teknium1 d7a4065568 perf(local-endpoints): disk L2 for server-type + ollama ctx probes, faster timeouts ...

Local-model users paid a fresh probe waterfall on EVERY CLI cold start
inside AIAgent.__init__: detect_local_server_type (up to 4 HTTP GETs,
2s timeout each on a hung server) + /api/show (3s timeout). The
existing caches were in-process only, so back-to-back invocations
(chat -q, cron ticks, subagents) re-paid the network every time.

- New 300s-TTL disk L2 at HERMES_HOME/cache/local_endpoint_probes.json
  for detect_local_server_type verdicts and query_ollama_num_ctx
  results. Only SUCCESSFUL probes persist (a down server never pins a
  negative verdict); stale entries pruned on write; corrupted cache
  degrades to a miss; atomic writes. 300s is strictly fresher than the
  1h in-process TTL that already accepts server-swap staleness.
- models.dev fetch timeout 15 -> (5, 10) connect/read tuple: a
  blackholed connect stalled the first-turn critical path 15s; now
  fails in 5s (matches the OpenRouter fetch convention, #46620).
- _auto_detect_local_model timeout 5 -> (2, 3): runs inside
  _get_model_config() at startup against a LOCAL endpoint; a hung local
  server cost 5s before the banner.

E2E (real HTTP server, two fresh subprocesses, isolated HERMES_HOME):
proc1 = 2 HTTP hits, proc2 = 0 HTTP hits, identical results
(ollama/131072), probe wall 74.5 -> 35.5 ms. 222 targeted tests green
incl. 9 new disk-L2 contract tests.

2026-07-29 10:52:13 -07:00

..

dashboard_auth

fix: route stray HERMES_HOME hardcodes through get_hermes_home() (profile + native-Windows safety)

2026-07-29 09:33:48 -07:00

observability

fix(observability): gate export on subscriber flush

2026-07-28 12:08:10 -07:00

proxy

rip out brew + pip/PyPI wheel support (#68217)

2026-07-22 16:51:01 -04:00

subcommands

Merge remote-tracking branch 'origin/main' into feat/gateway-health-diagnostics-monitoring

2026-07-29 15:37:14 +00:00

__init__.py

chore: release v0.19.0 (2026.7.20) (#68175)

2026-07-20 11:35:21 -07:00

_early_recovery.py

fix(ssl): detect and repair a missing certifi cacert.pem via existing venv-repair infra

2026-07-24 15:53:38 -07:00

_parser.py

feat: raise default tool-calling iteration limit from 90 to 500

2026-07-26 12:54:45 -07:00

_scan_venv_blockers.py

fix(desktop): surface external venv update blockers

2026-07-28 14:47:36 -07:00

_subprocess_compat.py

fix(git): never block internal git calls on credential prompts

2026-07-28 17:34:21 -07:00

active_sessions.py

fix(sessions): claim the cap slot on first turn, not on open

2026-07-28 12:11:52 -05:00

agent_import.py

refactor: extract atomic_write_text to utils.py; fix write-failure error handling

2026-07-29 16:49:07 +05:30

approval_mode.py

feat(approvals): add cross-surface mode command

2026-07-26 21:13:03 -07:00

approvals_suggest.py

feat(approvals): hermes approvals suggest — mine approval history into allowlist proposals

2026-07-26 17:49:03 -07:00

auth_commands.py

fix(auth): make xAI OAuth pools multi-account resilient

2026-07-17 11:37:25 +05:30

auth.py

refactor: single shared Retry-After parser

2026-07-29 10:13:50 -07:00

azure_detect.py

fix(security): secure Azure catalog probes

2026-07-11 12:28:55 +05:30

backup.py

fix(state): stop cancelling our own POSIX locks on live SQLite databases

2026-07-25 21:44:43 -07:00

banner.py

perf(banner): scope startup update-check fetch to origin/main

2026-07-29 10:09:14 -07:00

blueprint_cmd.py

refactor(cron): rebrand Cron Recipes -> Automation Blueprints

2026-06-11 10:49:47 -07:00

browser_connect.py

fix: /browser connect times out when another app squats the CDP port

2026-07-18 02:49:28 -07:00

build_info.py

…

bundles.py

…

callbacks.py

feat(clarify): add multi-select (checkbox) support to clarify tool

2026-07-26 17:46:55 -07:00

checkpoints.py

fix(checkpoints): bind an empty orphan preview to an empty deletion allowlist

2026-07-24 16:01:06 -07:00

claw.py

fix: add explicit UTF-8 encoding to all subprocess text=True calls (#53428)

