fix: lazy session creation — defer DB row until first message by alt-glitch · Pull Request #18370 · NousResearch/hermes-agent

alt-glitch · 2026-05-01T12:11:07Z

Problem

Empty sessions accumulate in state.db when the TUI/web dashboard is opened and closed without sending a message. Every TUI session eagerly creates a DB row within 50ms of opening, even if the user never interacts.

Evidence: 14 ghost sessions (zero messages, no title) found in state.db, all source=tui.

Solution

Defer SQLite session row creation from AIAgent.__init__ to run_conversation() entry — the moment the user actually sends a message.

Key changes:

run_agent.py: Add _ensure_db_session() gate method (boolean flag + error handling that disables _session_db on FK constraint risk). Called at top of run_conversation(). Remove eager create_session() from __init__.
tui_gateway/server.py: Remove eager db.create_session() in _start_agent_build(). Add post-first-message pending_title re-apply hook.
hermes_state.py: Extract _insert_session_row() shared helper (DRY — eliminates duplicate SQL between create_session and ensure_session). Add prune_empty_ghost_sessions() for one-time migration.
cli.py: One-time ghost session prune on startup (scoped to source=tui, NOT EXISTS(messages), 1hr age bound). Fix _pending_title to call _ensure_db_session() before set_session_title().
hermes_cli/main.py: Guard TUI exit summary — skip resume info when message_count == 0.

What stays the same:

CLI already lazy (no change needed)
Gateway already message-triggered (no change needed)
Session ID still generated at init (in-memory routing identifier)
JSON session file still guarded by if not messages: return

Other harness comparison

Tool	Open → close without message	Session persisted?
Codex	Zero artifacts	❌
Claude Code (Ctrl+C×2)	Nothing	❌
Hermes CLI	No DB row (already lazy)	❌
Hermes TUI (before)	DB row created eagerly	✅ BUG
Hermes TUI (after)	No DB row	❌ ✅

Testing

test_860_dedup.py: All 9 tests pass (adapted to call _ensure_db_session() before direct flush)
477 session-related tests pass
Manual verification: open/close Hermes → 0 new DB rows
Prune migration: cleaned 13/14 ghost sessions on first run (1 too recent for 1hr safety cutoff)

Adversarial review

Spec reviewed by Claude Code (Sonnet) and Codex (GPT-5.5) through 3 rounds:

R1: Found 7 issues (prune too broad, metadata loss, title re-apply broken, etc.) — all fixed
R2: Claude Code clean, Codex confirmed spec correctness
R3 (on implementation): Claude Code found metadata loss in compression path — fixed

Closes #18269
Supersedes #18283
Supersedes #18299

alt-glitch · 2026-05-01T12:36:38Z

Addresses #18269 (TUI eagerly persists empty sessions). Also related to #17128 (avoid creating chat sessions on dashboard mount).

Prevents ghost sessions from accumulating in state.db when the TUI/web dashboard is opened and closed without sending a message. Changes: - run_agent.py: Add _ensure_db_session() gate method, called at run_conversation() entry. Remove eager create_session() from __init__. Handle compression rotation flag correctly. - tui_gateway/server.py: Remove eager db.create_session() in _start_agent_build(). Add post-first-message pending_title re-apply. - hermes_state.py: Extract _insert_session_row() shared helper (DRY). Add prune_empty_ghost_sessions() for one-time migration. - cli.py: One-time ghost session prune on startup. Fix _pending_title to call _ensure_db_session() before set_session_title(). - hermes_cli/main.py: Guard TUI exit summary on message_count > 0. - tests: Update test_860_dedup to call _ensure_db_session() before direct _flush_messages_to_session_db() calls. Closes: ghost session clutter in hermes sessions list and web dashboard.

