Compare commits
10 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Alex Newman
|
69080dc291 | ||
|
Alex Newman
|
c76a439491 | ||
|
Alex Newman
|
70a150db74 | ||
|
Alex Newman
|
d7b4610e27 | ||
|
Alex Newman
|
88bb4e589e | ||
|
Alex Newman
|
ebefae864e | ||
|
Alex Newman
|
0cd931bb06 | ||
|
Alex Newman
|
4c792f026d | ||
|
Alex Newman
|
aa7cdb6d9f | ||
|
Alex Newman
|
5db90f2ea0 |
@@ -10,7 +10,7 @@
|
||||
"plugins": [
|
||||
{
|
||||
"name": "claude-mem",
|
||||
"version": "12.1.3",
|
||||
"version": "12.1.6",
|
||||
"source": "./plugin",
|
||||
"description": "Persistent memory system for Claude Code - context compression across sessions"
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "claude-mem",
|
||||
"version": "12.1.3",
|
||||
"version": "12.1.6",
|
||||
"description": "Memory compression system for Claude Code - persist context across sessions",
|
||||
"author": {
|
||||
"name": "Alex Newman"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "claude-mem",
|
||||
"version": "12.1.3",
|
||||
"version": "12.1.6",
|
||||
"description": "Memory compression system for Claude Code - persist context across sessions",
|
||||
"author": {
|
||||
"name": "Alex Newman",
|
||||
|
||||
+166
-109
@@ -4,10 +4,67 @@ All notable changes to this project will be documented in this file.
|
||||
|
||||
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
|
||||
|
||||
## [12.1.1] - 2026-
|
||||
✅ CHANGELOG.md generated successfully!
|
||||
226 releases processed
|
||||
dresses the most impactful bugs across summary persistence, MCP compliance, cross-platform compatibility, and data integrity.
|
||||
## [12.1.5] - 2026-04-15
|
||||
|
||||
## Forced update to ship --setting-sources fix
|
||||
|
||||
Users on v12.1.3 experience 100% observation failure due to empty-string arg filtering corrupting `--setting-sources` on Claude Code 2.1.109+. The fix landed in v12.1.4 (commit 3d92684 — `fix: filter empty string args before Bun spawn()`). This release forces the update to propagate across npm and the marketplace.
|
||||
|
||||
Also shipped earlier today: the April 2026 backlog consolidation merged 93 PRs and 147 issues into 138 clean tracking issues (95 bugs, 43 feature requests).
|
||||
|
||||
**Full Changelog**: https://github.com/thedotmack/claude-mem/compare/v12.1.4...v12.1.5
|
||||
|
||||
## [12.1.4] - 2026-04-15
|
||||
|
||||
A Claude instance inserted `$CMEM` token branding into the context injection header during a compression refactor. Reverted back to the original descriptive format: `# [project] recent context, datetime`
|
||||
|
||||
**Full Changelog**: https://github.com/thedotmack/claude-mem/compare/v12.1.3...v12.1.4
|
||||
|
||||
## [12.1.3] - 2026-04-15
|
||||
|
||||
## What's Changed
|
||||
|
||||
### Reverted
|
||||
- **Remove overengineered summary salvage logic** (#1850) — Reverts PR #1718 which fabricated synthetic summaries from observation data when the AI returned `<observation>` instead of `<summary>` tags. Missing a summary is preferable to creating a fake one with poorly-mapped fields.
