@lavralabs/lavra 0.7.0

package/plugins/lavra/gemini/commands/beads-quick.toml

@@ -0,0 +1,134 @@
+# Generated by beads-compound v0.6.0
+# DO NOT EDIT - changes will be overwritten on next install
+
+description = "Fast-track small tasks — abbreviated plan then straight to execution"
+
+prompt = """
+
+<objective>
+Fast-track small tasks with an abbreviated plan and immediate execution. Skips brainstorm and deepen phases, runs a MINIMAL plan (1-3 child tasks), then transitions directly to `/beads-work`. Still captures knowledge throughout.
+</objective>
+
+<execution_context>
+<raw_argument> #{{args}} </raw_argument>
+
+**Determine if the argument is a bead ID or a task description:**
+
+Check if the argument matches a bead ID pattern:
+- Pattern: lowercase alphanumeric segments separated by hyphens (e.g., `fix-auth`, `beads-123`)
+- Regex: `^[a-z0-9]+-[a-z0-9]+(-[a-z0-9]+)*$`
+
+**If bead ID pattern:**
+
+1. Load the bead:
+   ```bash
+   bd show "#$ARGUMENTS" --json
+   ```
+2. If it exists: extract title and description, announce "Quick-tracking bead #{{args}}: {title}"
+3. If not found: report error and stop
+
+**If task description:**
+- Create a bead:
+  ```bash
+  bd create --title="{concise title}" --description="#$ARGUMENTS" --type=task
+  ```
+- Capture the new bead ID
+
+**If empty:**
+- Ask: "What small task do you want to quick-track? Provide a bead ID or describe the task."
+- Do not proceed until input is provided
+</execution_context>
+
+<context>
+Use `/beads-quick` for small, well-understood tasks: bug fixes, config changes, small refactors, adding a field, writing a utility function.
+
+If you discover the task is larger than expected (touches 5+ files, needs architectural decisions, has unclear requirements), stop and suggest `/beads-plan` or `/beads-design` instead.
+</context>
+
+<process>
+
+### 1. Quick Context Scan
+
+Run in parallel:
+
+```bash
+# Recall relevant knowledge
+.lavra/memory/recall.sh "{keywords from task}"
+```
+
+```bash
+# Quick repo scan for related patterns
+# (grep/glob for relevant files based on task description)
+```
+
+Output recall results before continuing. If nothing found, state "No relevant knowledge found."
+
+### 2. Abbreviated Plan (MINIMAL)
+
+Create 1-3 child tasks as beads. No deep research, no deepen, no review.
+
+```bash
+bd create "{step title}" --parent {BEAD_ID} -d "## What
+{what to implement}
+
+## Validation
+- [ ] {acceptance criterion}"
+```
+
+Keep descriptions short -- this is the fast path. Each child bead needs only What and Validation sections.
+
+If two tasks touch the same file, add a dependency:
+```bash
+bd dep add {later_bead} {earlier_bead}
+```
+
+### 3. Begin Execution
+
+Update the parent bead status and transition to execution:
+
+```bash
+bd update {BEAD_ID} --status in_progress
+```
+
+Execute using the `/beads-work` workflow on the first ready child bead. Follow all `/beads-work` phases (Quick Start, Execute, Quality Check, Ship It) -- the abbreviated plan does not mean abbreviated execution.
+
+**Log knowledge as you work** -- at least one LEARNED/DECISION/FACT/PATTERN comment per task:
+
+```bash
+bd comments add {BEAD_ID} "LEARNED: {insight}"
+```
+
+### 4. Wrap Up
+
+After all child tasks are complete:
+
+1. Run tests and linting
+2. Commit with conventional format
+3. Close the bead: `bd close {BEAD_ID}`
+
+</process>
+
+<success_criteria>
+- Bead created (if description provided) or loaded (if ID provided)
+- 1-3 child tasks created with What/Validation sections
+- All tasks executed and tests passing
+- At least one knowledge comment captured
+- Bead closed on completion
+</success_criteria>
+
+<guardrails>
+- Do NOT use for complex features, architectural changes, or tasks with unclear requirements
+- If scope creep is detected (5+ files, new patterns needed, design decisions required), stop and suggest: "This task has grown beyond quick scope. Consider `/beads-plan` or `/beads-design` for a thorough approach."
