+ `dist/sessions/summary.js` from the built agent-knowledge library, pulls a
26
+ rich session summary via `getSessionSummary(sessionId)`, and writes it to
27
+ `~/agent-knowledge/sessions/<project-slug>/precompact-<timestamp>-<id>.md`.
28
+ Requires `npm run build` to have succeeded — if `dist/` is missing, the hook
29
+ logs the reason to stderr and emits `{}`.
30
+
31
+ ### Environment variables
32
+
33
+ | Variable | Default | Description |
34
+ | ---------------------- | ------------------- | -------------------------------- |
35
+ | `KNOWLEDGE_MEMORY_DIR` | `~/agent-knowledge` | Where rich summaries are written |
36
+
37
+ ## precompact-distill.mjs
38
+
39
+ A simpler heuristic companion to `precompact-flush.mjs`. Reads the last
40
+ ~200 KB of the transcript JSONL, extracts the last 10 user prompts, and
41
+ writes them to
42
+ `~/claude-memory/projects/precompact-<slug>-<session>.md`. This one does
43
+ not require the library to be built, so it still works when `dist/` is
44
+ missing. Running both is fine — they target different files.
45
+
46
+ ### Environment variables
47
+
48
+ | Variable | Default | Description |
49
+ | ---------------------- | ----------------- | ------------------------------------------------- |
50
+ | `KNOWLEDGE_MEMORY_DIR` | `~/claude-memory` | Where the snapshot is written (`<dir>/projects/`) |
51
+
52
+ ## sessionend-distill.mjs
53
+
54
+ On `SessionEnd`, walks the whole transcript JSONL, counts user / assistant
55
+ turns and `tool_use` blocks, collects the first 20 user prompts, and writes
56
+ a markdown summary to
57
+ `~/claude-memory/projects/session-<slug>-<session>.md`. Gives
58
+ agent-knowledge a breadcrumb for later session search/recall.
59
+
60
+ ## Manual configuration
61
+
62
+ `scripts/setup.js` writes the hooks into `~/.claude/settings.json`
63
+ automatically. If you need to configure them by hand, add entries like:
64
+
65
+ ```json
66
+ {
67
+ "hooks": {
68
+ "SessionStart": [
69
+ {
70
+ "hooks": [
71
+ {
72
+ "type": "command",
73
+ "command": "node \"/abs/path/to/agent-knowledge/scripts/hooks/session-start.js\"",
74
+ "timeout": 5
75
+ }
76
+ ]
77
+ }
78
+ ],
79
+ "PreCompact": [
80
+ {
81
+ "hooks": [
82
+ {
83
+ "type": "command",
84
+ "command": "node \"/abs/path/to/agent-knowledge/scripts/hooks/precompact-flush.mjs\"",
85
+ "timeout": 10
86
+ },
87
+ {
88
+ "type": "command",
89
+ "command": "node \"/abs/path/to/agent-knowledge/scripts/hooks/precompact-distill.mjs\"",
90
+ "timeout": 10
91
+ }
92
+ ]
93
+ }
94
+ ],
95
+ "SessionEnd": [
96
+ {
97
+ "hooks": [
98
+ {
99
+ "type": "command",
100
+ "command": "node \"/abs/path/to/agent-knowledge/scripts/hooks/sessionend-distill.mjs\"",
101
+ "timeout": 10
102
+ }
103
+ ]
104
+ }
105
+ ]
106
+ }
107
+ }
108
+ ```
109
+
110
+ Replace `/abs/path/to/agent-knowledge` with your clone path.
111
+
112
+ ## Testing the hooks
113
+
114
+ `tests/hooks/hooks.test.ts` covers all four scripts with shape-correct
115
+ fail-open assertions. Run `npm test -- tests/hooks/` to execute them in
116
+ isolation.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agent-knowledge",
3
- "version": "1.5.2",
3
+ "version": "1.5.3",
4
4
  "description": "Cross-session memory and recall for AI agents — git-synced knowledge base, knowledge graph, confidence scoring, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -0,0 +1,105 @@
1
+ #!/usr/bin/env node
2
+
3
+ // =============================================================================
4
+ // agent-knowledge PreCompact distill hook
5
+ //
6
+ // Dumps the tail of the current session transcript into the knowledge base
7
+ // right before the host compacts the conversation, so cross-machine memory
8
+ // survives the summarization. This is a lightweight heuristic snapshot —
9
+ // the companion `precompact-flush.mjs` hook does a richer summary via the
10
+ // compiled agent-knowledge library when available. Running both is fine;
11
+ // they write to distinct files.