|
||||
|
||||
**Full Changelog**: https://github.com/thedotmack/claude-mem/compare/v12.1.2...v12.1.3
|
||||
|
||||
## [12.1.2] - 2026-04-15
|
||||
|
||||
## Community PRs merged (15)
|
||||
|
||||
**Runtime & reliability**
|
||||
- #1698 Reap stuck generators in reapStaleSessions (@ousamabenyounes)
|
||||
- #1697 Circuit breaker on OpenClaw worker client (@ousamabenyounes)
|
||||
- #1696 Resolve Setup hook reference, warn on macOS-only binary (@ousamabenyounes)
|
||||
- #1693 Session lifecycle guards to prevent runaway API spend (@ousamabenyounes)
|
||||
- #1692 Resolve Gemini CLI 0.37.0 session capture failures (@ousamabenyounes)
|
||||
|
||||
**Cross-platform & hooks**
|
||||
- #1833 Replace hardcoded nvm/homebrew PATH with login-shell resolution (@masak1yu)
|
||||
- #1781 Filter empty-string args before Bun spawn() (@biswanath-cmd)
|
||||
- #1780 Fix npx search, default Codex context to workspace-local AGENTS (@enma998)
|
||||
|
||||
**Data integrity**
|
||||
- #1820 Use parent project name for worktree observation writes (@0xLeathery)
|
||||
- #1771 Exclude primary-key index from unique-constraint check in migration 7 (@derjochenmeyer)
|
||||
- #1770 Restrict ~/.claude-mem/.env permissions to 0600 (@derjochenmeyer)
|
||||
- #1729 Preserve targeted file reads and invalidate on mtime (@quangtran88)
|
||||
- #1776 Coerce corpus route filters (@suyua9)
|
||||
|
||||
**Docs**
|
||||
- #1777 Document CLAUDE_MEM_MODE (@AviArora02-commits)
|
||||
- #1765 Update opencode install instructions (@s-uryansh)
|
||||
|
||||
## Held for rebase
|
||||
- #1748, #1694, #1695 — developed conflicts during batch merge
|
||||
|
||||
## Test baseline
|
||||
1429 pass / 11 fail (improved from 18 fail at v12.1.1)
|
||||
|
||||
## [12.1.1] - 2026-04-15
|
||||
|
||||
14 community PRs merged + 1 post-merge bug fix. This patch addresses the most impactful bugs across summary persistence, MCP compliance, cross-platform compatibility, and data integrity.
|
||||
|
||||
### Highlights
|
||||
|
||||
@@ -2299,98 +2356,98 @@ Huge thanks to **Alexander Knigge** ([@AlexanderKnigge](https://x.com/AlexanderK
|
||||
|
||||
## [8.1.0] - 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 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.*
|
||||
|
||||
## [8.0.6] - 2025-12-24
|
||||
@@ -2617,13 +2674,13 @@ This represents a major reliability improvement for Windows users, eliminating c
|
||||
|
||||
## [7.3.5] - 2025-12-17
|
||||
|
||||
## What's Changed
|
||||
* fix(windows): solve zombie port problem with wrapper architecture by @ToxMox in https://github.com/thedotmack/claude-mem/pull/372
|
||||
* chore: bump version to 7.3.5 by @thedotmack in https://github.com/thedotmack/claude-mem/pull/375
|
||||
|
||||
## New Contributors
|
||||
* @ToxMox made their first contribution in https://github.com/thedotmack/claude-mem/pull/372
|
||||
|
||||
## What's Changed
|
||||
* fix(windows): solve zombie port problem with wrapper architecture by @ToxMox in https://github.com/thedotmack/claude-mem/pull/372
|
||||
* chore: bump version to 7.3.5 by @thedotmack in https://github.com/thedotmack/claude-mem/pull/375
|
||||
|
||||
## New Contributors
|
||||
* @ToxMox made their first contribution in https://github.com/thedotmack/claude-mem/pull/372
|
||||
|
||||
**Full Changelog**: https://github.com/thedotmack/claude-mem/compare/v7.3.4...v7.3.5
|
||||
|
||||
## [7.3.4] - 2025-12-17
|
||||
@@ -5153,12 +5210,12 @@ None (patch version)
|
||||
|
||||
## [4.3.0] - 2025-10-25
|
||||
|
||||
## What's Changed
|
