liteagents 2.4.7 → 2.5.0

package/packages/claude/commands/friction.md

@@ -0,0 +1,139 @@
+---
+name: friction
+description: Analyze session behavior patterns
+usage: /friction <sessions-path>
+argument-hint: <sessions-path>
+---
+
+Analyze Claude Code session logs for friction signals, behavioral patterns, and failure antigens.
+
+**Guardrails**
+- Favor straightforward, minimal implementations first and add complexity only when requested or clearly required.
+- Keep changes tightly scoped to the requested outcome.
+
+**Argument: sessions-path (required)**
+
+Path to the Claude Code sessions directory containing JSONL files.
+- Example: `/friction ~/.claude/projects/-home-hamr-PycharmProjects-aurora/`
+- If no argument provided, ask the user for the path. Do NOT guess.
+
+**What it does**
+
+Runs friction analysis on session JSONL files and writes results to `.claude/friction/` in the current project.
+
+**Steps**
+
+1. **Validate path**
+   - The argument `$ARGUMENTS` is the sessions path
+   - Verify the path exists and contains `.jsonl` files
+   - If path doesn't exist or has no JSONL files, tell the user and stop
+   - Count total session files found
+
+2. **Run friction.js** (bundled at `commands/friction/friction.js`)
+   - Look for friction.js in order:
+     1. `~/.claude/commands/friction/friction.js` (installed)
+     2. `packages/claude/commands/friction/friction.js` (package development)
+   - If found, run: `node <path-to-friction.js> "$ARGUMENTS"`
+   - If it does NOT exist anywhere, fall back to running the analysis manually (step 3)
+   - If friction.js succeeds, skip to step 7
+
+3. **Manual analysis fallback** (only if friction.js not available)
+   - For each `.jsonl` session file in the path:
+     - Read the file
+     - Extract signals using these patterns:
+
+   | Signal | Weight | How to detect |
+   |---|---|---|
+   | `user_intervention` | 10 | User message contains `/stash` |
+   | `session_abandoned` | 10 | Last 3 turns have friction > 15 and no `exit_success` |
+   | `false_success` | 8 | LLM text contains "done"/"complete"/"fixed" AND next tool result has error |
+   | `no_resolution` | 8 | Session has `exit_error` signals but no `exit_success` after them |
+   | `tool_loop` | 6 | Same tool called 3+ times with identical arguments |
+   | `rapid_exit` | 6 | <3 turns AND ends with error |
+   | `interrupt_cascade` | 5 | Multiple `request_interrupted` within 60 seconds |
+   | `user_curse` | 5 | User message matches profanity patterns |
+   | `request_interrupted` | 2.5 | Turn has `is_interrupted: true` or ESC/Ctrl+C signal |
+   | `exit_error` | 1 | Tool result has non-zero exit code |
+   | `repeated_question` | 1 | User asks same question twice (fuzzy match) |
+   | `long_silence` | 0.5 | >10 minute gap between turns |
+   | `user_negation` | 0.5 | User message starts with "no", "wrong", "didn't work" |
+   | `compaction` | 0.5 | System message indicates context compaction |
+
+4. **Score each session**
+   - Accumulate weighted signal scores (no subtraction, only accumulation)
+   - Track peak friction score
+   - Classify session quality:
+     - **BAD**: has `user_intervention` or `session_abandoned`
+     - **FRICTION**: has `user_curse` or `false_success`
+     - **ROUGH**: peak friction >= 15, no intervention
+     - **OK**: low friction, completed normally
+     - **ONE-SHOT**: single turn, not interactive (filter out)
+
+5. **Aggregate stats**
+   - Count sessions by quality
+   - Calculate BAD rate
+   - Identify worst and best sessions
+   - Daily trend if sessions span multiple days
+
+6. **Extract antigen candidates from BAD sessions**
+   - For each BAD session, extract:
+     - Anchor signal (what triggered BAD classification)
+     - Tool sequence around the failure
+     - Error messages
+     - Pattern description
+   - Write as antigen candidates
+
+7. **Write output to `.claude/friction/`**
+   - Create `.claude/friction/` directory if it doesn't exist
+   - Write these files:
+     - `friction_analysis.json` — per-session breakdown (quality, peak, signals)
+     - `friction_summary.json` — aggregate stats, verdict, daily trend
+     - `friction_raw.jsonl` — all raw signals with timestamps
+     - `antigen_candidates.json` — raw extracted failure patterns
+     - `antigen_clusters.json` — clustered patterns (primary artifact for /remember)
+     - `antigen_review.md` — human-readable clustered review
+
+8. **Report to user**
+   - Sessions analyzed count
+   - BAD / FRICTION / ROUGH / OK counts
+   - BAD rate percentage
+   - Worst session ID and peak friction
+   - Path to `antigen_review.md` for review
+   - Remind: run `/remember` to consolidate into project memory
+
+**Output format for antigen_review.md**
+
+```markdown
+# Friction Antigen Clusters
+
+Generated: [date]
+BAD sessions: [count] | Raw candidates: [count] | Clusters: [count]
+
+## Cluster Summary
+
+| # | Signal | Tool Pattern | Count | Sessions | Score | Median Peak |
+|---|--------|-------------|-------|----------|-------|-------------|
+| 1 | false_success | Bash,Bash | 35 | 23 | 280 | 73 |
+| 2 | user_intervention | (none) | 34 | 24 | 340 | 65 |
+
+## Cluster 1: false_success | Bash,Bash
+
+**Occurrences:** 35 across 23 sessions | **Score:** 280
+
+### User Context (what the user said)
+> [actual user quote from session]
+
+### Errors
+[error messages if any]
+
+### Files involved
+- [file paths]
+```
+
+**File locations**
+- Design doc: `docs/02-features/memory/LONG_TERM_MEMORY.md`
+- Input: JSONL session files from `$ARGUMENTS` path
+- Output: `.claude/friction/` (project-local)
+- JS script: `commands/friction/friction.js` (bundled alongside this command)
+- Python equivalent: `scripts/friction.py` (aurora users, same logic)
+- Manual fallback: built into this command if friction.js unavailable