2026-07-24 11:45:57 -07:00

cli_agent_setup_mixin.py

fix(tui,cli): render a resumed interrupted turn as an event

2026-07-28 03:54:25 -05:00

cli_billing_mixin.py

feat(cli): plan catalog on Free + plan= deep link + top-up/auto-refill copy split (#68689)

2026-07-22 08:11:09 +05:30

cli_commands_mixin.py

fix(cli): stop hard-wrapping streamed paragraphs; prefer OSC 52 over SSH

2026-07-29 08:42:16 -07:00

cli_output.py

…

clipboard.py

fix(cli): stop hard-wrapping streamed paragraphs; prefer OSC 52 over SSH

2026-07-29 08:42:16 -07:00

codex_models.py

fix(codex): send ChatGPT-Account-Id on /models probes

2026-07-21 05:27:13 -07:00

codex_runtime_plugin_migration.py

…

codex_runtime_switch.py

refactor(codex-runtime): tidy reapply-migration control flow

2026-07-01 23:51:54 +05:30

colors.py

…

commands.py

feat(voice): add "Hey Hermes" wake word to start a hands-free session

2026-07-28 07:56:45 -07:00

completion.py

…

config_defaults.py

fix(voice): full-duplex agent-turn listener — interrupt by voice during generation AND playback

2026-07-29 10:08:53 -07:00

config_migrations.py

refactor: table-driven config migration registry (17 if-blocks → (version, fn) table, byte-identical semantics)

2026-07-29 10:14:32 -07:00

config.py

refactor: table-driven config migration registry (17 if-blocks → (version, fn) table, byte-identical semantics)

2026-07-29 10:14:32 -07:00

console_engine.py

rip out brew + pip/PyPI wheel support (#68217)

2026-07-22 16:51:01 -04:00

container_boot.py

fix(gateway): detect and report unclean shutdowns via lifecycle ledger (NS-608)

2026-07-28 22:41:09 -07:00

context_switch_guard.py

fix(cli): honor custom_providers in preflight shrink warning

2026-07-22 21:17:21 -07:00

copilot_auth.py

fix: add explicit UTF-8 encoding to all subprocess text=True calls (#53428)

2026-07-24 11:45:57 -07:00

credential_lifecycle.py

fix(credentials): unified provider key delete/update across .env, auth.json, config.yaml (#67213)

2026-07-19 03:02:21 -07:00

cron.py

feat(cron): user-owned model pins + cron.model fleet default

2026-07-28 11:52:47 -07:00

curator.py

fix(curator): make the autonomous write policy consistent (#67140)

2026-07-25 19:27:17 -07:00

curses_ui.py

fix(models): match bare Kimi Coding k3 when searching kimi

2026-07-26 21:22:40 -07:00

dashboard_register.py

fix(cli): correct stale hermes auth login nous hints to hermes auth add nous (#53929)

2026-06-27 21:30:37 -07:00

debug.py

fix: remove dead f-string prefixes via ruff F541 (216 sites) (#52336)

2026-07-05 13:42:46 -07:00

default_soul.py

fix(soul): installers seed the real default persona, upgrade legacy empty templates (#52246)

2026-06-24 18:56:26 -07:00

dep_ensure.py

fix(security): centralize credential-safe subprocess env (#29157)

2026-06-27 20:45:31 -07:00

diagnostics_upload.py

feat(debug): drop dead confirm step from --nous upload (stateless NAS)

2026-06-30 17:29:23 -07:00

dingtalk_auth.py

refactor(setup): route dependency installs through the canonical uv→pip→ensurepip ladder

2026-07-07 04:09:35 -07:00

doctor.py

fix(doctor): resolve managed/legacy agent-browser dirs PATHEXT-aware

2026-07-29 00:16:21 -07:00

dump.py

revert: PR #72817 — session activity watchdog, stall notify, compress timeout

2026-07-28 00:15:00 +05:00

env_loader.py

perf(config): one raw config.yaml parse per process instead of 3-4

2026-07-29 10:32:25 -07:00

fallback_cmd.py

refactor(fallback): single owner for backend identity and failure-scoped skips

2026-07-26 23:41:54 -07:00

fallback_config.py

fix(auth): honor per-entry key_env when resolving fallback providers

2026-07-16 07:19:36 -07:00

focus_view.py

feat(cli): /focus — reduced-output view with hidden-line recovery and status indicator

2026-07-26 18:10:34 -07:00

gateway_enroll.py

feat(gateway): generic OIDC client-credentials relay provisioning (NAS-free) (#60730)