||||
* feat: Enhanced context hook with session observations and cross-platform improvements by @thedotmack in https://github.com/thedotmack/claude-mem/pull/25
|
||||
|
||||
## New Contributors
|
||||
* @thedotmack made their first contribution in https://github.com/thedotmack/claude-mem/pull/25
|
||||
|
||||
## What's Changed
|
||||
* feat: Enhanced context hook with session observations and cross-platform improvements by @thedotmack in https://github.com/thedotmack/claude-mem/pull/25
|
||||
|
||||
## New Contributors
|
||||
* @thedotmack made their first contribution in https://github.com/thedotmack/claude-mem/pull/25
|
||||
|
||||
**Full Changelog**: https://github.com/thedotmack/claude-mem/compare/v4.2.11...v4.3.0
|
||||
|
||||
## [4.2.10] - 2025-10-25
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "claude-mem",
|
||||
"version": "12.1.3",
|
||||
"version": "12.1.6",
|
||||
"description": "Memory compression system for Claude Code - persist context across sessions",
|
||||
"keywords": [
|
||||
"claude",
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "claude-mem",
|
||||
"version": "12.1.3",
|
||||
"version": "12.1.6",
|
||||
"description": "Persistent memory system for Claude Code - seamlessly preserve context across sessions",
|
||||
"author": {
|
||||
"name": "Alex Newman"
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "claude-mem-plugin",
|
||||
"version": "12.1.3",
|
||||
"version": "12.1.6",
|
||||
"private": true,
|
||||
"description": "Runtime dependencies for claude-mem bundled hooks",
|
||||
"type": "module",
|
||||
|
||||
@@ -747,7 +747,7 @@ ${o.stack}`:` ${o.message}`:this.getLevel()===0&&typeof o=="object"?m=`
|
||||
ORDER BY ss.created_at_epoch DESC
|
||||
LIMIT ?
|
||||
`).all(...e,...s?[s]:[],t.sessionCount+ne)}function Bt(r){return r.replace(/\//g,"-")}function Wt(r){try{if(!(0,V.existsSync)(r))return{userMessage:"",assistantMessage:""};let e=(0,V.readFileSync)(r,"utf-8").trim();if(!e)return{userMessage:"",assistantMessage:""};let t=e.split(`
|
||||
`).filter(n=>n.trim()),s="";for(let n=t.length-1;n>=0;n--)try{let o=t[n];if(!o.includes('"type":"assistant"'))continue;let i=JSON.parse(o);if(i.type==="assistant"&&i.message?.content&&Array.isArray(i.message.content)){let a="";for(let d of i.message.content)d.type==="text"&&(a+=d.text);if(a=a.replace(xe,"").trim(),a){s=a;break}}}catch(o){_.debug("PARSER","Skipping malformed transcript line",{lineIndex:n},o);continue}return{userMessage:"",assistantMessage:s}}catch(e){return _.failure("WORKER","Failed to extract prior messages from transcript",{transcriptPath:r},e),{userMessage:"",assistantMessage:""}}}function ce(r,e,t,s){if(!e.showLastMessage||r.length===0)return{userMessage:"",assistantMessage:""};let n=r.find(d=>d.memory_session_id!==t);if(!n)return{userMessage:"",assistantMessage:""};let o=n.memory_session_id,i=Bt(s),a=ke.default.join(y,"projects",i,`${o}.jsonl`);return Wt(a)}function we(r,e){let t=e[0]?.id;return r.map((s,n)=>{let o=n===0?null:e[n+1];return{...s,displayEpoch:o?o.created_at_epoch:s.created_at_epoch,displayTime:o?o.created_at:s.created_at,shouldShowLink:s.id!