Compare commits

...

12 Commits

Author SHA1 Message Date
Alex Newman 327dd44992 chore: bump version to 10.1.0
Publish to npm / publish (push) Has been cancelled
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-16 00:17:34 -05:00
Alex Newman 0e11d4812a Merge pull request #1125 from thedotmack/feat/session-start-system-message
feat: SessionStart systemMessage + cleaner defaults
2026-02-16 00:15:52 -05:00
Alex Newman 676a3d175e fix: make context and colored timeline fetches truly parallel
Address PR #1125 review feedback - both fetches now start simultaneously
via Promise.all instead of sequential-then-parallel.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-16 00:11:25 -05:00
Alex Newman 34358ab33d feat: add systemMessage support for SessionStart hook and tune defaults
Add systemMessage field to HookResult so SessionStart can display a
colored timeline directly to the user in the CLI. The handler now
parallel-fetches both markdown (for Claude context) and ANSI-colored
(for user display) timelines, appending a viewer URL link.

Also update default settings to hide verbose token columns (read/work
tokens, savings amount) and disable full observation expansion, keeping
the cleaner index-only view by default.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-16 00:05:13 -05:00
Alex Newman 5ccaf40ad0 docs: update CHANGELOG.md for v10.0.8
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 23:33:51 -05:00
Alex Newman 51abe5d1ff chore: bump version to 10.0.8
Publish to npm / publish (push) Has been cancelled
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 23:33:20 -05:00
Alex Newman 2dea824cc0 Merge pull request #1122 from thedotmack/claude/friendly-pascal
fix: resolve orphaned subprocesses and Chroma HTTP regressions
2026-02-15 23:31:10 -05:00
Alex Newman 055888e181 fix: address PR review feedback for subprocess cleanup and binary resolution
Wrap SDK query loop in try/finally so subprocess cleanup runs on error paths.
Swap Chroma binary check order to try project-level .bin first (common case).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 23:24:00 -05:00
Alex Newman 67ba17cc8a fix: use WASM backend for Chroma embeddings to fix cross-platform issues
Chroma requires client-side embeddings — the server is storage only.
The previous commit incorrectly removed @chroma-core/default-embed.

Uses DefaultEmbeddingFunction({ wasm: true }) which forces the WASM
backend instead of native ONNX binaries. Same model (all-MiniLM-L6-v2),
same embeddings, but works on all platforms without segfaults or
ENOENT errors (#1104, #1105, #1110).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 23:14:21 -05:00
Alex Newman e1ef14dbcc fix: resolve orphaned subprocesses and Chroma HTTP regressions
- Add subprocess cleanup after SDK query loop completes, using existing
  ProcessRegistry infrastructure (getProcessBySession + ensureProcessExit)
- Replace npx-based Chroma binary spawning with absolute path resolution
  via require.resolve, falling back to npx with explicit cwd (#1120)
- Remove @chroma-core/default-embed client-side dependency; let Chroma
  HTTP server handle embeddings server-side (#1104, #1105, #1110)

Closes #1010, #1089, #1090, #1068, #1120, #1104, #1105, #1110

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 22:04:52 -05:00
Alex Newman 685d54f2cb ci: add npm publish workflow on tag push
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-14 17:06:24 -05:00
Alex Newman 490f36099f docs: update CHANGELOG.md for v10.0.7
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-14 16:53:19 -05:00
16 changed files with 387 additions and 368 deletions
+1 -1
View File
@@ -10,7 +10,7 @@
"plugins": [
{
"name": "claude-mem",
"version": "10.0.7",
"version": "10.1.0",
"source": "./plugin",
"description": "Persistent memory system for Claude Code - context compression across sessions"
}
+21
View File
@@ -0,0 +1,21 @@
name: Publish to npm
on:
push:
tags:
- 'v*'
jobs:
publish:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: '20'
registry-url: 'https://registry.npmjs.org'
- run: npm install --ignore-scripts
- run: npm run build
- run: npm publish
env:
NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
+39 -104
View File
@@ -2,6 +2,45 @@
All notable changes to claude-mem.