2026-07-08 16:55:32 +10:00

gateway_windows.py

fix(update): migrate legacy pythonw Windows gateway launchers to the hidden-console design

2026-07-26 17:50:54 -07:00

gateway.py

fix(setup): stop asking about self-configuring platform knobs

2026-07-26 08:43:24 -07:00

goals.py

fix(goals): auto-pause goal loop on consecutive transport failures

2026-07-20 05:38:25 -07:00

gui_uninstall.py

…

hooks.py

Reapply "feat(observability): integrate NeMo Relay runtime and shared metrics"

2026-07-27 21:10:51 -07:00

init_command.py

feat(cli): /init — generate or update AGENTS.md from a project scan

2026-07-26 17:46:29 -07:00

input_sanitize.py

fix(input): strip bracketed-paste leaks before prompt persistence (#62557)

2026-07-15 07:39:42 -07:00

inventory.py

feat(picker): derive a newest-per-lab featured shortlist from models.dev

2026-07-28 03:52:33 -05:00

journey.py

fix(cli): render /journey color instead of leaking raw ANSI

2026-07-01 16:25:48 -05:00

kanban_db.py

Reapply "feat(observability): integrate NeMo Relay runtime and shared metrics"

2026-07-27 21:10:51 -07:00

kanban_decompose.py

fix(auxiliary): route direct-create aux callers through call_llm (#65029)

2026-07-15 07:39:17 -07:00

kanban_diagnostics.py

fix(kanban): clear failure/crash diagnostics while a retry is in flight

2026-07-09 16:13:59 -05:00

kanban_specify.py

fix(auxiliary): route direct-create aux callers through call_llm (#65029)

2026-07-15 07:39:17 -07:00

kanban_swarm.py

refactor(kanban): fold worker/orchestrator skills into injected guidance (#50473)

2026-06-21 17:06:48 -07:00

kanban.py

fix(kanban): cover remaining add_notify_sub call sites for chat_type (#56580)

2026-07-26 13:42:33 -07:00

lifecycle.py

Reapply "feat(observability): integrate NeMo Relay runtime and shared metrics"

2026-07-27 21:10:51 -07:00

logs.py

fix: remove dead f-string prefixes via ruff F541 (216 sites) (#52336)

2026-07-05 13:42:46 -07:00

main.py

perf(config): one raw config.yaml parse per process instead of 3-4

2026-07-29 10:32:25 -07:00

managed_scope.py

fix(managed-scope): honor managed scope in all standalone config loaders

2026-06-19 07:46:33 -07:00

managed_uv.py

perf(update): cut redundant network + subprocess work from hermes update

2026-07-29 10:16:44 -07:00

mcp_catalog.py

fix(git): never block internal git calls on credential prompts

2026-07-28 17:34:21 -07:00

mcp_config.py

fix(mcp): make Figma remote OAuth work via DCR allowlist defaults

2026-07-28 00:53:16 -05:00

mcp_picker.py

…

mcp_security.py

fix(security): close hermes-0day MCP-persistence attack surface

2026-06-21 19:05:27 -07:00

mcp_startup.py

fix(mcp): propagate profile HERMES_HOME override into shared discovery owner; restore stdio startup + WSTransport tests

2026-07-26 14:14:03 -07:00

memory_oauth.py

feat(memory): Honcho OAuth connect — desktop and CLI flows + token refresh (#44335)

2026-06-22 19:16:47 -05:00

memory_setup.py

fix: route memory-provider dep installs through lazy_deps durable target

2026-07-28 22:40:33 -07:00

middleware.py

Reapply "feat(observability): integrate NeMo Relay runtime and shared metrics"

2026-07-27 21:10:51 -07:00

migrate.py

…

moa_cmd.py

feat(moa): add reference model toggles

2026-07-23 18:11:57 -07:00

moa_config.py

feat(moa): default advisor fanout to user_turn — the cheapest cadence

2026-07-23 21:07:18 -07:00

model_catalog.py

feat(models): catalog-labeled silent default — GLM-5.2 marked "default": true in the model catalog

2026-07-15 00:10:31 -07:00

model_cost_guard.py

fix(model): require confirmation for expensive model selections

2026-06-10 00:24:06 -07:00

model_normalize.py

fix(model): don't strip alias-derived prefixes for the custom provider bucket

2026-07-27 19:32:12 +05:30

model_search.py

fix(picker): fold live bare k3 wire id into curated kimi-k3 row

2026-07-26 21:22:40 -07:00

model_setup_flows.py

fix: extend pool-credential resolution to Bedrock API-key flow

2026-07-29 10:56:19 +05:30

model_switch.py

nous portal anthropic wire

2026-07-27 11:53:48 -04:00

models.py

fix(lmstudio): respect applied runtime context

2026-07-29 02:19:13 +05:30

nous_account.py

feat(billing): /credits command — balance + portal top-up handoff (#44776)