==t}})}function ue(r,e){let t=[...r.map(s=>({type:"observation",data:s})),...e.map(s=>({type:"summary",data:s}))];return t.sort((s,n)=>{let o=s.type==="observation"?s.data.created_at_epoch:s.data.displayEpoch,i=n.type==="observation"?n.data.created_at_epoch:n.data.displayEpoch;return o-i}),t}function Pe(r,e){return new Set(r.slice(0,e).map(t=>t.id))}function je(){let r=new Date,e=r.toLocaleDateString("en-CA"),t=r.toLocaleTimeString("en-US",{hour:"numeric",minute:"2-digit",hour12:!0}).toLowerCase().replace(" ",""),s=r.toLocaleTimeString("en-US",{timeZoneName:"short"}).split(" ").pop();return`${e} ${t} ${s}`}function He(r){return[`# $CMEM ${r} ${je()}`,""]}function Xe(){return[`Legend: \u{1F3AF}session ${A.getInstance().getActiveMode().observation_types.map(t=>`${t.emoji}${t.id}`).join(" ")}`,"Format: ID TIME TYPE TITLE","Fetch details: get_observations([IDs]) | Search: mem-search skill",""]}function Ge(){return[]}function Be(){return[]}function We(r,e){let t=[],s=[`${r.totalObservations} obs (${r.totalReadTokens.toLocaleString()}t read)`,`${r.totalDiscoveryTokens.toLocaleString()}t work`];return r.totalDiscoveryTokens>0&&(e.showSavingsAmount||e.showSavingsPercent)&&(e.showSavingsPercent?s.push(`${r.savingsPercent}% savings`):e.showSavingsAmount&&s.push(`${r.savings.toLocaleString()}t saved`)),t.push(`Stats: ${s.join(" | ")}`),t.push(""),t}function Ye(r){return[`### ${r}`]}function qe(r){return r.toLowerCase().replace(" am","a").replace(" pm","p")}function Ve(r,e,t){let s=r.title||"Untitled",n=A.getInstance().getTypeIcon(r.type),o=e?qe(e):'"';return`${r.id} ${o} ${n} ${s}`}function Ke(r,e,t,s){let n=[],o=r.title||"Untitled",i=A.getInstance().getTypeIcon(r.type),a=e?qe(e):'"',{readTokens:d,discoveryDisplay:u}=k(r,s);n.push(`**${r.id}** ${a} ${i} **${o}**`),t&&n.push(t);let m=[];return s.showReadTokens&&m.push(`~${d}t`),s.showWorkTokens&&m.push(u),m.length>0&&n.push(m.join(" ")),n.push(""),n}function Je(r,e){return[`S${r.id} ${r.request||"Session started"} (${e})`]}function $(r,e){return e?[`**${r}**: ${e}`,""]:[]}function ze(r){return r.assistantMessage?["","---","","**Previously**","",`A: ${r.assistantMessage}`,""]:[]}function Qe(r,e){return["",`Access ${Math.round(r/1e3)}k tokens of past work via get_observations([IDs]) or mem-search skill.`]}function Ze(r){return`# $CMEM ${r} ${je()}
|
||||
`).filter(n=>n.trim()),s="";for(let n=t.length-1;n>=0;n--)try{let o=t[n];if(!o.includes('"type":"assistant"'))continue;let i=JSON.parse(o);if(i.type==="assistant"&&i.message?.content&&Array.isArray(i.message.content)){let a="";for(let d of i.message.content)d.type==="text"&&(a+=d.text);if(a=a.replace(xe,"").trim(),a){s=a;break}}}catch(o){_.debug("PARSER","Skipping malformed transcript line",{lineIndex:n},o);continue}return{userMessage:"",assistantMessage:s}}catch(e){return _.failure("WORKER","Failed to extract prior messages from transcript",{transcriptPath:r},e),{userMessage:"",assistantMessage:""}}}function ce(r,e,t,s){if(!e.showLastMessage||r.length===0)return{userMessage:"",assistantMessage:""};let n=r.find(d=>d.memory_session_id!==t);if(!n)return{userMessage:"",assistantMessage:""};let o=n.memory_session_id,i=Bt(s),a=ke.default.join(y,"projects",i,`${o}.jsonl`);return Wt(a)}function we(r,e){let t=e[0]?.id;return r.map((s,n)=>{let o=n===0?null:e[n+1];return{...s,displayEpoch:o?o.created_at_epoch:s.created_at_epoch,displayTime:o?o.created_at:s.created_at,shouldShowLink:s.id!