Ben Barclay af93cb33cb feat(gateway): key Discord auto-thread sessions on prospective_thread_id ... Live staging (2026-08-02): only the FIRST auto-thread in a channel got an auto-title/rename. Root cause is a grouping-model mismatch — the connector auto-threads per message (each channel message spawns its own thread), but the gateway keyed sessions per PARENT CHANNEL, so every message after the first reused the first message's already-titled session; auto-title short-circuited and the rename lane never fired for later threads. Intended model: a channel message INITIATES a session, the thread CONTINUES it. A Discord thread created from a message reuses that message's id as the thread id, so the connector can tell us the thread id at inbound (before the thread exists). The paired connector change stamps it as source.prospective_thread_id; this keys the session on it: - SessionSource.prospective_thread_id (new field; to_dict/from_dict + the relay ws_transport inbound source build read it off the wire). - build_session_key: effective_thread_id = thread_id or prospective_thread_id. The channel-initiating message (no thread_id, carries prospective) and the later follow-ups that arrive IN that thread (real thread_id == prospective_thread_id) now produce the SAME key. A real thread_id always wins. The chat_type slot is normalized to "thread" when keying on a prospective id so the initiating "group"/"channel" event byte-matches the follow-up "thread" event. Prospective-thread sessions are shared across participants like any thread (not per-user). Net effect: each distinct channel message is its own session/thread and gets its own title + rename; follow-ups inside a thread continue that session with full history. Additive and inert until the connector sends the field, so non-relay and pre-deploy behaviour is byte-identical. Tests: initiate-then-continue share one session; distinct channel messages get distinct sessions; real thread_id wins over prospective; prospective sessions shared across participants. Session suite 59 passed; relay suite green; ruff + footguns clean. Paired: gateway-gateway stamps prospective_thread_id per auto-threading instance.		2026-08-01 18:34:01 -07:00
..
acp	fix(acp): bind session_id in session context for subprocess isolation	2026-08-01 14:53:34 -07:00
acp_adapter	fix(acp): serialize late MCP refresh with turn start + self-sufficient agent-build wait	2026-08-01 13:27:58 +05:30
agent	fix(auth): route anthropic adapter credential reads through the profile secret scope	2026-08-01 16:42:51 -07:00
ci	ci: skip Desktop E2E + Docker build on tests-only PRs (python_prod lane)	2026-08-01 14:59:14 -07:00
cli	fix(cli): route keyless first run into provider onboarding instead of a broken chat	2026-08-01 15:34:16 -07:00
computer_use	Merge remote-tracking branch 'origin/main' into tests/prune-low-value	2026-07-29 14:12:25 -07:00
conformance	test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s	2026-07-29 13:39:40 -07:00
cron	test(tests): assert SessionDB timeout without wall-clock	2026-07-29 18:55:10 -07:00
dashboard	test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s	2026-07-29 13:39:40 -07:00
docker	fix(docker): update runtime tests and docs for the entrypoint dispatcher	2026-08-01 10:52:34 -07:00
e2e	test(relay): gate native Anthropic streaming in e2e	2026-07-28 08:25:25 -07:00
fakes	…
fixtures	feat(computer_use): align cua-driver 0.9 contracts	2026-07-29 12:19:37 -07:00
gateway	feat(gateway): key Discord auto-thread sessions on prospective_thread_id	2026-08-01 18:34:01 -07:00
hermes_cli	fix(managed_uv): keep project uv config on the candidate locked sync	2026-08-01 20:02:43 -05:00
hermes_state	test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s	2026-07-29 13:39:40 -07:00
honcho_plugin	fix(honcho): network-hermetic unit tests + lazy async writer start	2026-07-29 18:55:10 -07:00
integration	…
manual	…
monitoring	test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s	2026-07-29 13:39:40 -07:00
openviking_plugin	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
plugins	Merge pull request #76417 from NousResearch/bb/kanban-model-picker	2026-08-01 16:55:01 -05:00
providers	modernize re-added Vercel integrations: SDK 0.7.2, telemetry off, sibling-site wiring	2026-07-29 19:48:37 -07:00
run_agent	fix(tool-executor): emit tool results on hard interrupt to keep alternation	2026-08-01 16:42:57 -07:00
scripts	fix(skills-hub): include owner in ClawHub source URLs and add retry on 429 (#51236)	2026-07-31 22:33:11 -07:00
secret_sources	test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s	2026-07-29 13:39:40 -07:00
skills	fix(deps): repair Google transitive security floors (#72108)	2026-07-31 23:18:38 -07:00
state	fix(state): heal session_model_usage PK unconditionally to restore token/cost accounting	2026-07-31 23:18:12 -07:00
stress	…
tools	fix(tools): validate timeout, reject whitespace old_string, narrow /private/var block	2026-08-01 15:41:21 -07:00
tui_gateway	fix(gateway): only follow settles into same-repo worktrees; never override an explicit cwd	2026-08-01 10:51:30 -07:00
website	fix(skills-hub): include owner in ClawHub source URLs and add retry on 429 (#51236)	2026-07-31 22:33:11 -07:00