12
+ //
13
+ // Fail-open: any error logs to stderr and emits `{}` so it never blocks.
14
+ // =============================================================================
15
+
16
+ import { readFileSync, writeFileSync, existsSync, mkdirSync } from 'fs';
17
+ import { join } from 'path';
18
+ import { homedir } from 'os';
19
+
20
+ process.on('uncaughtException', (err) => {
21
+ process.stderr.write(`[precompact-distill] fatal: ${err.message}\n`);
22
+ console.log(JSON.stringify({}));
23
+ process.exit(0);
24
+ });
25
+
26
+ const MEMORY_DIR = process.env.KNOWLEDGE_MEMORY_DIR || join(homedir(), 'claude-memory');
27
+
28
+ async function main() {
29
+ let input = '';
30
+ for await (const chunk of process.stdin) input += chunk;
31
+
32
+ let hookData = {};
33
+ try {
34
+ hookData = JSON.parse(input);
35
+ } catch {
36
+ // ignore
37
+ }
38
+
39
+ const transcriptPath = hookData?.transcript_path;
40
+ const sessionId = hookData?.session_id || 'unknown';
41
+ const cwd = hookData?.workspace?.current_dir || process.cwd();
42
+
43
+ if (!transcriptPath || !existsSync(transcriptPath)) {
44
+ console.log(JSON.stringify({}));
45
+ return;
46
+ }
47
+
48
+ let recent = '';
49
+ try {
50
+ const buf = readFileSync(transcriptPath);
51
+ recent = buf.slice(Math.max(0, buf.length - 200_000)).toString('utf8');
52
+ } catch {
53
+ // ignore
54
+ }
55
+
56
+ const lines = recent.split(/\r?\n/).filter(Boolean);
57
+ const userMsgs = [];
58
+ for (const line of lines) {
59
+ try {
60
+ const obj = JSON.parse(line);
61
+ if (obj?.type === 'user' && typeof obj.message?.content === 'string') {
62
+ userMsgs.push(obj.message.content.slice(0, 500));
63
+ }
64
+ } catch {
65
+ // ignore non-JSON lines
66
+ }
67
+ }
68
+ const summary = userMsgs.slice(-10).join('\n---\n');
69
+
70
+ const memDir = join(MEMORY_DIR, 'projects');
71
+ try {
72
+ mkdirSync(memDir, { recursive: true });
73
+ } catch {
74
+ // ignore
75
+ }
76
+
77
+ const slug = cwd.replace(/[^a-zA-Z0-9]+/g, '-').slice(0, 64);
78
+ const file = join(memDir, `precompact-${slug}-${sessionId.slice(0, 8)}.md`);
79
+ const body = `---
80
+ type: precompact-snapshot
81
+ session: ${sessionId}
82
+ cwd: ${cwd}
83
+ created: ${new Date().toISOString()}
84
+ ---
85
+
86
+ # Pre-compact snapshot
87
+
88
+ Last ${userMsgs.length} user prompts (most recent ${Math.min(10, userMsgs.length)}):
89
+
90
+ ${summary}
91
+ `;
92
+
93
+ try {
94
+ writeFileSync(file, body, 'utf8');
95
+ } catch {
96
+ // ignore — don't block on write failure
97
+ }
98
+
99
+ console.log(JSON.stringify({}));
100
+ }
101
+
102
+ main().catch((err) => {
103
+ process.stderr.write(`[precompact-distill] ${err.message}\n`);
104
+ console.log(JSON.stringify({}));
105
+ });
@@ -0,0 +1,122 @@
1
+ #!/usr/bin/env node
2
+
3
+ // =============================================================================
4
+ // agent-knowledge SessionEnd distill hook
5
+ //
6
+ // Dumps a final session summary (turn counts, tool uses, first 20 user
7
+ // prompts) into the knowledge base when the host ends the conversation.