## [v10.0.8] - 2026-02-16
## Bug Fixes
### Orphaned Subprocess Cleanup
- Add explicit subprocess cleanup after SDK query loop using existing `ProcessRegistry` infrastructure (`getProcessBySession` + `ensureProcessExit`), preventing orphaned Claude subprocesses from accumulating
- Closes #1010, #1089, #1090, #1068
### Chroma Binary Resolution
- Replace `npx chroma run` with absolute binary path resolution via `require.resolve`, falling back to `npx` with explicit `cwd` when the binary isn't found directly
- Closes #1120
### Cross-Platform Embedding Fix
- Remove `@chroma-core/default-embed` which pulled in `onnxruntime` + `sharp` native binaries that fail on many platforms
- Use WASM backend for Chroma embeddings, eliminating native binary compilation issues
- Closes #1104, #1105, #1110
## [v10.0.7] - 2026-02-14
## Chroma HTTP Server Architecture
- **Persistent HTTP server**: Switched from in-process Chroma to a persistent HTTP server managed by the new `ChromaServerManager` for better reliability and performance
- **Local embeddings**: Added `DefaultEmbeddingFunction` for local vector embeddings — no external API required
- **Pinned chromadb v3.2.2**: Fixed compatibility with v2 API heartbeat endpoint
- **Server lifecycle improvements**: Addressed PR review feedback for proper start/stop/health check handling
## Bug Fixes
- Fixed SDK spawn failures and sharp native binary crashes
- Added `plugin.json` to root `.claude-plugin` directory for proper plugin structure
- Removed duplicate else block from merge artifact
## Infrastructure
- Added multi-tenancy support for claude-mem Pro
- Updated OpenClaw install URLs to `install.cmem.ai`
- Added Vercel deploy workflow for install scripts
- Added `.claude/plans` and `.claude/worktrees` to `.gitignore`
## [v10.0.6] - 2026-02-13
## Bug Fixes
@@ -1463,107 +1502,3 @@ Huge thanks to **Alexander Knigge** ([@AlexanderKnigge](https://x.com/AlexanderK
**Full Changelog**: https://github.com/thedotmack/claude-mem/compare/v8.1.0...v8.2.0
## [v8.1.0] - 2025-12-25
## The 3-Month Battle Against Complexity
**TL;DR:** For three months, Claude's instinct to add code instead of delete it caused the same bugs to recur. What should have been 5 lines of code became ~1000 lines, 11 useless methods, and 7+ failed "fixes." The timestamp corruption that finally broke things was just a symptom. The real achievement: **984 lines of code deleted.**
---
## What Actually Happened
Every Claude Code hook receives a session ID. That's all you need.
But Claude built an entire redundant session management system on top:
- An `sdk_sessions` table with status tracking, port assignment, and prompt counting
- 11 methods in `SessionStore` to manage this artificial complexity
- Auto-creation logic scattered across 3 locations
- A cleanup hook that "completed" sessions at the end
**Why?** Because it seemed "robust." Because "what if the session doesn't exist?"
But the edge cases didn't exist. Hooks ALWAYS provide session IDs. The "defensive" code was solving imaginary problems while creating real ones.
---
## The Pattern of Failure
Every time a bug appeared, Claude's instinct was to **ADD** more code:
| Bug | What Claude Added | What Should Have Happened |
|-----|------------------|--------------------------|
| Race conditions | Auto-create fallbacks | Delete the auto-create logic |
| Duplicate observations | Validation layers | Delete the code path allowing duplicates |
| UNIQUE constraint violations | Try-catch with fallbacks | Use `INSERT OR IGNORE` (5 characters) |
| Session not found | Silent auto-creation | **FAIL LOUDLY** (it's a hook bug) |
---
## The 7+ Failed Attempts
- **Nov 4**: "Always store session data regardless of pre-existence." Complexity planted.
- **Nov 11**: `INSERT OR IGNORE` recognized. But complexity documented, not removed.
- **Nov 21**: Duplicate observations bug. Fixed. Then broken again by endless mode.
- **Dec 5**: "6 hours of work delivered zero value." User requests self-audit.
- **Dec 20**: "Phase 2: Eliminated Race Conditions" — felt like progress. Complexity remained.
- **Dec 24**: Finally, forced deletion.
The user stated "hooks provide session IDs, no extra management needed" **seven times** across months. Claude didn't listen.