package/packages/claude/commands/remember.md

@@ -0,0 +1,110 @@
+---
+name: remember
+description: Consolidate stashes + friction into project memory
+usage: /remember
+---
+
+Consolidate session stashes and friction analysis into a single project-local MEMORY.md, then inject into CLAUDE.md.
+
+**Guardrails**
+- Favor straightforward, minimal implementations first and add complexity only when requested or clearly required.
+- Keep changes tightly scoped to the requested outcome.
+
+**What it does**
+
+Reads all raw material (`.claude/stash/*.md` + `.claude/friction/antigen_clusters.json`), extracts durable facts, episodes, and behavioral preferences into a single `.claude/memory/MEMORY.md`, then injects a managed memory section into `CLAUDE.md`.
+
+**Steps**
+
+1. **Gather sources**
+   - Read all `.claude/stash/*.md` files in the current project
+   - Check for friction output at `.claude/friction/antigen_clusters.json` (preferred) or `.claude/friction/antigen_review.md` (fallback)
+   - Read existing `.claude/memory/MEMORY.md` if it exists — create dir if missing
+   - Read processed manifest at `.claude/memory/.processed` — skip already-processed stashes
+   - If no unprocessed stashes, report "nothing to consolidate" and stop
+
+2. **Extract from unprocessed stashes** (use Task tool with sonnet model for each)
+   - For each unprocessed stash, call sonnet to extract:
+     - **FACTS** (atomic, one-line): stable preferences, decisions, corrections, explicit "remember this"
+     - **EPISODE** (3-5 bullet narrative): what was the goal, what was tried, outcome, lesson
+     - **SKIP**: code details, file paths, errors, mechanical steps, LLM responses
+   - Collect all new facts and episodes
+
+3. **Merge into MEMORY.md**
+   - Read existing `.claude/memory/MEMORY.md` and parse its three sections (## Facts, ## Episodes, ## Preferences)
+   - **Facts section**: call sonnet with existing facts + newly extracted facts
+     - Rules: new updates replace old, contradictions keep new version, duplicates dropped
+     - Keep facts atomic, one line each
+   - **Episodes section**: append new episode entries (append-only, timestamped, no dedup)
+   - **Preferences section**: only update if friction output exists (step 4)
+   - Write merged result to `.claude/memory/MEMORY.md` in this format:
+
+   ```markdown
+   # Project Memory
+   > Auto-generated by /remember. Do not edit manually.
+
+   ## Facts
+   - [atomic fact 1]
+   - [atomic fact 2]
+
+   ## Episodes
+   ### YYYY-MM-DD - [title]
+   - [bullet narrative]
+
+   ### YYYY-MM-DD - [title]
+   - [bullet narrative]
+
+   ## Preferences
+   ### High Confidence
+   - [pattern] (evidence: [count] observations)
+
+   ### Medium Confidence
+   - [pattern] (evidence: [count] observations)
+
+   ### Low Confidence
+   - [pattern] (evidence: [count] observations)
+   ```
+
+4. **Distill friction into preferences** (only if friction output exists)
+   - Read `.claude/friction/antigen_clusters.json` — this contains clustered failure patterns with counts, user_context quotes, and tool sequences