2026-06-12 08:51:10 +00:00

nous_auth_keepalive.py

fix Nous auth refresh for idle agents

2026-06-21 22:43:48 -07:00

nous_billing.py

refactor: single shared Retry-After parser

2026-07-29 10:13:50 -07:00

nous_subscription.py

fix(desktop): honest browser-backend readiness + explicit backend activation + full OpenAI TTS voice/model options

2026-07-28 23:52:49 -07:00

onepassword_secrets_cli.py

refactor: single build_subprocess_env() factory for all child-process spawns (profile + secret-scrub single owner)

2026-07-29 10:14:11 -07:00

oneshot.py

feat(clarify): add multi-select (checkbox) support to clarify tool

2026-07-26 17:46:55 -07:00

pairing.py

…

partial_compress.py

feat(commands): /compact alias + --preview/--dry-run flags for /compress (#3243 salvage)

2026-07-02 05:10:31 -07:00

pets.py

feat(pets): generation RPCs, non-blocking gallery + gateway plumbing

2026-06-24 13:48:38 -05:00

platforms.py

…

plugins_cmd.py

fix(git): never block internal git calls on credential prompts

2026-07-28 17:34:21 -07:00

plugins.py

Reapply "feat(observability): integrate NeMo Relay runtime and shared metrics"

2026-07-27 21:10:51 -07:00

portal_cli.py

fix(auth): use refresh-free Nous status snapshot on read-only display paths

2026-07-28 22:42:19 -07:00

profile_describer.py

fix(auxiliary): route direct-create aux callers through call_llm (#65029)

2026-07-15 07:39:17 -07:00

profile_distribution.py

fix(git): never block internal git calls on credential prompts

2026-07-28 17:34:21 -07:00

profiles.py

fix: add encoding="utf-8" to Path.write_text() calls (P1)

2026-07-24 17:10:39 -07:00

projects_cmd.py

feat(projects): add per-profile project store

2026-06-25 16:40:26 -05:00

projects_db.py

feat(desktop): configure repository discovery (supersedes #67630) (#68642)

2026-07-21 10:09:31 -04:00

prompt_size.py

fix(prompt-size): include names-only skills in breakdown

2026-07-26 18:06:21 -07:00

provider_catalog.py

feat(moa): expose MoA presets as selectable virtual models (#46081)

2026-06-25 13:52:06 -07:00

providers.py

fix: restore zero-arg fetch_models_dev call on default paths

2026-07-29 17:13:48 +05:30

proxy_cli.py

Reapply "Merge pull request #30179 from NousResearch/feat/iron-proxy"

2026-07-24 09:49:00 -07:00

psutil_android.py

…

pt_input_extras.py

…

pty_bridge.py

refactor: single build_subprocess_env() factory for all child-process spawns (profile + secret-scrub single owner)

2026-07-29 10:14:11 -07:00

pty_session.py

feat(pty): periodic reaper wired into dashboard lifespan

2026-07-07 15:15:37 -07:00

relaunch.py

revert(windows): roll back terminal-popup PRs #53791 #53810 #53829 (#53853)

2026-06-27 15:59:00 -07:00

route_identity.py

refactor: fold simplify-code review findings

2026-07-29 17:13:48 +05:30

runtime_provider.py

perf(local-endpoints): disk L2 for server-type + ollama ctx probes, faster timeouts

2026-07-29 10:52:13 -07:00

secret_prompt.py

feat(memory): improve OpenViking setup UX

2026-06-17 01:04:26 +08:00

secrets_cli.py

refactor: single build_subprocess_env() factory for all child-process spawns (profile + secret-scrub single owner)

2026-07-29 10:14:11 -07:00

security_advisories.py

…

security_audit_startup.py

fix: route stray HERMES_HOME hardcodes through get_hermes_home() (profile + native-Windows safety)