---
## The Fix
### Deleted (984 lines):
- 11 `SessionStore` methods: `incrementPromptCounter`, `getPromptCounter`, `setWorkerPort`, `getWorkerPort`, `markSessionCompleted`, `markSessionFailed`, `reactivateSession`, `findActiveSDKSession`, `findAnySDKSession`, `updateSDKSessionId`
- Auto-create logic from `storeObservation` and `storeSummary`
- The entire cleanup hook (was aborting SDK agent and causing data loss)
- 117 lines from `worker-utils.ts`
### What remains (~10 lines):
```javascript
createSDKSession(sessionId) {
db.run('INSERT OR IGNORE INTO sdk_sessions (...) VALUES (...)');
return db.query('SELECT id FROM sdk_sessions WHERE ...').get(sessionId);
}
```
**That's it.**
---
## Behavior Change
- **Before:** Missing session? Auto-create silently. Bug hidden.
- **After:** Missing session? Storage fails. Bug visible immediately.
---
## New Tools
Since we're now explicit about recovery instead of silently papering over problems:
- `GET /api/pending-queue` - See what's stuck
- `POST /api/pending-queue/process` - Manually trigger recovery
- `npm run queue:check` / `npm run queue:process` - CLI equivalents
---
## Dependencies
- Upgraded `@anthropic-ai/claude-agent-sdk` from `^0.1.67` to `^0.1.76`
---
**PR #437:** https://github.com/thedotmack/claude-mem/pull/437
*The evidence: Observations #3646, #6738, #7598, #12860, #12866, #13046, #15259, #20995, #21055, #30524, #31080, #32114, #32116, #32125, #32126, #32127, #32146, #32324—the complete record of a 3-month battle.*
## [v8.0.6] - 2025-12-24
## Bug Fixes
- Add error handlers to Chroma sync operations to prevent worker crashes on timeout (#428)
This patch release improves stability by adding proper error handling to Chroma vector database sync operations, preventing worker crashes when sync operations timeout.
+2 -2
View File
@@ -1,6 +1,6 @@
{
"name": "claude-mem",
"version": "10.0.7",
"version": "10.1.0",
"description": "Memory compression system for Claude Code - persist context across sessions",
"keywords": [
"claude",
@@ -97,8 +97,8 @@
},
"dependencies": {
"@anthropic-ai/claude-agent-sdk": "^0.1.76",
"@chroma-core/default-embed": "^0.1.9",
"@modelcontextprotocol/sdk": "^1.25.1",
"@chroma-core/default-embed": "^0.1.9",
"ansi-to-html": "^0.7.2",
"chromadb": "^3.2.2",
"dompurify": "^3.3.1",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "claude-mem",
"version": "10.0.7",
"version": "10.1.0",
"description": "Persistent memory system for Claude Code - seamlessly preserve context across sessions",
"author": {
"name": "Alex Newman"
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "claude-mem-plugin",
"version": "10.0.7",
"version": "10.1.0",
"private": true,
"description": "Runtime dependencies for claude-mem bundled hooks",
"type": "module",
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
+5 -1
View File
@@ -17,7 +17,11 @@ export const claudeCodeAdapter: PlatformAdapter = {
},
formatOutput(result) {
if (result.hookSpecificOutput) {
return { hookSpecificOutput: result.hookSpecificOutput };
const output: Record<string, unknown> = { hookSpecificOutput: result.hookSpecificOutput };
if (result.systemMessage) {
output.systemMessage = result.systemMessage;
}
return output;
}
return { continue: result.continue ?? true, suppressOutput: result.suppressOutput ?? true };
}
+18 -4
View File
@@ -37,7 +37,12 @@ export const contextHandler: EventHandler = {
// Note: Removed AbortSignal.timeout due to Windows Bun cleanup issue (libuv assertion)
// Worker service has its own timeouts, so client-side timeout is redundant
try {
const response = await fetch(url);
// Fetch both markdown (for Claude context) and colored (for user display) truly in parallel
const colorUrl = `${url}&colors=true`;
const [response, colorResponse] = await Promise.all([
fetch(url),
fetch(colorUrl).catch(() => null)
]);