+   - For the **top 10 clusters** (by score), extract the `contexts` field — these are the actual user messages that show behavioral patterns
+   - Call sonnet with:
+     - The top 10 clusters (signal, tool_pattern, count, sessions, contexts, errors)
+     - Existing Preferences section from MEMORY.md
+   - Extract BEHAVIORAL preferences (patterns demonstrated, not stated) — the user_context quotes are the primary evidence
+   - Confidence tiers:
+     - **High Confidence**: 5+ observations — available via @MEMORY.md
+     - **Medium Confidence**: 3+ observations — observing, not loaded
+     - **Low Confidence**: <3 observations — needs more data
+   - Promote/demote based on new evidence
+   - Update the Preferences section in MEMORY.md
+
+5. **Inject memory reference into CLAUDE.md**
+   - Compose the section between `<!-- MEMORY:START -->` and `<!-- MEMORY:END -->` markers:
+     ```
+     <!-- MEMORY:START -->
+     @MEMORY.md
+     <!-- MEMORY:END -->
+     ```
+   - The `@MEMORY.md` reference points to `.claude/memory/MEMORY.md` — Claude loads the full file directly, so no inline duplication is needed
+   - If CLAUDE.md already has MEMORY markers, replace the section between them
+   - If CLAUDE.md has no MEMORY markers, append the section at the end
+   - If no CLAUDE.md exists, create one with just the memory section
+
+6. **Update processed manifest**
+   - Append paths of newly processed stashes to `.claude/memory/.processed`
+
+7. **Report to user**
+   - Number of stashes processed
+   - Facts count (total, new)
+   - Episodes count (total, new)
+   - Preferences count by confidence tier
+   - Confirm MEMORY.md and CLAUDE.md updated
+
+**File locations (all project-local)**
+- Memory file: `.claude/memory/MEMORY.md` (single source of truth, referenced as @MEMORY.md)
+- Stash files: `.claude/stash/*.md`
+- Friction output: `.claude/friction/antigen_clusters.json` (clustered patterns with user contexts)
+- Friction fallback: `.claude/friction/antigen_review.md` (human-readable clusters)
+- Processed manifest: `.claude/memory/.processed`
+- Output: `CLAUDE.md` (managed MEMORY section with @MEMORY.md reference)

package/packages/claude/skills/docs-builder/SKILL.md

@@ -125,7 +125,8 @@ mkdir -p docs/{00-context,01-product,02-features,03-logs,04-process,archive}
 
 Create these files (see `references/templates.md` for content):
 
-**00-context/** (3 files):
+**00-context/** (4 files):
+- [ ] `blueprint.md` - Overarching project artifact (see below)
 - [ ] `vision.md` - Product purpose & boundaries
 - [ ] `assumptions.md` - Constraints, risks, unknowns
 - [ ] `system-state.md` - What's currently built
@@ -194,19 +195,69 @@ Update to reference new structure with quick links.
 ls -la docs/{00-context,01-product,02-features,03-logs,04-process,archive}
 
 # Verify minimum files
+test -f docs/00-context/blueprint.md && echo "✓ blueprint.md"
 test -f docs/00-context/vision.md && echo "✓ vision.md"
 test -f docs/00-context/system-state.md && echo "✓ system-state.md"
 test -f docs/01-product/prd.md && echo "✓ prd.md"
 test -f docs/README.md && echo "✓ README.md"
 