==t}})}function ue(r,e){let t=[...r.map(s=>({type:"observation",data:s})),...e.map(s=>({type:"summary",data:s}))];return t.sort((s,n)=>{let o=s.type==="observation"?s.data.created_at_epoch:s.data.displayEpoch,i=n.type==="observation"?n.data.created_at_epoch:n.data.displayEpoch;return o-i}),t}function Pe(r,e){return new Set(r.slice(0,e).map(t=>t.id))}function je(){let r=new Date,e=r.toLocaleDateString("en-CA"),t=r.toLocaleTimeString("en-US",{hour:"numeric",minute:"2-digit",hour12:!0}).toLowerCase().replace(" ",""),s=r.toLocaleTimeString("en-US",{timeZoneName:"short"}).split(" ").pop();return`${e} ${t} ${s}`}function He(r){return[`# [${r}] recent context, ${je()}`,""]}function Xe(){return[`Legend: \u{1F3AF}session ${A.getInstance().getActiveMode().observation_types.map(t=>`${t.emoji}${t.id}`).join(" ")}`,"Format: ID TIME TYPE TITLE","Fetch details: get_observations([IDs]) | Search: mem-search skill",""]}function Ge(){return[]}function Be(){return[]}function We(r,e){let t=[],s=[`${r.totalObservations} obs (${r.totalReadTokens.toLocaleString()}t read)`,`${r.totalDiscoveryTokens.toLocaleString()}t work`];return r.totalDiscoveryTokens>0&&(e.showSavingsAmount||e.showSavingsPercent)&&(e.showSavingsPercent?s.push(`${r.savingsPercent}% savings`):e.showSavingsAmount&&s.push(`${r.savings.toLocaleString()}t saved`)),t.push(`Stats: ${s.join(" | ")}`),t.push(""),t}function Ye(r){return[`### ${r}`]}function qe(r){return r.toLowerCase().replace(" am","a").replace(" pm","p")}function Ve(r,e,t){let s=r.title||"Untitled",n=A.getInstance().getTypeIcon(r.type),o=e?qe(e):'"';return`${r.id} ${o} ${n} ${s}`}function Ke(r,e,t,s){let n=[],o=r.title||"Untitled",i=A.getInstance().getTypeIcon(r.type),a=e?qe(e):'"',{readTokens:d,discoveryDisplay:u}=k(r,s);n.push(`**${r.id}** ${a} ${i} **${o}**`),t&&n.push(t);let m=[];return s.showReadTokens&&m.push(`~${d}t`),s.showWorkTokens&&m.push(u),m.length>0&&n.push(m.join(" ")),n.push(""),n}function Je(r,e){return[`S${r.id} ${r.request||"Session started"} (${e})`]}function $(r,e){return e?[`**${r}**: ${e}`,""]:[]}function ze(r){return r.assistantMessage?["","---","","**Previously**","",`A: ${r.assistantMessage}`,""]:[]}function Qe(r,e){return["",`Access ${Math.round(r/1e3)}k tokens of past work via get_observations([IDs]) or mem-search skill.`]}function Ze(r){return`# [${r}] recent context, ${je()}
|
||||
|
||||
No previous sessions found.`}function et(){let r=new Date,e=r.toLocaleDateString("en-CA"),t=r.toLocaleTimeString("en-US",{hour:"numeric",minute:"2-digit",hour12:!0}).toLowerCase().replace(" ",""),s=r.toLocaleTimeString("en-US",{timeZoneName:"short"}).split(" ").pop();return`${e} ${t} ${s}`}function tt(r){return["",`${c.bright}${c.cyan}[${r}] recent context, ${et()}${c.reset}`,`${c.gray}${"\u2500".repeat(60)}${c.reset}`,""]}function st(){let e=A.getInstance().getActiveMode().observation_types.map(t=>`${t.emoji} ${t.id}`).join(" | ");return[`${c.dim}Legend: session-request | ${e}${c.reset}`,""]}function rt(){return[`${c.bright}Column Key${c.reset}`,`${c.dim} Read: Tokens to read this observation (cost to learn it now)${c.reset}`,`${c.dim} Work: Tokens spent on work that produced this record ( research, building, deciding)${c.reset}`,""]}function nt(){return[`${c.dim}Context Index: This semantic index (titles, types, files, tokens) is usually sufficient to understand past work.${c.reset}`,"",`${c.dim}When you need implementation details, rationale, or debugging context:${c.reset}`,`${c.dim} - Fetch by ID: get_observations([IDs]) for observations visible in this index${c.reset}`,`${c.dim} - Search history: Use the mem-search skill for past decisions, bugs, and deeper research${c.reset}`,`${c.dim} - Trust this index over re-reading code for past decisions and learnings${c.reset}`,""]}function ot(r,e){let t=[];if(t.push(`${c.bright}${c.cyan}Context Economics${c.reset}`),t.push(`${c.dim} Loading: ${r.totalObservations} observations (${r.totalReadTokens.toLocaleString()} tokens to read)${c.reset}`),t.push(`${c.dim} Work