+- Do NOT skip knowledge capture -- the fast path still feeds the memory system
+- Do NOT skip tests -- abbreviated planning does not mean lower quality
+</guardrails>
+
+<handoff>
+After completion, present options:
+
+1. **Quick-track another task** -- run `/beads-quick` again
+2. **Review the work** -- run `/beads-review` for a code review
+3. **Checkpoint** -- run `/beads-checkpoint` to save progress
+</handoff>
+
+"""

package/plugins/lavra/gemini/commands/beads-recall.toml

@@ -0,0 +1,281 @@
+# Generated by beads-compound v0.6.0
+# DO NOT EDIT - changes will be overwritten on next install
+
+description = "Search knowledge base mid-session and inject relevant context"
+
+prompt = """
+
+<objective>
+Search the knowledge base (`.lavra/memory/knowledge.jsonl`) mid-session and inject relevant context without restarting Claude Code.
+</objective>
+
+<execution_context>
+<input_document> #{{args}} </input_document>
+
+**Parse the arguments to determine mode:**
+
+1. **Check for flags first:**
+   - `--stats` -> Statistics mode
+   - `--recent N` -> Recent entries mode
+   - `--topic BEAD_ID` -> Topic/epic mode
+
+2. **Check if argument matches bead ID pattern:**
+   - Pattern: lowercase alphanumeric segments separated by hyphens
+   - Regex: `^[a-z0-9]+-[a-z0-9]+(-[a-z0-9]+)*$`
+   - Examples: `bd-001`, `oauth-bug`, `beads-feature-123`
+
+3. **Otherwise treat as keyword search**
+</execution_context>
+
+<process>
+
+### Mode 1: Statistics (--stats)
+
+```bash
+bash .lavra/memory/recall.sh --stats
+```
+
+Display the output directly as a code block:
+
+```
+## Knowledge Base Statistics
+
+{statistics output from recall.sh}
+```
+
+### Mode 2: Recent Entries (--recent N)
+
+```bash
+bash .lavra/memory/recall.sh --recent {N}
+```
+
+Format output:
+
+```
+## Recent Knowledge ({N} entries)
+
+{formatted entries from recall.sh}
+```
+
+### Mode 3: Topic/Epic (--topic BEAD_ID)
+
+```bash
+bash .lavra/memory/recall.sh --topic {BEAD_ID}
+```
+
+Format output:
+
+```
+## Knowledge for Topic: {BEAD_ID}
+
+{formatted entries from recall.sh}
+```
+
+If no results:
+```
+No knowledge found for topic {BEAD_ID}.
+
+The topic may not have child beads with captured knowledge yet.
+```
+
+### Mode 4: Bead ID Recall
+
+When argument matches bead ID pattern:
+
+1. **Load the bead:**
+   ```bash
+   bd show "#$ARGUMENTS" --json
+   ```
+
+2. **If bead doesn't exist:**
+   ```
+   ## Bead Not Found
+
+   Bead ID '#$ARGUMENTS' not found. Check the ID with:
+
+   ```bash
+   bd list --status=open
+   ```
+
+   Stop execution.
+
+3. **If bead exists, extract context:**
+   ```bash
+   TITLE=$(bd show "#{{args}}" --json | jq -r '.[0].title')
+   TYPE=$(bd show "#{{args}}" --json | jq -r '.[0].type')
+   ```
+
+4. **Search using bead title as keywords:**
+   ```bash
+   bash .lavra/memory/recall.sh "$TITLE"
+   ```
+
+5. **Also search by bead ID directly:**
+   ```bash
+   grep "\"bead\":\"#{{args}}\"" .lavra/memory/knowledge.jsonl | jq -r '"\(.type | ascii_upcase): \(.content)"'
+   ```
+
+6. **Format output:**
+
+   ```
+   ## Knowledge Recall: {BEAD_ID}
+
+   **Bead:** {TITLE} ({TYPE})
+
+   ### Direct Knowledge (logged to this bead):
+
+   {entries where bead field matches}
+
+   ### Related Knowledge (matching "{TITLE}"):
+
+   {entries from keyword search}
+   ```
+
+   If no results:
+   ```
+   ## No Knowledge Found
+
+   No knowledge entries found for bead {BEAD_ID} or matching keywords from its title.