8
+ // Lightweight heuristic snapshot — the richer distillation happens via
9
+ // the library on next agent-knowledge startup.
10
+ //
11
+ // Fail-open.
12
+ // =============================================================================
13
+
14
+ import { readFileSync, writeFileSync, existsSync, mkdirSync } from 'fs';
15
+ import { join } from 'path';
16
+ import { homedir } from 'os';
17
+
18
+ process.on('uncaughtException', (err) => {
19
+ process.stderr.write(`[sessionend-distill] fatal: ${err.message}\n`);
20
+ console.log(JSON.stringify({}));
21
+ process.exit(0);
22
+ });
23
+
24
+ const MEMORY_DIR = process.env.KNOWLEDGE_MEMORY_DIR || join(homedir(), 'claude-memory');
25
+
26
+ async function main() {
27
+ let input = '';
28
+ for await (const chunk of process.stdin) input += chunk;
29
+
30
+ let hookData = {};
31
+ try {
32
+ hookData = JSON.parse(input);
33
+ } catch {
34
+ // ignore
35
+ }
36
+
37
+ const transcriptPath = hookData?.transcript_path;
38
+ const sessionId = hookData?.session_id || 'unknown';
39
+ const cwd = hookData?.workspace?.current_dir || process.cwd();
40
+
41
+ if (!transcriptPath || !existsSync(transcriptPath)) {
42
+ console.log(JSON.stringify({}));
43
+ return;
44
+ }
45
+
46
+ let raw = '';
47
+ try {
48
+ raw = readFileSync(transcriptPath, 'utf8');
49
+ } catch {
50
+ // ignore
51
+ }
52
+
53
+ const lines = raw.split(/\r?\n/).filter(Boolean);
54
+ let userTurns = 0;
55
+ let assistantTurns = 0;
56
+ let toolUses = 0;
57
+ const userMsgs = [];
58
+ for (const line of lines) {
59
+ try {
60
+ const obj = JSON.parse(line);
61
+ if (obj?.type === 'user') {
62
+ userTurns++;
63
+ if (typeof obj.message?.content === 'string') {
64
+ userMsgs.push(obj.message.content.slice(0, 300));
65
+ }
66
+ } else if (obj?.type === 'assistant') {
67
+ assistantTurns++;
68
+ const content = obj.message?.content;
69
+ if (Array.isArray(content)) {
70
+ toolUses += content.filter((c) => c.type === 'tool_use').length;
71
+ }
72
+ }
73
+ } catch {
74
+ // ignore non-JSON lines
75
+ }
76
+ }
77
+
78
+ const memDir = join(MEMORY_DIR, 'projects');
79
+ try {
80
+ mkdirSync(memDir, { recursive: true });
81
+ } catch {
82
+ // ignore
83
+ }
84
+
85
+ const slug = cwd.replace(/[^a-zA-Z0-9]+/g, '-').slice(0, 64);
86
+ const file = join(memDir, `session-${slug}-${sessionId.slice(0, 8)}.md`);
87
+ const body = `---
88
+ type: session-end
89
+ session: ${sessionId}
90
+ cwd: ${cwd}
91
+ ended: ${new Date().toISOString()}
92
+ turns: ${userTurns}u/${assistantTurns}a
93
+ tool_uses: ${toolUses}
94
+ ---
95
+
96
+ # Session ${sessionId.slice(0, 8)}
97
+
98
+ **cwd**: ${cwd}
99
+ **Turns**: ${userTurns} user / ${assistantTurns} assistant
100
+ **Tool uses**: ${toolUses}
101
+
102
+ ## User prompts (first 20)
103
+
104
+ ${userMsgs
105
+ .slice(0, 20)
106
+ .map((m, i) => `${i + 1}. ${m}`)
107
+ .join('\n')}
108
+ `;
109
+
110
+ try {
111
+ writeFileSync(file, body, 'utf8');
112
+ } catch {
113
+ // ignore
114
+ }
115
+
116
+ console.log(JSON.stringify({}));
117
+ }
118
+
119
+ main().catch((err) => {
120
+ process.stderr.write(`[sessionend-distill] ${err.message}\n`);
121
+ console.log(JSON.stringify({}));
122
+ });
@@ -0,0 +1,175 @@
1
+ #!/usr/bin/env node
2
+
3
+ // =============================================================================
4
+ // agent-knowledge setup script
5
+ //
6
+ // Configures an MCP-compatible AI agent to use agent-knowledge.