2026-07-29 09:33:48 -07:00

security_audit.py

…

send_cmd.py

fix(managed-scope): honor managed scope in config→env bridges too

2026-06-19 07:46:33 -07:00

service_manager.py

fix(hermes_cli): drop privileges before clearing s6-log lock

2026-07-27 19:19:01 +05:30

session_export_html.py

fix(session-export): escape html tool call names

2026-07-09 19:54:02 -07:00

session_export_md.py

feat(sessions): full prune-filter set + --redact on sessions export

2026-07-07 12:36:41 -07:00

session_export.py

feat: add prompt-only session export

2026-07-07 13:29:58 -07:00

session_filters.py

fix(sessions): preserve recently active sessions during pruning

2026-07-26 19:30:21 -07:00

session_listing.py

feat(gateway): add /sessions search <query> (#57685)

2026-07-03 13:44:00 -07:00

session_recap.py

fix(cli): sanitize terminal escapes when replaying stored history (/resume recap, /status recap)

2026-07-17 04:53:38 -07:00

session_recovery.py

fix(sessions): verify fully reconstructed recovery

2026-07-26 23:34:29 -07:00

setup_hidden_env.py

fix(setup): stop asking about self-configuring platform knobs

2026-07-26 08:43:24 -07:00

setup_whatsapp_cloud.py

fix(whatsapp-cloud): review follow-ups for #43921

2026-06-11 07:51:01 -07:00

setup.py

fix(setup): tolerate feature dicts without an stt entry in the STT status line

2026-07-29 00:20:50 -07:00

skills_config.py

fix(cli): normalize malformed skills config in get_disabled_skills (#61797)

2026-07-09 19:57:54 -07:00

skills_hub.py

refactor: remove the claude-marketplace skill source (redundant Marketplace hub tab)

2026-07-28 23:16:27 -07:00

skin_cmd.py

feat(themes): hermes skin set — deterministic one-color tweak, bg untouched

2026-07-21 21:00:43 -05:00

skin_engine.py

feat(themes): dedicated code-syntax palette keys

2026-07-21 21:00:43 -05:00

slack_cli.py

fix: route stray HERMES_HOME hardcodes through get_hermes_home() (profile + native-Windows safety)

2026-07-29 09:33:48 -07:00

sqlite_runtime.py

fix(runtime): repair vulnerable managed SQLite builds (E-949)

2026-07-24 16:00:03 -07:00

sqlite_safe_read.py

fix(sessions): close the snapshot check/use race and guard damaged state_meta

2026-07-25 23:05:30 -07:00

sqlite_util.py

feat(projects): add per-profile project store

2026-06-25 16:40:26 -05:00

status.py

fix(auth): use refresh-free Nous status snapshot on read-only display paths

2026-07-28 22:42:19 -07:00

stdio.py

…

suggestions_cmd.py

fix: remove dead f-string prefixes via ruff F541 (216 sites) (#52336)

2026-07-05 13:42:46 -07:00

telegram_managed_bot.py

…

timeouts.py

…

tips.py

feat: raise default tool-calling iteration limit from 90 to 500

2026-07-26 12:54:45 -07:00

tools_config.py

fix: pin cua-driver refresh to the release check-update confirmed

2026-07-29 09:02:19 -07:00

toolset_validation.py

fix(config): surface invalid platform_toolsets instead of silently dropping tools (#38798)

2026-06-26 14:07:43 +05:30

uninstall.py

fix(install): install a hermes-acp launcher onto PATH

2026-07-28 11:53:12 -07:00

urllib_security.py

fix(security): order sanitizer after installed hooks

2026-07-11 12:28:55 +05:30

voice.py

fix(voice): spoken barge-in works on every TTS playback path (CLI + gateway/desktop backends)

2026-07-29 08:24:00 -07:00

web_git.py

fix(git): never block internal git calls on credential prompts

2026-07-28 17:34:21 -07:00

web_models.py

refactor: extract web_server Pydantic models to web_models.py (pure schema move)

2026-07-29 10:15:07 -07:00

web_server.py

Merge pull request #74033 from NousResearch/jb/session-detail-profile-stamp

2026-07-29 12:39:09 -05:00

webhook.py

fix: repair sweep fallout — duplicate encoding kwargs, non-subprocess call sites, kwarg-snapshot tests

2026-07-24 11:45:57 -07:00

win_pty_bridge.py

refactor: single build_subprocess_env() factory for all child-process spawns (profile + secret-scrub single owner)

2026-07-29 10:14:11 -07:00

windows_ssh_runtime.py

fix(windows): sweep remaining unguarded text-mode subprocess sites codebase-wide

2026-07-24 11:45:57 -07:00

write_approval_commands.py

refactor(memory,skills): replace tri-state write_mode with boolean write_approval (default off) (#43354)

2026-06-09 23:21:14 -07:00

xai_retirement.py

fix(config): guard xai migration writer + drop gratuitous annotation

2026-07-05 23:00:34 +05:30