__init__.py	…
conftest.py	test(tui_gateway): make the tui gateway suite order-independent	2026-07-29 21:30:53 -07:00
run_interrupt_test.py	…
test_account_usage.py	…
test_atomic_replace_symlinks.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_audio_playback_guard.py	fix(tests): stop the test suite speaking aloud and launching a browser	2026-07-28 14:07:21 -07:00
test_background_review_list_shapes.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_background_review_session_isolation.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_base_url_hostname.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_batch_runner_checkpoint.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_batch_runner_durability.py	refactor: dedupe fallback warning per model, drive pool-cleanup tests through real run()	2026-08-01 15:05:05 +05:30
test_bitwarden_secrets.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_cli_manual_compress.py	…
test_cli_skin_integration.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_code_skew.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_command_secret_source.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_conftest_wal_gate.py	…
test_copilot_initiator.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_credential_file_permissions.py	…
test_ctx_halving_fix.py	fix(tests): eliminate flaky/broken tests — shadow sys.path inserts, unmocked network in compressor tests, stale-SDK feishu pin guard, quadratic redact regexes	2026-07-29 15:12:28 -07:00
test_delegate_cascade_49148.py	…
test_dispatch_session_id.py	…
test_empty_model_fallback.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_empty_session_hygiene.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_env_loader_applied_homes.py	…
test_env_loader_op_bootstrap.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_env_loader_secret_sources.py	…
test_evidence_store.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_fast_safe_load.py	…
test_fts_cjk_bigram.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_gateway_streaming_nested_config.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_get_tool_definitions_cache_isolation.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_hermes_bootstrap.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_hermes_constants.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_hermes_home_profile_warning.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_hermes_logging.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_hermes_state.py	fix(gateway): scope session lists before limiting	2026-07-31 22:36:55 -07:00
test_hermes_state_compression_busy_retry.py	fix(sessions): briefly wait out a live compression lock instead of killing the turn	2026-07-31 22:35:07 -07:00
test_hermes_state_compression_locks.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_hermes_state_readonly_preflight.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_hermes_state_wal_fallback.py	fix(state): reconcile salvaged WAL fixes with current main	2026-07-29 18:13:09 -07:00
test_hermetic_side_effect_guards.py	test: guard browser and Keychain side effects suite-wide (#35404)	2026-07-29 18:55:10 -07:00
test_honcho_client_concurrency.py	…
test_honcho_client_config.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_honcho_session_context.py	…
test_honcho_startup_fail_open.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_install_autostash_conflict_recovery.py	…
test_install_commit_pin_rollback.py	fix(installer): never let a stale --commit pin roll an install backwards	2026-07-29 17:35:16 -05:00
test_install_diverged_update.py	…
test_install_lockfile_churn.py	…
test_install_macos_launcher.py	fix(install): avoid realpath-dependent uv launcher on macOS	2026-07-26 19:30:32 -07:00
test_install_no_initial_commit.py	…
test_install_ps1_ascii_only.py	…
test_install_ps1_native_stderr_eap.py	…
test_install_ps1_node_path_for_npm.py	…
test_install_ps1_python_fallback_venv.py	…
test_install_ps1_uv_powershell_host.py	…
test_install_ps1_web_server_syntax_probe.py	…
test_install_sh_acp_launcher.py	fix(install): expose hermes-agent and hermes-acp launchers on PATH	2026-07-31 22:39:11 -07:00
test_install_sh_bootstrap_marker.py	…
test_install_sh_browser_install.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_install_sh_install_method_stamp.py	…
test_install_sh_node_global_prefix.py	…
test_install_sh_pythonpath_sanitization.py	…
test_install_sh_root_fhs_uv_python_path.py	…
test_install_sh_setup_wizard_tty_probe.py	…
test_install_sh_symlink_stomp.py	…
test_install_sh_termux_network_prereqs.py	…
test_install_unmerged_index.py	…
test_ipv4_preference.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_iron_proxy.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_iron_proxy_cli.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_iron_proxy_e2e.py	…
test_journal_mode_config.py	fix(state): make journal mode canonical and behaviorally verified	2026-07-29 18:13:09 -07:00
test_lazy_session_regressions.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_live_system_guard.py	test(tui_gateway): make the tui gateway suite order-independent	2026-07-29 21:30:53 -07:00
