# Habit Miner
# Excavates your AI session history to find recurring workflows worth automating
# Scans .claude, .opencode, .cursor, etc. — discovers patterns, writes .prose programs
#
# BACKEND: Run with sqlite+ or postgres for incremental processing across runs
#   prose run 48-habit-miner.prose --backend sqlite+
#
# KEY VM FEATURES USED:
# - persist: true on miner — remembers patterns across runs, watches them mature
# - resume: — incremental processing, only analyzes new logs since last run
# - recursive blocks — handles arbitrarily large log corpora
# - reference-based context — agents read from storage, not everything in memory

input mode: "Mode: 'full' (analyze everything), 'incremental' (new logs only), 'check' (see what's new)"
input min_frequency: "Minimum times a pattern must appear to qualify (default: 3)"
input focus: "Optional: filter to specific area (e.g., 'git', 'testing', 'refactoring')"

# ============================================================
# Agents
# ============================================================

agent scout:
  model: sonnet
  prompt: """
    You discover AI assistant log files on the user's system.

    Check common locations:
    - ~/.claude/ (Claude Code)
    - ~/.opencode/ (OpenCode)
    - ~/.cursor/ (Cursor)
    - ~/.continue/ (Continue)
    - ~/.aider/ (Aider)
    - ~/.copilot/ (GitHub Copilot)
    - ~/.codeium/ (Codeium)
    - ~/.tabnine/ (Tabnine)
    - ~/.config/claude-code/
    - ~/.config/github-copilot/
    - ~/.local/share/*/

    For each location found, report:
    - Path
    - Log format (jsonl, sqlite, json, etc.)
    - Approximate size
    - Number of sessions/files
    - Date range (oldest to newest)
    - NEW since last scan (if incremental)

    Be thorough but respect permissions. Don't read content yet, just inventory.
  """
  permissions:
    bash: allow
    read: ["~/.claude/**", "~/.opencode/**", "~/.cursor/**", "~/.continue/**",
           "~/.aider/**", "~/.copilot/**", "~/.codeium/**", "~/.tabnine/**",
           "~/.config/**", "~/.local/share/**"]

agent parser:
  model: sonnet
  prompt: """
    You parse AI assistant log files into normalized conversation format.

    Handle formats:
    - JSONL: one JSON object per line (Claude Code, many others)
    - SQLite: query conversation tables
    - JSON: array of messages or nested structure
    - Markdown: conversation exports

    Extract for each session:
    - Session ID / timestamp
    - User messages (the requests)
    - Assistant actions (tools used, files modified)
    - Outcome (success/failure indicators)

    Normalize to common schema regardless of source format.
    Track file modification times for incremental processing.
  """
  permissions:
    bash: allow
    read: ["~/.claude/**", "~/.opencode/**", "~/.cursor/**", "~/.continue/**",
           "~/.aider/**", "~/.copilot/**", "~/.codeium/**", "~/.tabnine/**"]

agent miner:
  model: opus
  persist: true  # <-- KEY: Remembers patterns across runs
  prompt: """
    You find and track patterns in conversation histories over time.

    Your memory contains patterns from previous runs. Each pattern has:
    - name: descriptive identifier
    - maturity: emerging (3-5 hits) → established (6-15) → proven (16+)
    - examples: representative instances
    - last_seen: when pattern last appeared
    - trend: growing / stable / declining

    On each run:
    1. Load your memory of known patterns
    2. Process new sessions
    3. Update pattern frequencies and maturity
    4. Identify NEW emerging patterns
    5. Note patterns that are declining (not seen recently)

    Patterns MATURE over time. Don't rush to automate emerging patterns.
    Wait until they're established before recommending automation.
  """

agent qualifier:
  model: opus
  prompt: """
    You determine which patterns are ready for automation.

    Consider MATURITY (from miner's memory):
    - emerging: Too early. Note it, but don't automate yet.
    - established: Good candidate. Enough data to generalize.
    - proven: Strong candidate. Battle-tested pattern.