 # Count files per tier
-find docs/00-context -name "*.md" | wc -l  # >= 3
+find docs/00-context -name "*.md" | wc -l  # >= 4
 find docs/03-logs -name "*.md" | wc -l     # >= 5
 find docs/04-process -name "*.md" | wc -l  # >= 3
 ```
 
 ---
 
+## Blueprint: The Overarching Project Artifact
+
+`docs/00-context/blueprint.md` is the **one and only** high-level project document. It answers: what is this project, what's built, what's planned, where is it headed.
+
+**When to create:** Always. blueprint.md is the first file created in 00-context/. It is required for both Fresh and Existing modes.
+
+**Content sources:**
+- Root `README.md` — project identity, purpose, stats
+- `package.json` / `pyproject.toml` — tech stack, dependencies
+- Existing docs — features implemented vs planned
+- Code structure — what modules/packages exist
+
+**Structure:**
+
+```markdown
+# [Project Name] Blueprint
+
+## Identity
+[What this project IS in 2-3 sentences. Sourced from README.]
+
+## Status
+| Area | Status | Notes |
+|------|--------|-------|
+| [feature/module] | implemented / in-progress / planned | [brief] |
+
+## Architecture
+[High-level structure: packages, modules, entry points. No ASCII trees — use tables or flat lists.]
+
+## Implemented
+[What works today. Group by feature area. Be specific.]
+
+## Planned
+[What's next. Ordered by priority. Include design docs if they exist.]
+
+## Future Direction
+[Where does this project want to be? North star. 3-5 bullets max.]
+
+## Key Decisions
+[Major architectural choices already made. Link to decisions-log if it exists.]
+```
+
+**Rules for blueprint.md:**
+- Keep it under 150 lines — it's an overview, not a manual
+- Update it when features ship or plans change
+- It is the FIRST document a new contributor or LLM should read
+- No duplication with vision.md (vision = WHY, blueprint = WHAT + WHERE)
+
+---
+
 ## Rules
 
 **DO:**

package/packages/claude/skills/docs-builder/references/templates.md

@@ -2,6 +2,35 @@
 
 Detailed templates for each file in the /docs structure.
 
+## 00-context/blueprint.md
+
+```markdown
+# [Project Name] Blueprint
+
+## Identity
+[What this project IS in 2-3 sentences. Sourced from README.]
+
+## Status
+| Area | Status | Notes |
+|------|--------|-------|
+| [feature/module] | implemented / in-progress / planned | [brief] |
+
+## Architecture
+[High-level structure: packages, modules, entry points. Tables or flat lists, no ASCII trees.]
+
+## Implemented
+[What works today. Group by feature area. Be specific about what ships.]
+
+## Planned
+[What's next. Ordered by priority. Link to design docs if they exist.]
+
+## Future Direction
+[Where does this project want to be? North star. 3-5 bullets max.]
+
+## Key Decisions
+[Major architectural choices already made. Brief rationale. Link to decisions-log if available.]
+```
+
 ## 00-context/vision.md
 
 ```markdown

package/packages/droid/AGENTS.md

@@ -22,7 +22,7 @@ These subagents are available when using Claude Code CLI. Droid can reference th
 | system-architect | Architect | Use for system design, architecture documents, technology selection, API design, and infrastructure planning |
 | ui-designer | UX Expert | Use for UI/UX design, wireframes, prototypes, front-end specifications, and user experience optimization |
 
-## Droid Commands (20 total)
+## Droid Commands (22 total)
 
 | ID | Description | Usage | Auto |
 |---|---|---|---|
@@ -32,9 +32,11 @@ These subagents are available when using Claude Code CLI. Droid can reference th
 | debug | Debug an issue systematically using structured investigation techniques | /debug <issue-description> | - |
 | docs-builder | Create comprehensive project documentation with structured /docs hierarchy | /docs-builder | false |
 | explain | Explain code for someone new to the codebase | /explain <code-section> | - |
+| friction | Analyze session logs for failure patterns and behavioral signals | /friction <sessions-path> | - |
 | git-commit | Analyze changes and create intelligent git commits | /git-commit | - |
 | optimize | Analyze and optimize performance issues | /optimize <target-area> | - |
 | refactor | Refactor code while maintaining behavior and tests | /refactor <code-section> | - |
+| remember | Consolidate stashes + friction into project memory | /remember | - |
 | review | Comprehensive code review including quality, tests, and architecture | /review | - |
 | root-cause-tracing | Systematically traces bugs backward through call stack to identify source | /root-cause-tracing <issue-description> | false |
 | security | Security vulnerability scan and analysis | /security | - |

package/packages/droid/commands/docs-builder/templates.md

@@ -2,6 +2,35 @@
 
 Detailed templates for each file in the /docs structure.
 