investment: ${r.totalDiscoveryTokens.toLocaleString()} tokens spent on research, building, and decisions${c.reset}`),r.totalDiscoveryTokens>0&&(e.showSavingsAmount||e.showSavingsPercent)){let s=" Your savings: ";e.showSavingsAmount&&e.showSavingsPercent?s+=`${r.savings.toLocaleString()} tokens (${r.savingsPercent}% reduction from reuse)`:e.showSavingsAmount?s+=`${r.savings.toLocaleString()} tokens`:s+=`${r.savingsPercent}% reduction from reuse`,t.push(`${c.green}${s}${c.reset}`)}return t.push(""),t}function it(r){return[`${c.bright}${c.cyan}${r}${c.reset}`,""]}function at(r){return[`${c.dim}${r}${c.reset}`]}function dt(r,e,t,s){let n=r.title||"Untitled",o=A.getInstance().getTypeIcon(r.type),{readTokens:i,discoveryTokens:a,workEmoji:d}=k(r,s),u=t?`${c.dim}${e}${c.reset}`:" ".repeat(e.length),m=s.showReadTokens&&i>0?`${c.dim}(~${i}t)${c.reset}`:"",l=s.showWorkTokens&&a>0?`${c.dim}(${d} ${a.toLocaleString()}t)${c.reset}`:"";return` ${c.dim}#${r.id}${c.reset} ${u} ${o} ${n} ${m} ${l}`}function ct(r,e,t,s,n){let o=[],i=r.title||"Untitled",a=A.getInstance().getTypeIcon(r.type),{readTokens:d,discoveryTokens:u,workEmoji:m}=k(r,n),l=t?`${c.dim}${e}${c.reset}`:" ".repeat(e.length),E=n.showReadTokens&&d>0?`${c.dim}(~${d}t)${c.reset}`:"",T=n.showWorkTokens&&u>0?`${c.dim}(${m} ${u.toLocaleString()}t)${c.reset}`:"";return o.push(` ${c.dim}#${r.id}${c.reset} ${l} ${a} ${c.bright}${i}${c.reset}`),s&&o.push(` ${c.dim}${s}${c.reset}`),(E||T)&&o.push(` ${E} ${T}`),o.push(""),o}function ut(r,e){let t=`${r.request||"Session started"} (${e})`;return[`${c.yellow}#S${r.id}${c.reset} ${t}`,""]}function F(r,e,t){return e?[`${t}${r}:${c.reset} ${e}`,""]:[]}function mt(r){return r.assistantMessage?["","---","",`${c.bright}${c.magenta}Previously${c.reset}`,"",`${c.dim}A: ${r.assistantMessage}${c.reset}`,""]:[]}function _t(r,e){let t=Math.round(r/1e3);return["",`${c.dim}Access ${t}k tokens of past research & decisions for just ${e.toLocaleString()}t. Use the claude-mem skill to access memories by ID.${c.reset}`]}function pt(r){return`
|
||||
${c.bright}${c.cyan}[${r}] recent context, ${et()}${c.reset}
|
||||
|
||||
File diff suppressed because one or more lines are too long
+184
-184
File diff suppressed because one or more lines are too long
+11
-11
File diff suppressed because one or more lines are too long
@@ -35,7 +35,7 @@ function formatHeaderDateTime(): string {
|
||||
*/
|
||||
export function renderAgentHeader(project: string): string[] {
|
||||
return [
|
||||
`# $CMEM ${project} ${formatHeaderDateTime()}`,
|
||||
`# [${project}] recent context, ${formatHeaderDateTime()}`,
|
||||
''
|
||||
];
|
||||
}
|
||||
@@ -223,5 +223,5 @@ export function renderAgentFooter(totalDiscoveryTokens: number, totalReadTokens:
|
||||
* Render agent empty state
|
||||
*/
|
||||
export function renderAgentEmptyState(project: string): string {
|
||||
return `# $CMEM ${project} ${formatHeaderDateTime()}\n\nNo previous sessions found.`;
|
||||
return `# [${project}] recent context, ${formatHeaderDateTime()}\n\nNo previous sessions found.`;
|
||||
}
|
||||
|
||||
@@ -412,11 +412,22 @@ export function createPidCapturingSpawn(sessionDbId: number) {
|
||||
const useCmdWrapper = process.platform === 'win32' && spawnOptions.command.endsWith('.cmd');
|
||||
const env = sanitizeEnv(spawnOptions.env ?? process.env);
|
||||
|
||||
// Filter empty string args: Bun's spawn() silently drops empty strings from argv,
|
||||
// causing subsequent flags to be consumed as values for the preceding flag.