test_live_system_guard_self_test.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_log_isolation.py	fix(tests): stop the suite writing into the operator's real Hermes logs	2026-07-29 19:53:17 -07:00
test_mcp_serve.py	fix(mcp): avoid replaying historical events on startup (#13414)	2026-08-01 13:13:30 +05:30
test_message_reactions.py	fix(state): make _row_id opt-in per consumer instead of universal	2026-07-30 00:08:28 -05:00
test_mini_swe_runner.py	…
test_minimax_model_validation.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_minimax_oauth.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_minisweagent_path.py	…
test_model_forces_max_completion_tokens.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_model_picker_scroll.py	fix(tests): eliminate flaky/broken tests — shadow sys.path inserts, unmocked network in compressor tests, stale-SDK feishu pin guard, quadratic redact regexes	2026-07-29 15:12:28 -07:00
test_model_tools.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_model_tools_async_bridge.py	…
test_no_shadowed_test_definitions.py	test: restore four silently shadowed definitions and guard against more	2026-07-31 22:35:16 -07:00
test_ollama_num_ctx.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_onepassword_secrets.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_output_cap_parsing.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_packaging_build_guard.py	…
test_packaging_metadata.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_plugin_skills.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_plugin_utils.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_process_loop_event_loop_warning.py	…
test_profile_isolation_runtime.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_project_metadata.py	Revert "remove Vercel AI Gateway and Vercel Sandbox (#33067)"	2026-07-29 19:48:37 -07:00
test_pty_keepalive_ws.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_pty_session.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_retry_utils.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_run_tests_parallel.py	fix(test-runner): native Windows venv probe + glyph-safe stdio	2026-07-29 21:30:53 -07:00
test_run_tests_parallel_stdio.py	fix(test-runner): native Windows venv probe + glyph-safe stdio	2026-07-29 21:30:53 -07:00
test_sanitize_tool_error.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_search_slow_query_log.py	…
test_session_db_read_path_split.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_session_skill_previews.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_session_workspace_binding.py	…
test_slack_thread_require_mention.py	…
test_slash_worker_watchdog.py	…
test_sql_injection.py	…
test_sqlite_lock_safe_inspection.py	fix(cli): untrack sqlite connections only after close succeeds	2026-07-31 23:18:12 -07:00
test_sqlite_wal_reset_gate.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_stale_utils_module_import.py	…
test_state_db_malformed_repair.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_subprocess_home_isolation.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_telegram_polling_progress_ptb.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_termux_all_extra_compat.py	…
test_timezone.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_tini_shim.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_toolset_distributions.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_toolsets.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_trajectory_compressor.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_trajectory_compressor_async.py	…
test_transform_llm_output_hook.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_transform_tool_result_hook.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_tui_entry_mcp_owner.py	…
test_tui_gateway_loop_noise.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_tui_gateway_queue_on_busy.py	fix(tui): preserve queued image ownership	2026-08-01 15:58:42 +05:30
test_tui_gateway_server.py	fix(tui): preserve queued image ownership	2026-08-01 15:58:42 +05:30
test_tui_gateway_ws.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_tui_mcp_late_refresh.py	…
test_utils_truthy_values.py	…
test_voice_max_recording_seconds.py	fix(voice): enforce voice.max_recording_seconds (was dead config)	2026-07-28 11:57:37 -07:00
test_wal_checkpoint_strategy.py	…
test_web_server.py	fix(web): raise uvicorn WS frame cap for Desktop file.attach	2026-07-28 19:20:14 -05:00
test_web_server_sessiondb_eventloop.py	refactor(web): extract sessions/mcp/skills/tools routes to APIRouter modules (wave 2; route-table equality verified)	2026-07-29 16:21:54 -07:00
test_windows_subprocess_no_window_flags.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_yaml_indent_consistency_31999.py	…
test_yuanbao_integration.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_yuanbao_markdown.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_yuanbao_pipeline.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_yuanbao_proto.py	test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions	2026-07-29 13:10:23 -07:00
test_yuanbao_reconnect_set_active.py	…
test_yuanbao_shutdown.py	…
test_zeroed_state_db.py	…