+
+   To capture knowledge for this bead:
+   ```bash
+   bd comments add {BEAD_ID} "LEARNED: ..."
+   ```
+
+   Use `/beads-compound` for deep problem documentation.
+   ```
+
+### Mode 5: Keyword Search
+
+When argument is plain text (not a flag or bead ID):
+
+1. **Search with recall.sh:**
+   ```bash
+   bash .lavra/memory/recall.sh "#{{args}}"
+   ```
+
+2. **Check for --type filter:**
+   - If `#$ARGUMENTS` contains `--type learned|decision|fact|pattern|investigation`
+   - Pass to recall.sh: `bash .lavra/memory/recall.sh "query" --type TYPE`
+
+3. **Format output:**
+
+   ```
+   ## Knowledge Recall: "{query}"
+
+   Found {count} entries:
+
+   {formatted output from recall.sh}
+   ```
+
+   If no results:
+   ```
+   ## No Matches Found
+
+   No knowledge entries match "{query}".
+
+   Try:
+   - Different keywords (e.g., "auth" instead of "authentication")
+   - Broader search terms
+   - `/beads-recall --recent 20` to see latest entries
+   - `/beads-recall --stats` to see all topics and tags
+   ```
+
+### Mode 6: Empty Arguments
+
+If `#$ARGUMENTS` is empty:
+
+```
+## Knowledge Recall
+
+Usage:
+```bash
+/beads-recall "keywords"           # Search by keywords
+/beads-recall BD-001               # Recall for specific bead
+/beads-recall --recent 10          # Show recent entries
+/beads-recall --stats              # Database statistics
+/beads-recall --topic BD-005       # Epic's knowledge
+```
+
+Or try:
+```bash
+/beads-recall --recent 10          # See what's been captured lately
+```
+```
+
+## Output Format Standards
+
+**Entry format from recall.sh:**
+```
+[TYPE] content
+  bead: BD-XXX | tag1, tag2, tag3
+```
+
+**Always wrap in code blocks for readability.**
+
+**Count results when possible:**
+- Parse output line count (entries have 2 lines each)
+- Report: "Found {count} entries" or "No matches found"
+
+</process>
+
+<success_criteria>
+- Correct mode detected from arguments
+- Knowledge search executed with appropriate parameters
+- Results formatted clearly with entry counts
+- Empty/no-result cases handled with helpful suggestions
+</success_criteria>
+
+<guardrails>
+- Recall uses FTS5 full-text search (if sqlite3 available) with BM25 ranking
+- Falls back to grep search if sqlite3 not installed
+- Search is case-insensitive and supports fuzzy matching
+- Archive can be included with `--all` flag (not exposed in this command for simplicity)
+- Knowledge is git-tracked, so pulling updates automatically rebuilds the search index
+
+**Error handling:**
+
+**If .lavra/memory/ doesn't exist:**
+```
+## Memory Not Initialized
+
+This project doesn't have knowledge capture set up yet.
+
+Run the beads-compound installer to enable memory features:
+```bash
+bash /path/to/beads-compound-plugin/install.sh
+```
+```
+
+**If knowledge.jsonl doesn't exist:**
+```
+## No Knowledge Captured Yet
+
+Knowledge base is empty. Start capturing knowledge:
+```bash
+bd comments add <BEAD_ID> "LEARNED: ..."
+bd comments add <BEAD_ID> "DECISION: ..."
+```
+
+The memory-capture hook will automatically extract and store these.
+```
+
+**If bd command fails:**
+```
+Beads CLI not found. Install from: https://github.com/steveyegge/beads
+```
+</guardrails>
+
+<handoff>
+**If results found:**
+- Use this knowledge to inform your current work
+- Add new learnings: `bd comments add <BEAD_ID> "LEARNED: ..."`
+- Document complex solutions: `/beads-compound`
+
+**If implementing related work:**
+```bash
+bd create --title="..." --type=feature --priority=2
+```
+</handoff>
+
+"""