    Also consider:
    - COMPLEXITY: Multi-step, not trivial
    - CONSISTENCY: Similar enough across instances
    - AUTOMATABLE: Not too context-dependent
    - VALUE: Would save meaningful time/effort

    Reject patterns that are:
    - Still emerging (wait for more data)
    - Too simple (just run a single command)
    - Too variable (every instance is different)
  """

agent author:
  model: opus
  prompt: """
    You write .prose programs from mature workflow patterns.

    For each qualified pattern:
    - Identify the inputs (what varies between instances)
    - Identify the constants (what's always the same)
    - Design appropriate agents for the workflow
    - Structure phases logically
    - Add error handling where needed
    - Include user checkpoints at decision points

    Write idiomatic OpenProse. Follow existing example patterns.
    Reference the pattern's maturity level in a header comment.
  """
  permissions:
    write: ["**/*.prose"]

agent organizer:
  model: sonnet
  prompt: """
    You organize generated .prose programs into a coherent collection.

    Tasks:
    - Group related programs by domain (git, testing, docs, etc.)
    - Suggest directory structure
    - Create an index/README
    - Identify programs that could share blocks or agents
    - Note potential compositions (program A often followed by B)
  """
  permissions:
    write: ["**/*.md", "**/*.prose"]

# ============================================================
# Recursive block for processing large log corpora
# ============================================================

block process_logs(sources, depth):
  # Base case: small enough to process directly
  if **fewer than 50 sessions** or depth <= 0:
    output sources | pmap:
      session: parser
        prompt: "Parse these logs into normalized format"
        context: item

  # Recursive case: chunk and fan out
  let chunks = session "Split sources into ~25 session batches"
    context: sources

  let results = []
  parallel for chunk in chunks:
    let chunk_result = do process_logs(chunk, depth - 1)
    results = results + chunk_result

  output results

# ============================================================
# Phase 0: Discovery
# ============================================================

let inventory = session: scout
  prompt: """
    Scan the system for AI assistant log files.
    Mode: {mode}

    Check all common locations. For each found, report:
    - Full path
    - Format detected
    - Size (human readable)
    - Session/file count
    - Date range
    - If incremental: how many NEW since last scan

    Return a structured inventory.
  """

# For "check" mode, just show what's available and exit
if **mode is check**:
  output result = {
    status: "check-complete",
    inventory: inventory,
    hint: "Run with mode:'incremental' to process new logs, or mode:'full' for everything"
  }

input source_selection: """
  ## AI Assistant Logs Found

  {inventory}

  ---

  Mode: {mode}

  Select which sources to analyze:
  - List the paths you want included
  - Or say "all" to analyze everything found
  - Or say "none" to cancel
"""

if **user selected none or wants to cancel**:
  output result = {
    status: "cancelled",
    inventory: inventory
  }
  throw "User cancelled - no sources selected"

let selected_sources = session: scout
  prompt: "Parse user's selection into a list of paths to analyze"
  context: { inventory, source_selection, mode }

# ============================================================
# Phase 1: Parsing (with recursive chunking for scale)
# ============================================================

let parsed_sessions = do process_logs(selected_sources, 3)

let session_count = session "Count total sessions parsed"
  context: parsed_sessions

# ============================================================
# Phase 2: Mining (with persistent memory)
# ============================================================

# Resume the miner with its accumulated pattern knowledge
let pattern_update = resume: miner
  prompt: """
    Process these new sessions against your pattern memory.

    1. Load your known patterns (with maturity levels)
    2. Match new sessions to existing patterns OR identify new ones
    3. Update frequencies, maturity levels, last_seen dates
    4. Report:
       - Patterns that MATURED (crossed a threshold)
       - NEW patterns emerging
       - Patterns DECLINING (not seen in a while)
       - Current state of all tracked patterns

    Focus area (if specified): {focus}
  """
  context: { parsed_sessions, focus }

# ============================================================
# Phase 3: Qualification
# ============================================================

let qualified = session: qualifier
  prompt: """
    Review the miner's pattern update. Identify patterns ready for automation.