if (!response.ok) {
// Log but don't throw — context fetch failure should not block session start
@@ -48,14 +53,23 @@ export const contextHandler: EventHandler = {
};
}
const result = await response.text();
const additionalContext = result.trim();
const [contextResult, colorResult] = await Promise.all([
response.text(),
colorResponse?.ok ? colorResponse.text() : Promise.resolve('')
]);
const additionalContext = contextResult.trim();
const coloredTimeline = colorResult.trim();
const systemMessage = coloredTimeline
? `${coloredTimeline}\n\nView Observations Live @ http://localhost:${port}`
: undefined;
return {
hookSpecificOutput: {
hookEventName: 'SessionStart',
additionalContext
}
},
systemMessage
};
} catch (error) {
// Worker unreachable — return empty context gracefully
+1
View File
@@ -16,6 +16,7 @@ export interface HookResult {
continue?: boolean;
suppressOutput?: boolean;
hookSpecificOutput?: { hookEventName: string; additionalContext: string };
systemMessage?: string;
exitCode?: number;
}
+39 -9
View File
@@ -11,7 +11,7 @@
import { spawn, ChildProcess, execSync } from 'child_process';
import path from 'path';
import os from 'os';
import fs from 'fs';
import fs, { existsSync } from 'fs';
import { logger } from '../../utils/logger.js';
export interface ChromaServerConfig {
@@ -108,14 +108,35 @@ export class ChromaServerManager {
// Cross-platform: use npx.cmd on Windows
const isWindows = process.platform === 'win32';
const command = isWindows ? 'npx.cmd' : 'npx';
const args = [
'chroma', 'run',
'--path', this.config.dataDir,
'--host', this.config.host,
'--port', String(this.config.port)
];
// Resolve chroma binary absolutely — npx fails when spawned from cache dirs (#1120)
let command: string;
let args: string[];
try {
// chromadb package installs a 'chroma' bin entry
const chromaBinDir = path.dirname(require.resolve('chromadb/package.json'));
// Check project-level .bin first (most common npm/bun installation layout)
const projectBin = path.join(chromaBinDir, '..', '.bin', isWindows ? 'chroma.cmd' : 'chroma');
// Fallback: nested node_modules .bin (rare — pnpm or workspace hoisting)
const nestedBin = path.join(chromaBinDir, 'node_modules', '.bin', isWindows ? 'chroma.cmd' : 'chroma');
if (existsSync(projectBin)) {
command = projectBin;
} else if (existsSync(nestedBin)) {
command = nestedBin;
} else {
// Last resort: npx with explicit cwd
command = isWindows ? 'npx.cmd' : 'npx';
}
} catch {
command = isWindows ? 'npx.cmd' : 'npx';
}
if (command.includes('npx')) {
args = ['chroma', 'run', '--path', this.config.dataDir, '--host', this.config.host, '--port', String(this.config.port)];
} else {
args = ['run', '--path', this.config.dataDir, '--host', this.config.host, '--port', String(this.config.port)];
}
logger.info('CHROMA_SERVER', 'Starting Chroma server', {
command,
@@ -125,11 +146,20 @@ export class ChromaServerManager {
const spawnEnv = this.getSpawnEnv();
// Resolve cwd for npx fallback — ensures node_modules is findable (#1120)
let spawnCwd: string | undefined;
try {
spawnCwd = path.dirname(require.resolve('chromadb/package.json'));
} catch {
// If chromadb isn't resolvable, omit cwd and let npx handle it
}
this.serverProcess = spawn(command, args, {
stdio: ['ignore', 'pipe', 'pipe'],
detached: !isWindows, // Don't detach on Windows (no process groups)
windowsHide: true, // Hide console window on Windows
env: spawnEnv
env: spawnEnv,
...(spawnCwd && { cwd: spawnCwd })
});
// Log server output for debugging
+8 -5
View File
@@ -189,17 +189,20 @@ export class ChromaSync {
}
try {
// getOrCreateCollection handles both cases
// Lazy-load DefaultEmbeddingFunction to avoid eagerly pulling in
// @huggingface/transformers → sharp native binaries at bundle startup
// Use WASM backend to avoid native ONNX binary issues (#1104, #1105, #1110).