|
||||
// The Agent SDK may produce empty-string args (e.g., settingSources defaults to []
|
||||
// which joins to ""). Node preserves these, but Bun drops them, breaking CLI parsing.
|
||||
const args = spawnOptions.args.filter(arg => arg !== '');
|
||||
// Filter empty string args AND their preceding flag (Issue #2049).
|
||||
// The Agent SDK emits ["--setting-sources", ""] when settingSources defaults to [].
|
||||
// Simply dropping "" leaves an orphan --setting-sources that consumes the next
|
||||
// flag (e.g. --permission-mode) as its value, crashing Claude Code 2.1.109+ with
|
||||
// "Invalid setting source: --permission-mode". Drop the flag too so the SDK
|
||||
// default (no setting sources) is preserved by omission.
|
||||
const args: string[] = [];
|
||||
for (const arg of spawnOptions.args) {
|
||||
if (arg === '') {
|
||||
if (args.length > 0 && args[args.length - 1].startsWith('--')) {
|
||||
args.pop();
|
||||
}
|
||||
continue;
|
||||
}
|
||||
args.push(arg);
|
||||
}
|
||||
|
||||
const child = useCmdWrapper
|
||||
? spawn('cmd.exe', ['/d', '/c', spawnOptions.command, ...args], {
|
||||
|
||||
@@ -103,7 +103,7 @@ describe('AgentFormatter', () => {
|
||||
const result = renderAgentHeader('my-project');
|
||||
|
||||
expect(result).toHaveLength(2);
|
||||
expect(result[0]).toMatch(/^# \$CMEM my-project \d{4}-\d{2}-\d{2} \d{1,2}:\d{2}[ap]m [A-Z]{3,4}$/);
|
||||
expect(result[0]).toMatch(/^# \[my-project\] recent context, \d{4}-\d{2}-\d{2} \d{1,2}:\d{2}[ap]m [A-Z]{3,4}$/);
|
||||
expect(result[1]).toBe('');
|
||||
});
|
||||
|
||||
@@ -116,7 +116,7 @@ describe('AgentFormatter', () => {
|
||||
it('should handle empty project name', () => {
|
||||
const result = renderAgentHeader('');
|
||||
|
||||
expect(result[0]).toMatch(/^# \$CMEM \d{4}-\d{2}-\d{2} \d{1,2}:\d{2}[ap]m [A-Z]{3,4}$/);
|
||||
expect(result[0]).toMatch(/^# \[\] recent context, \d{4}-\d{2}-\d{2} \d{1,2}:\d{2}[ap]m [A-Z]{3,4}$/);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -452,7 +452,7 @@ describe('AgentFormatter', () => {
|
||||
it('should return helpful message with project name', () => {
|
||||
const result = renderAgentEmptyState('my-project');
|
||||
|
||||
expect(result).toContain('# $CMEM my-project');
|
||||
expect(result).toContain('# [my-project] recent context,');
|
||||
expect(result).toContain('No previous sessions found.');
|
||||
});
|
||||
|
||||
@@ -466,7 +466,7 @@ describe('AgentFormatter', () => {
|
||||
it('should handle empty project name', () => {
|
||||
const result = renderAgentEmptyState('');
|
||||
|
||||
expect(result).toContain('# $CMEM ');
|
||||
expect(result).toContain('# [] recent context,');
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user