…ation Cherry-picked from NousResearch/hermes-agent: 1. f0dc919 - fix(compression): include system prompt + tool schemas in token estimates (NousResearch#18265). Replaces estimate_messages_tokens_rough() with estimate_request_tokens_rough() so that tool schema tokens (20-30K with 50+ tools) are counted, preventing compression from being skipped past its threshold. 2. c5b4c48 - fix: lazy session creation — defer DB row until first message (NousResearch#18370). Prevents empty/ghost session rows from accumulating. Adds prune_empty_ghost_sessions() for one-time cleanup. Co-Authored-By: Claude Opus 4.7 <[email protected]>

Fix three regressions introduced by PR #18370 (lazy session creation): 1. _finalize_session() uses stale session_key after compression (#20001) 2. session_key not synced after auto-compression in run_conversation (#20001) 3. pending_title ValueError leaves title wedged forever (#19029) 4. Gateway silently swallows null responses when agent did work (#18765) 5. One-time cleanup for accumulated ghost compression continuations (#20001) Changes: - tui_gateway/server.py: _finalize_session() now uses agent.session_id (falls back to session_key when agent is None). Refactor _sync_session_key_after_compress() with clear_pending_title and restart_slash_worker policy flags. Call it post-run_conversation() to sync session_key after auto-compression. Add ValueError handler to pending_title flush. - gateway/run.py: Extract _normalize_empty_agent_response() helper that consolidates failed/partial/null response handling. Surfaces user-facing error when agent did work (api_calls > 0) but returned no text. - hermes_state.py: Add finalize_orphaned_compression_sessions() — marks ghost continuation sessions as ended (non-destructive, preserves data). - cli.py: One-time startup migration for orphaned compression sessions. Test changes: - tests/test_tui_gateway_server.py: Update pending_title ValueError test for post-#18370 architecture (title applied post-message, not at create). - tests/test_lazy_session_regressions.py: 14 new regression tests covering all fixed paths.

…llout) (NousResearch#20363) Fix three regressions introduced by PR NousResearch#18370 (lazy session creation): 1. _finalize_session() uses stale session_key after compression (NousResearch#20001) 2. session_key not synced after auto-compression in run_conversation (NousResearch#20001) 3. pending_title ValueError leaves title wedged forever (NousResearch#19029) 4. Gateway silently swallows null responses when agent did work (NousResearch#18765) 5. One-time cleanup for accumulated ghost compression continuations (NousResearch#20001) Changes: - tui_gateway/server.py: _finalize_session() now uses agent.session_id (falls back to session_key when agent is None). Refactor _sync_session_key_after_compress() with clear_pending_title and restart_slash_worker policy flags. Call it post-run_conversation() to sync session_key after auto-compression. Add ValueError handler to pending_title flush. - gateway/run.py: Extract _normalize_empty_agent_response() helper that consolidates failed/partial/null response handling. Surfaces user-facing error when agent did work (api_calls > 0) but returned no text. - hermes_state.py: Add finalize_orphaned_compression_sessions() — marks ghost continuation sessions as ended (non-destructive, preserves data). - cli.py: One-time startup migration for orphaned compression sessions. Test changes: - tests/test_tui_gateway_server.py: Update pending_title ValueError test for post-NousResearch#18370 architecture (title applied post-message, not at create). - tests/test_lazy_session_regressions.py: 14 new regression tests covering all fixed paths.

…search#18370) Prevents ghost sessions from accumulating in state.db when the TUI/web dashboard is opened and closed without sending a message. Changes: - run_agent.py: Add _ensure_db_session() gate method, called at run_conversation() entry. Remove eager create_session() from __init__. Handle compression rotation flag correctly. - tui_gateway/server.py: Remove eager db.create_session() in _start_agent_build(). Add post-first-message pending_title re-apply. - hermes_state.py: Extract _insert_session_row() shared helper (DRY). Add prune_empty_ghost_sessions() for one-time migration. - cli.py: One-time ghost session prune on startup. Fix _pending_title to call _ensure_db_session() before set_session_title(). - hermes_cli/main.py: Guard TUI exit summary on message_count > 0. - tests: Update test_860_dedup to call _ensure_db_session() before direct _flush_messages_to_session_db() calls. Closes: ghost session clutter in hermes sessions list and web dashboard.