// Same model (all-MiniLM-L6-v2), same embeddings, but runs in WASM —
// no native binary loading, no segfaults, no ENOENT errors.
const { DefaultEmbeddingFunction } = await import('@chroma-core/default-embed');
const embeddingFunction = new DefaultEmbeddingFunction();
const embeddingFunction = new DefaultEmbeddingFunction({ wasm: true });
this.collection = await this.chromaClient.getOrCreateCollection({
name: this.collectionName,
embeddingFunction
});
logger.debug('CHROMA_SYNC', 'Collection ready', { collection: this.collectionName });
logger.debug('CHROMA_SYNC', 'Collection ready', {
collection: this.collectionName
});
} catch (error) {
logger.error('CHROMA_SYNC', 'Failed to get/create collection', { collection: this.collectionName }, error as Error);
throw new Error(`Collection setup failed: ${error instanceof Error ? error.message : String(error)}`);
+127 -118
View File
@@ -141,134 +141,143 @@ export class SDKAgent {
}
});
// Process SDK messages
for await (const message of queryResult) {
// Capture or update memory session ID from SDK message
// IMPORTANT: The SDK may return a DIFFERENT session_id on resume than what we sent!
// We must always sync the DB to match what the SDK actually uses.
//
// MULTI-TERMINAL COLLISION FIX (FK constraint bug):
// Use ensureMemorySessionIdRegistered() instead of updateMemorySessionId() because:
// 1. It's idempotent - safe to call multiple times
// 2. It verifies the update happened (SELECT before UPDATE)
// 3. Consistent with ResponseProcessor's usage pattern
// This ensures FK constraint compliance BEFORE any observations are stored.
if (message.session_id && message.session_id !== session.memorySessionId) {
const previousId = session.memorySessionId;
session.memorySessionId = message.session_id;
// Persist to database IMMEDIATELY for FK constraint compliance
// This must happen BEFORE any observations referencing this ID are stored
this.dbManager.getSessionStore().ensureMemorySessionIdRegistered(
session.sessionDbId,
message.session_id
);
// Verify the update by reading back from DB
const verification = this.dbManager.getSessionStore().getSessionById(session.sessionDbId);
const dbVerified = verification?.memory_session_id === message.session_id;
const logMessage = previousId
? `MEMORY_ID_CHANGED | sessionDbId=${session.sessionDbId} | from=${previousId} | to=${message.session_id} | dbVerified=${dbVerified}`
: `MEMORY_ID_CAPTURED | sessionDbId=${session.sessionDbId} | memorySessionId=${message.session_id} | dbVerified=${dbVerified}`;
logger.info('SESSION', logMessage, {
sessionId: session.sessionDbId,
memorySessionId: message.session_id,
previousId
});
if (!dbVerified) {
logger.error('SESSION', `MEMORY_ID_MISMATCH | sessionDbId=${session.sessionDbId} | expected=${message.session_id} | got=${verification?.memory_session_id}`, {
sessionId: session.sessionDbId
// Process SDK messages — cleanup in finally ensures subprocess termination
// even if the loop throws (e.g., context overflow, invalid API key)
try {
for await (const message of queryResult) {
// Capture or update memory session ID from SDK message
// IMPORTANT: The SDK may return a DIFFERENT session_id on resume than what we sent!
// We must always sync the DB to match what the SDK actually uses.
//
// MULTI-TERMINAL COLLISION FIX (FK constraint bug):
// Use ensureMemorySessionIdRegistered() instead of updateMemorySessionId() because:
// 1. It's idempotent - safe to call multiple times
// 2. It verifies the update happened (SELECT before UPDATE)
// 3. Consistent with ResponseProcessor's usage pattern
// This ensures FK constraint compliance BEFORE any observations are stored.
