Session Storage

~/.mibyan/state.db (SQLite, WAL mode)
├── sessions              — Session metadata, token counts, billing
├── messages              — Full message history per session
├── session_model_usage   — Per-model/per-task usage attribution rows
├── messages_fts          — FTS5 virtual table (content + tool_name + tool_calls)
├── messages_fts_trigram  — FTS5 virtual table with trigram tokenizer (CJK / substring search)
├── messages_fts_cjk      — FTS5 virtual table with cjk_unicode61 tokenizer
├── state_meta            — Key/value metadata table
├── gateway_routing       — Gateway routing metadata
├── compression_locks     — Cross-process compression locking
├── async_delegations     — Async delegation bookkeeping
├── delivery_obligations  — Gateway outbox (owed replies); created lazily by gateway/delivery_ledger.py
└── schema_version        — Single-row table tracking migration state

CREATE TABLE IF NOT EXISTS sessions (
    id TEXT PRIMARY KEY,
    source TEXT NOT NULL,
    user_id TEXT,
    model TEXT,
    model_config TEXT,
    system_prompt TEXT,
    parent_session_id TEXT,
    started_at REAL NOT NULL,
    ended_at REAL,
    end_reason TEXT,
    message_count INTEGER DEFAULT 0,
    tool_call_count INTEGER DEFAULT 0,
    input_tokens INTEGER DEFAULT 0,
    output_tokens INTEGER DEFAULT 0,
    cache_read_tokens INTEGER DEFAULT 0,
    cache_write_tokens INTEGER DEFAULT 0,
    reasoning_tokens INTEGER DEFAULT 0,
    billing_provider TEXT,
    billing_base_url TEXT,
    billing_mode TEXT,
    estimated_cost_usd REAL,
    actual_cost_usd REAL,
    cost_status TEXT,
    cost_source TEXT,
    pricing_version TEXT,
    title TEXT,
    api_call_count INTEGER DEFAULT 0,
    -- ... additional gateway/workspace/handoff/compression columns ...
    FOREIGN KEY (parent_session_id) REFERENCES sessions(id)
);

CREATE INDEX IF NOT EXISTS idx_sessions_source ON sessions(source);
CREATE INDEX IF NOT EXISTS idx_sessions_parent ON sessions(parent_session_id);
CREATE INDEX IF NOT EXISTS idx_sessions_started ON sessions(started_at DESC);
CREATE UNIQUE INDEX IF NOT EXISTS idx_sessions_title_unique
    ON sessions(title) WHERE title IS NOT NULL;

CREATE TABLE IF NOT EXISTS messages (
    id INTEGER PRIMARY KEY AUTOINCREMENT,
    session_id TEXT NOT NULL REFERENCES sessions(id),
    role TEXT NOT NULL,
    content TEXT,
    tool_call_id TEXT,
    tool_calls TEXT,
    tool_name TEXT,
    timestamp REAL NOT NULL,
    token_count INTEGER,
    finish_reason TEXT,
    reasoning TEXT,
    reasoning_content TEXT,
    reasoning_details TEXT,
    codex_reasoning_items TEXT,
    codex_message_items TEXT
    -- ... additional display/compaction columns ...
);

CREATE INDEX IF NOT EXISTS idx_messages_session ON messages(session_id, timestamp);
CREATE INDEX IF NOT EXISTS idx_messages_session_id ON messages(session_id, id);

CREATE VIRTUAL TABLE IF NOT EXISTS messages_fts USING fts5(
    content,
    tool_name,
    tool_calls,
    content='messages',
    content_rowid='id'
);

_WRITE_PATIENCE_S, _TRANSCRIPT_WRITE_PATIENCE_S, _ACTIVITY_WRITE_PATIENCE_S = 20.0, 60.0, 0.5
_WRITE_RETRY_MIN_S, _WRITE_RETRY_MAX_S = 0.020, 0.150
_WRITE_RETRY_SLOW_MIN_S, _WRITE_RETRY_SLOW_MAX_S = 0.250, 1.000
_CHECKPOINT_EVERY_N_WRITES = 50

from mibyan_state import SessionDB

db = SessionDB()                           # Default: ~/.mibyan/state.db
db = SessionDB(db_path=Path("~/.mibyan/cache/scratch/test.db").expanduser())  # Custom path