7
+ // Currently supports: Claude Code (auto-detected via ~/.claude.json)
8
+ //
9
+ // What it does:
10
+ // - Builds the project if dist/ is missing
11
+ // - Registers the MCP server in the agent's config
12
+ // - Adds lifecycle hooks for Claude Code (SessionStart banner, PreCompact
13
+ // flush + distill, SessionEnd distill)
14
+ // - Adds permission for mcp__agent-knowledge__* tools
15
+ //
16
+ // Usage: node scripts/setup.js [--agent claude|generic]
17
+ // =============================================================================
18
+
19
+ import { readFileSync, writeFileSync, existsSync } from 'fs';
20
+ import { join, resolve, dirname } from 'path';
21
+ import { homedir } from 'os';
22
+ import { execSync } from 'child_process';
23
+ import { fileURLToPath } from 'url';
24
+
25
+ const __dirname = dirname(fileURLToPath(import.meta.url));
26
+ const PROJECT_DIR = resolve(join(__dirname, '..'));
27
+ const HOME = homedir();
28
+ const CLAUDE_JSON = join(HOME, '.claude.json');
29
+ const SETTINGS_JSON = join(HOME, '.claude', 'settings.json');
30
+
31
+ const AGENT_FLAG = process.argv.find((_a, i, arr) => arr[i - 1] === '--agent') ?? 'auto';
32
+ const IS_CLAUDE = AGENT_FLAG === 'claude' || (AGENT_FLAG === 'auto' && existsSync(CLAUDE_JSON));
33
+
34
+ console.log('agent-knowledge setup\n');
35
+ console.log(`Agent type: ${IS_CLAUDE ? 'Claude Code' : 'Generic (manual MCP config)'}`);
36
+
37
+ // ---------------------------------------------------------------------------
38
+ // Build if needed
39
+ // ---------------------------------------------------------------------------
40
+
41
+ if (!existsSync(join(PROJECT_DIR, 'dist', 'index.js'))) {
42
+ console.log('Building agent-knowledge...');
43
+ execSync('npm run build', { cwd: PROJECT_DIR, stdio: 'inherit' });
44
+ console.log('');
45
+ }
46
+
47
+ // ---------------------------------------------------------------------------
48
+ // Register MCP server
49
+ // ---------------------------------------------------------------------------
50
+
51
+ const distPath = join(PROJECT_DIR, 'dist', 'index.js');
52
+
53
+ console.log('Registering MCP server...');
54
+ if (IS_CLAUDE && existsSync(CLAUDE_JSON)) {
55
+ const config = JSON.parse(readFileSync(CLAUDE_JSON, 'utf-8'));
56
+ if (!config.mcpServers) config.mcpServers = {};
57
+
58
+ config.mcpServers['agent-knowledge'] = {
59
+ type: 'stdio',
60
+ command: 'node',
61
+ args: [distPath],
62
+ env: {},
63
+ };
64
+
65
+ writeFileSync(CLAUDE_JSON, JSON.stringify(config, null, 2));
66
+ console.log(` Added agent-knowledge MCP server → ${distPath}`);
67
+ } else {
68
+ console.log(' Add this to your MCP client config:');
69
+ console.log(' {');
70
+ console.log(' "mcpServers": {');
71
+ console.log(' "agent-knowledge": {');
72
+ console.log(' "command": "node",');
73
+ console.log(` "args": ["${distPath.replace(/\\/g, '/')}"]`);
74
+ console.log(' }');
75
+ console.log(' }');
76
+ console.log(' }');
77
+ }
78
+
79
+ // ---------------------------------------------------------------------------
80
+
81
+ if (!IS_CLAUDE) {
82
+ console.log(`
83
+ Setup complete!