if (message.session_id && message.session_id !== session.memorySessionId) {
const previousId = session.memorySessionId;
session.memorySessionId = message.session_id;
// Persist to database IMMEDIATELY for FK constraint compliance
// This must happen BEFORE any observations referencing this ID are stored
this.dbManager.getSessionStore().ensureMemorySessionIdRegistered(
session.sessionDbId,
message.session_id
);
// Verify the update by reading back from DB
const verification = this.dbManager.getSessionStore().getSessionById(session.sessionDbId);
const dbVerified = verification?.memory_session_id === message.session_id;
const logMessage = previousId
? `MEMORY_ID_CHANGED | sessionDbId=${session.sessionDbId} | from=${previousId} | to=${message.session_id} | dbVerified=${dbVerified}`
: `MEMORY_ID_CAPTURED | sessionDbId=${session.sessionDbId} | memorySessionId=${message.session_id} | dbVerified=${dbVerified}`;
logger.info('SESSION', logMessage, {
sessionId: session.sessionDbId,
memorySessionId: message.session_id,
previousId
});
}
// Debug-level alignment log for detailed tracing
logger.debug('SDK', `[ALIGNMENT] ${previousId ? 'Updated' : 'Captured'} | contentSessionId=${session.contentSessionId} → memorySessionId=${message.session_id} | Future prompts will resume with this ID`);
}
// Handle assistant messages
if (message.type === 'assistant') {
const content = message.message.content;
const textContent = Array.isArray(content)
? content.filter((c: any) => c.type === 'text').map((c: any) => c.text).join('\n')
: typeof content === 'string' ? content : '';
// Check for context overflow - prevents infinite retry loops
if (textContent.includes('prompt is too long') ||
textContent.includes('context window')) {
logger.error('SDK', 'Context overflow detected - terminating session');
session.abortController.abort();
return;
if (!dbVerified) {
logger.error('SESSION', `MEMORY_ID_MISMATCH | sessionDbId=${session.sessionDbId} | expected=${message.session_id} | got=${verification?.memory_session_id}`, {
sessionId: session.sessionDbId
});
}
// Debug-level alignment log for detailed tracing
logger.debug('SDK', `[ALIGNMENT] ${previousId ? 'Updated' : 'Captured'} | contentSessionId=${session.contentSessionId} → memorySessionId=${message.session_id} | Future prompts will resume with this ID`);
}
const responseSize = textContent.length;
// Handle assistant messages
if (message.type === 'assistant') {
const content = message.message.content;
const textContent = Array.isArray(content)
? content.filter((c: any) => c.type === 'text').map((c: any) => c.text).join('\n')
: typeof content === 'string' ? content : '';
// Capture token state BEFORE updating (for delta calculation)
const tokensBeforeResponse = session.cumulativeInputTokens + session.cumulativeOutputTokens;
// Extract and track token usage
const usage = message.message.usage;
if (usage) {
session.cumulativeInputTokens += usage.input_tokens || 0;
session.cumulativeOutputTokens += usage.output_tokens || 0;
// Cache creation counts as discovery, cache read doesn't
if (usage.cache_creation_input_tokens) {
session.cumulativeInputTokens += usage.cache_creation_input_tokens;
// Check for context overflow - prevents infinite retry loops
if (textContent.includes('prompt is too long') ||
textContent.includes('context window')) {
logger.error('SDK', 'Context overflow detected - terminating session');
session.abortController.abort();
return;
}
logger.debug('SDK', 'Token usage captured', {
sessionId: session.sessionDbId,
inputTokens: usage.input_tokens,
outputTokens: usage.output_tokens,
cacheCreation: usage.cache_creation_input_tokens || 0,
cacheRead: usage.cache_read_input_tokens || 0,
cumulativeInput: session.cumulativeInputTokens,
cumulativeOutput: session.cumulativeOutputTokens
});
const responseSize = textContent.length;
// Capture token state BEFORE updating (for delta calculation)
const tokensBeforeResponse = session.cumulativeInputTokens + session.cumulativeOutputTokens;
// Extract and track token usage
const usage = message.message.usage;
if (usage) {
session.cumulativeInputTokens += usage.input_tokens || 0;
session.cumulativeOutputTokens += usage.output_tokens || 0;
// Cache creation counts as discovery, cache read doesn't
if (usage.cache_creation_input_tokens) {
session.cumulativeInputTokens += usage.cache_creation_input_tokens;
}
logger.debug('SDK', 'Token usage captured', {
sessionId: session.sessionDbId,
inputTokens: usage.input_tokens,
outputTokens: usage.output_tokens,
cacheCreation: usage.cache_creation_input_tokens || 0,
cacheRead: usage.cache_read_input_tokens || 0,
cumulativeInput: session.cumulativeInputTokens,
cumulativeOutput: session.cumulativeOutputTokens
});
}
// Calculate discovery tokens (delta for this response only)
const discoveryTokens = (session.cumulativeInputTokens + session.cumulativeOutputTokens) - tokensBeforeResponse;
// Process response (empty or not) and mark messages as processed
// Capture earliest timestamp BEFORE processing (will be cleared after)
const originalTimestamp = session.earliestPendingTimestamp;
if (responseSize > 0) {
const truncatedResponse = responseSize > 100
? textContent.substring(0, 100) + '...'