# Create a new session
db.create_session(
    session_id="sess_abc123",
    source="cli",
    model="anthropic/claude-sonnet-4.6",
    user_id="user_1",
    parent_session_id=None,  # or previous session ID for lineage
)

# End a session
db.end_session("sess_abc123", end_reason="user_exit")

# Reopen a session (clear ended_at/end_reason)
db.reopen_session("sess_abc123")

msg_id = db.append_message(
    session_id="sess_abc123",
    role="assistant",
    content="Here's the answer...",
    tool_calls=[{"id": "call_1", "function": {"name": "terminal", "arguments": "{}"}}],
    token_count=150,
    finish_reason="stop",
    reasoning="Let me think about this...",
)

# Raw messages with all metadata
messages = db.get_messages("sess_abc123")

# OpenAI conversation format (for API replay)
conversation = db.get_messages_as_conversation("sess_abc123")
# Returns: [{"role": "user", "content": "..."}, {"role": "assistant", ...}]

# Set a title (must be unique among non-NULL titles)
db.set_session_title("sess_abc123", "Fix Docker Build")

# Resolve by title (returns most recent in lineage)
session_id = db.resolve_session_by_title("Fix Docker Build")

# Auto-generate next title in lineage
next_title = db.get_next_title_in_lineage("Fix Docker Build")
# Returns: "Fix Docker Build #2"

results = db.search_messages("docker deployment")

# Search only CLI sessions
results = db.search_messages("error", source_filter=["cli"])

# Exclude gateway sessions
results = db.search_messages("bug", exclude_sources=["telegram", "discord"])

# Search only user messages
results = db.search_messages("help", role_filter=["user"])

-- Find all ancestors of a session
WITH RECURSIVE lineage AS (
    SELECT * FROM sessions WHERE id = ?
    UNION ALL
    SELECT s.* FROM sessions s
    JOIN lineage l ON s.id = l.parent_session_id
)
SELECT id, title, started_at, parent_session_id FROM lineage;

-- Find all descendants of a session
WITH RECURSIVE descendants AS (
    SELECT * FROM sessions WHERE id = ?
    UNION ALL
    SELECT s.* FROM sessions s
    JOIN descendants d ON s.parent_session_id = d.id
)
SELECT id, title, started_at FROM descendants;

SELECT s.*,
    COALESCE(
        (SELECT SUBSTR(m.content, 1, 63)
         FROM messages m
         WHERE m.session_id = s.id AND m.role = 'user' AND m.content IS NOT NULL
         ORDER BY m.timestamp, m.id LIMIT 1),
        ''
    ) AS preview,
    COALESCE(
        (SELECT MAX(m2.timestamp) FROM messages m2 WHERE m2.session_id = s.id),
        s.started_at
    ) AS last_active
FROM sessions s
ORDER BY s.started_at DESC
LIMIT 20;

-- Total tokens by model
SELECT model,
       COUNT(*) as session_count,
       SUM(input_tokens) as total_input,
       SUM(output_tokens) as total_output,
       SUM(estimated_cost_usd) as total_cost
FROM sessions
WHERE model IS NOT NULL
GROUP BY model
ORDER BY total_cost DESC;

-- Sessions with highest token usage
SELECT id, title, model, input_tokens + output_tokens AS total_tokens,
       estimated_cost_usd
FROM sessions
ORDER BY total_tokens DESC
LIMIT 10;

# Export a single session with messages
data = db.export_session("sess_abc123")

# Export all sessions (with messages) as list of dicts
all_data = db.export_all(source="cli")

# Delete old sessions (only ended sessions)
deleted_count = db.prune_sessions(older_than_days=90)
deleted_count = db.prune_sessions(older_than_days=30, source="telegram")

# Clear messages but keep the session record
db.clear_messages("sess_abc123")

# Delete session and all messages
db.delete_session("sess_abc123")