84
+
85
+ Start the dashboard: node dist/server.js
86
+ MCP server (stdio): node dist/index.js
87
+ Dashboard URL: http://localhost:3423
88
+ `);
89
+ process.exit(0);
90
+ }
91
+
92
+ console.log('Configuring Claude Code hooks...');
93
+ if (!existsSync(SETTINGS_JSON)) {
94
+ console.log(' Warning: settings.json not found. Configure hooks manually.');
95
+ process.exit(0);
96
+ }
97
+
98
+ const settings = JSON.parse(readFileSync(SETTINGS_JSON, 'utf-8'));
99
+
100
+ if (!settings.permissions) settings.permissions = {};
101
+ if (!settings.permissions.allow) settings.permissions.allow = [];
102
+ if (!settings.permissions.allow.includes('mcp__agent-knowledge__*')) {
103
+ settings.permissions.allow.push('mcp__agent-knowledge__*');
104
+ console.log(' Added mcp__agent-knowledge__* permission');
105
+ }
106
+
107
+ if (!settings.hooks) settings.hooks = {};
108
+
109
+ const hookDir = join(PROJECT_DIR, 'scripts', 'hooks');
110
+
111
+ function addUnmatchedHook(eventName, marker, command, timeout = 10) {
112
+ if (!settings.hooks[eventName]) settings.hooks[eventName] = [];
113
+ const groups = settings.hooks[eventName];
114
+ const existing = groups.find(
115
+ (g) => g.hooks && g.hooks.some((h) => h.command && h.command.includes(marker)),
116
+ );
117
+ if (existing) {
118
+ console.log(` ${eventName} (${marker}): already configured`);
119
+ return;
120
+ }
121
+ if (groups.length > 0 && groups[0].hooks && !groups[0].matcher) {
122
+ groups[0].hooks.push({ type: 'command', command, timeout });
123
+ } else {
124
+ groups.push({ hooks: [{ type: 'command', command, timeout }] });
125
+ }
126
+ console.log(` ${eventName}: added ${marker} hook`);
127
+ }
128
+
129
+ // SessionStart: dashboard banner
130
+ addUnmatchedHook(
131
+ 'SessionStart',
132
+ 'session-start.js',
133
+ `node "${join(hookDir, 'session-start.js')}"`,
134
+ 5,
135
+ );
136
+
137
+ // PreCompact: rich summary (library) + simple text distill (heuristic)
138
+ addUnmatchedHook(
139
+ 'PreCompact',
140
+ 'precompact-flush.mjs',
141
+ `node "${join(hookDir, 'precompact-flush.mjs')}"`,
142
+ 10,
143
+ );
144
+ addUnmatchedHook(
145
+ 'PreCompact',
146
+ 'precompact-distill.mjs',
147
+ `node "${join(hookDir, 'precompact-distill.mjs')}"`,
148
+ 10,
149
+ );
150
+
151
+ // SessionEnd: simple text distill for cross-machine memory
152
+ addUnmatchedHook(
153
+ 'SessionEnd',
154
+ 'sessionend-distill.mjs',
155
+ `node "${join(hookDir, 'sessionend-distill.mjs')}"`,
156
+ 10,
157
+ );
158
+
159
+ writeFileSync(SETTINGS_JSON, JSON.stringify(settings, null, 2));
160
+ console.log(' Saved settings.json');
161
+
162
+ console.log(`
163
+ Setup complete!
164
+
165
+ Restart Claude Code to load the new MCP server. Every session will now:
166
+ - Show the knowledge dashboard URL on start (SessionStart hook)
167
+ - Flush a rich session summary before compaction (precompact-flush)
168
+ - Snapshot recent user prompts before compaction (precompact-distill)
169
+ - Dump a final session summary on exit (sessionend-distill)
170
+
171
+ Dashboard: http://localhost:3423 (auto-starts on first MCP connection)
172
+ Knowledge base: ~/claude-memory/ (configurable via KNOWLEDGE_MEMORY_DIR)
173
+
174
+ See docs/hooks.md for details and docs/SETUP.md for manual configuration.
175
+ `);