+## 00-context/blueprint.md
+
+```markdown
+# [Project Name] Blueprint
+
+## Identity
+[What this project IS in 2-3 sentences. Sourced from README.]
+
+## Status
+| Area | Status | Notes |
+|------|--------|-------|
+| [feature/module] | implemented / in-progress / planned | [brief] |
+
+## Architecture
+[High-level structure: packages, modules, entry points. Tables or flat lists, no ASCII trees.]
+
+## Implemented
+[What works today. Group by feature area. Be specific about what ships.]
+
+## Planned
+[What's next. Ordered by priority. Link to design docs if they exist.]
+
+## Future Direction
+[Where does this project want to be? North star. 3-5 bullets max.]
+
+## Key Decisions
+[Major architectural choices already made. Brief rationale. Link to decisions-log if available.]
+```
+
 ## 00-context/vision.md
 
 ```markdown

package/packages/droid/commands/docs-builder.md

@@ -125,7 +125,8 @@ mkdir -p docs/{00-context,01-product,02-features,03-logs,04-process,archive}
 
 Create these files (see `docs-builder/templates.md` for content):
 
-**00-context/** (3 files):
+**00-context/** (4 files):
+- [ ] `blueprint.md` - Overarching project artifact (see below)
 - [ ] `vision.md` - Product purpose & boundaries
 - [ ] `assumptions.md` - Constraints, risks, unknowns
 - [ ] `system-state.md` - What's currently built
@@ -175,7 +176,7 @@ When moving files:
 
 ## Step 5: Integration
 
-**If CLAUDE.md exists:**
+**If AGENTS.md exists:**
 Add or update documentation pointer:
 ```markdown
 ## Documentation
@@ -194,19 +195,69 @@ Update to reference new structure with quick links.
 ls -la docs/{00-context,01-product,02-features,03-logs,04-process,archive}
 
 # Verify minimum files
+test -f docs/00-context/blueprint.md && echo "✓ blueprint.md"
 test -f docs/00-context/vision.md && echo "✓ vision.md"
 test -f docs/00-context/system-state.md && echo "✓ system-state.md"
 test -f docs/01-product/prd.md && echo "✓ prd.md"
 test -f docs/README.md && echo "✓ README.md"
 
 # Count files per tier
-find docs/00-context -name "*.md" | wc -l  # >= 3
+find docs/00-context -name "*.md" | wc -l  # >= 4
 find docs/03-logs -name "*.md" | wc -l     # >= 5
 find docs/04-process -name "*.md" | wc -l  # >= 3
 ```
 
 ---
 
+## Blueprint: The Overarching Project Artifact
+
+`docs/00-context/blueprint.md` is the **one and only** high-level project document. It answers: what is this project, what's built, what's planned, where is it headed.
+
+**When to create:** Always. blueprint.md is the first file created in 00-context/. It is required for both Fresh and Existing modes.
+
+**Content sources:**
+- Root `README.md` — project identity, purpose, stats
+- `package.json` / `pyproject.toml` — tech stack, dependencies
+- Existing docs — features implemented vs planned
+- Code structure — what modules/packages exist
+
+**Structure:**
+
+```markdown
+# [Project Name] Blueprint
+
+## Identity
+[What this project IS in 2-3 sentences. Sourced from README.]
+
+## Status
+| Area | Status | Notes |
+|------|--------|-------|
+| [feature/module] | implemented / in-progress / planned | [brief] |
+
+## Architecture
+[High-level structure: packages, modules, entry points. No ASCII trees — use tables or flat lists.]
+
+## Implemented
+[What works today. Group by feature area. Be specific.]
+
+## Planned
+[What's next. Ordered by priority. Include design docs if they exist.]
+
+## Future Direction
+[Where does this project want to be? North star. 3-5 bullets max.]
+
+## Key Decisions
+[Major architectural choices already made. Link to decisions-log if it exists.]
+```
+
+**Rules for blueprint.md:**
+- Keep it under 150 lines — it's an overview, not a manual
+- Update it when features ship or plans change
+- It is the FIRST document a new contributor or LLM should read
+- No duplication with vision.md (vision = WHY, blueprint = WHAT + WHERE)
+
+---
+
 ## Rules
 
 **DO:**