: textContent;
logger.dataOut('SDK', `Response received (${responseSize} chars)`, {
sessionId: session.sessionDbId,
promptNumber: session.lastPromptNumber
}, truncatedResponse);
}
// Detect fatal context overflow and terminate gracefully (issue #870)
if (typeof textContent === 'string' && textContent.includes('Prompt is too long')) {
throw new Error('Claude session context overflow: prompt is too long');
}
// Detect invalid API key — SDK returns this as response text, not an error.
// Throw so it surfaces in health endpoint and prevents silent failures.
if (typeof textContent === 'string' && textContent.includes('Invalid API key')) {
throw new Error('Invalid API key: check your API key configuration in ~/.claude-mem/settings.json or ~/.claude-mem/.env');
}
// Parse and process response using shared ResponseProcessor
await processAgentResponse(
textContent,
session,
this.dbManager,
this.sessionManager,
worker,
discoveryTokens,
originalTimestamp,
'SDK',
cwdTracker.lastCwd
);
}
// Calculate discovery tokens (delta for this response only)
const discoveryTokens = (session.cumulativeInputTokens + session.cumulativeOutputTokens) - tokensBeforeResponse;
// Process response (empty or not) and mark messages as processed
// Capture earliest timestamp BEFORE processing (will be cleared after)
const originalTimestamp = session.earliestPendingTimestamp;
if (responseSize > 0) {
const truncatedResponse = responseSize > 100
? textContent.substring(0, 100) + '...'
: textContent;
logger.dataOut('SDK', `Response received (${responseSize} chars)`, {
sessionId: session.sessionDbId,
promptNumber: session.lastPromptNumber
}, truncatedResponse);
// Log result messages
if (message.type === 'result' && message.subtype === 'success') {
// Usage telemetry is captured at SDK level
}
// Detect fatal context overflow and terminate gracefully (issue #870)
if (typeof textContent === 'string' && textContent.includes('Prompt is too long')) {
throw new Error('Claude session context overflow: prompt is too long');
}
// Detect invalid API key — SDK returns this as response text, not an error.
// Throw so it surfaces in health endpoint and prevents silent failures.
if (typeof textContent === 'string' && textContent.includes('Invalid API key')) {
throw new Error('Invalid API key: check your API key configuration in ~/.claude-mem/settings.json or ~/.claude-mem/.env');
}
// Parse and process response using shared ResponseProcessor
await processAgentResponse(
textContent,
session,
this.dbManager,
this.sessionManager,
worker,
discoveryTokens,
originalTimestamp,
'SDK',
cwdTracker.lastCwd
);
}
// Log result messages
if (message.type === 'result' && message.subtype === 'success') {
// Usage telemetry is captured at SDK level
} finally {
// Ensure subprocess is terminated after query completes (or on error)
const tracked = getProcessBySession(session.sessionDbId);
if (tracked && !tracked.process.killed && tracked.process.exitCode === null) {
await ensureProcessExit(tracked, 5000);
}
}
+4 -4
View File
@@ -95,15 +95,15 @@ export class SettingsDefaultsManager {
CLAUDE_CODE_PATH: '', // Empty means auto-detect via 'which claude'
CLAUDE_MEM_MODE: 'code', // Default mode profile
// Token Economics
CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS: 'true',
CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS: 'true',
CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT: 'true',
CLAUDE_MEM_CONTEXT_SHOW_READ_TOKENS: 'false',
CLAUDE_MEM_CONTEXT_SHOW_WORK_TOKENS: 'false',
CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_AMOUNT: 'false',
CLAUDE_MEM_CONTEXT_SHOW_SAVINGS_PERCENT: 'true',
// Observation Filtering
CLAUDE_MEM_CONTEXT_OBSERVATION_TYPES: DEFAULT_OBSERVATION_TYPES_STRING,
CLAUDE_MEM_CONTEXT_OBSERVATION_CONCEPTS: DEFAULT_OBSERVATION_CONCEPTS_STRING,
// Display Configuration
CLAUDE_MEM_CONTEXT_FULL_COUNT: '5',
CLAUDE_MEM_CONTEXT_FULL_COUNT: '0',
CLAUDE_MEM_CONTEXT_FULL_FIELD: 'narrative',
CLAUDE_MEM_CONTEXT_SESSION_COUNT: '10',
// Feature Toggles