    Minimum frequency threshold: {min_frequency}

    PRIORITIZE:
    1. Patterns that just reached "established" or "proven" maturity
    2. Proven patterns not yet automated
    3. High-value patterns even if just established

    SKIP:
    - Emerging patterns (let them mature)
    - Already-automated patterns (unless significantly evolved)
    - Declining patterns (might be obsolete)

    Return ranked list with reasoning.
  """
  context: { pattern_update, min_frequency }

if **no patterns ready for automation**:
  output result = {
    status: "no-new-automations",
    sessions_analyzed: session_count,
    pattern_update: pattern_update,
    message: "Patterns are still maturing. Run again later."
  }

# ============================================================
# Phase 4: User Checkpoint
# ============================================================

input pattern_selection: """
  ## Patterns Ready for Automation

  Analyzed {session_count} sessions.

  Pattern Update:
  {pattern_update}

  Ready for automation:
  {qualified}

  ---

  Which patterns should I write .prose programs for?
  - List by name or number
  - Or say "all" for everything qualified
  - Or say "none" to let patterns mature further

  You can also refine any pattern description before I write code.
"""

if **user wants to wait for more maturity**:
  output result = {
    status: "deferred",
    sessions_analyzed: session_count,
    pattern_update: pattern_update,
    qualified: qualified
  }

let patterns_to_automate = session: qualifier
  prompt: "Parse user selection into final list of patterns to automate"
  context: { qualified, pattern_selection }

# ============================================================
# Phase 5: Program Generation
# ============================================================

let programs = patterns_to_automate | map:
  session: author
    prompt: """
      Write a .prose program for this pattern.

      Pattern maturity: {pattern.maturity}
      Times observed: {pattern.frequency}
      Representative examples: {pattern.examples}

      The program should:
      - Parameterize what varies between instances
      - Hardcode what's always the same
      - Use appropriate agents for distinct roles
      - Include error handling
      - Add user checkpoints at decision points

      Include a header comment noting:
      - Pattern maturity level
      - Number of observations it's based on
      - Date generated
    """
    context: item

# ============================================================
# Phase 6: Organization
# ============================================================

let organized = session: organizer
  prompt: """
    Organize the generated programs.

    Tasks:
    1. Group by domain (git, testing, docs, refactoring, etc.)
    2. Suggest directory structure
    3. Create an index README with:
       - Program name and one-line description
       - Pattern maturity (established/proven)
       - When to use it
       - Example invocation
    4. Identify shared patterns that could be extracted
    5. Note programs that often chain together
  """
  context: programs

# ============================================================
# Phase 7: Output Location
# ============================================================

input output_location: """
  ## Generated Programs

  {organized}

  ---

  Where should I write these programs?

  Options:
  - A directory path (e.g., ~/my-workflows/)
  - "preview" to just show them without writing
"""

if **user wants preview only**:
  output result = {
    status: "preview",
    sessions_analyzed: session_count,
    pattern_update: pattern_update,
    qualified: qualified,
    programs: programs,
    organization: organized
  }

let written = session: organizer
  prompt: "Write all programs to the specified location with proper structure"
  context: { programs, organized, output_location }
  permissions:
    write: ["**/*.prose", "**/*.md"]

# ============================================================
# Output
# ============================================================

output result = {
  status: "complete",

  # Discovery
  sources_scanned: inventory,
  sources_analyzed: selected_sources,

  # Analysis
  sessions_analyzed: session_count,
  pattern_update: pattern_update,

  # Qualification
  patterns_qualified: qualified,
  patterns_automated: patterns_to_automate,

  # Generation
  programs_written: written,
  organization: organized,

  # For next run
  next_step: "Run again with mode:'incremental' to process new logs and mature patterns"
}