Restate the trust model from first principles: the OS is the only
load-bearing boundary against an adversarial LLM. Distinguish
terminal-backend isolation (sandboxes the shell tool) from
whole-process wrapping (sandboxes the agent itself, reference
deployment NVIDIA OpenShell). Name in-process components (approval
gate, output redaction, Skills Guard) as heuristics, and the class
of reports that defeat them as out of scope under this policy —
while explicitly welcoming them as regular issues or PRs.

Introduce 'agent-loaded content' as the narrow, honest commitment:
attacker-influenced input must not chain into a write the agent
later loads on its own initiative.

Strip implementation-detail enumerations (backend names, adapter
names, config keys, env vars, internal symbols) so the doc stays
evergreen as code evolves.

5 commands: quote, search, history, compare, crypto
Zero dependencies, Python stdlib only.
Supports multi-symbol queries and crypto prices.

When the Discord typing API call fails (rate limit, network error, 403),
_typing_loop returns early but the stale task remains in _typing_tasks.
Subsequent send_typing calls see the stale entry and skip, leaving no
typing indicator for the rest of the agent invocation.

Add finally block to _typing_loop to always remove the task from
_typing_tasks on exit, whether from cancellation, error, or normal
completion. This allows send_typing to create a fresh task.

3 new tests in test_discord_send.py:
- Task removed after API error
- Typing restartable after failure
- stop_typing cleans up

…er-call retry storms (NousResearch#23597)

When an auxiliary provider returns HTTP 402 (credit / payment), every
subsequent compression / title-gen / session-search / vision call still
re-tried it as the FIRST entry in the chain — burning ~1 RTT to hit 402
again, then falling back. On a long Discord/LCM session that meant dozens
of doomed 402s per minute (issue NousResearch#23570).

Add a per-process unhealthy-provider cache with a 10 min TTL. When any
caller observes a payment error against a provider, the label is marked
unhealthy and skipped by:
  * _resolve_auto Step-1 (main provider use-as-aux path)
  * _resolve_auto Step-2 (aggregator/fallback chain)
  * _try_payment_fallback (used by call_llm/acall_llm on first 402)

Skip-logs are throttled to once per minute per label so a bursty session
doesn't spam agent.log. Entries auto-expire so a topped-up account
recovers without manual intervention. The cache is in-process only by
design — multi-profile users with different keys per profile must each
hit the 402 once.

Refs NousResearch#23570

Two independent opt-in QoL toggles, both off by default.

terminal.docker_extra_args:
- List of extra flags appended verbatim to docker run after security
  defaults. Useful for adding capabilities (e.g. --cap-add SETUID) or
  other docker run options not exposed by existing config keys.
- Non-string entries are logged and skipped.
- Also available via TERMINAL_DOCKER_EXTRA_ARGS='[...]' env var.

display.timestamps:
- Appends [HH:MM] to user input bullet and the assistant response box
  header. Single hub in _format_submitted_user_message_preview()
  covers both single-line and multi-line user previews; assistant
  response label gets the timestamp at box-open time.

Closes NousResearch#1569 (timestamps).

Co-authored-by: Mibayy <Mibayy@users.noreply.github.com>

…#21818)

Declares hindsight-client as an optional dependency group [hindsight]
in pyproject.toml. This allows build-time inclusion for environments
where runtime pip install is not possible (NixOS sealed venvs, Docker,
Kubernetes).

Not included in [all] — memory providers are plugins and should be
opted into explicitly.

Install via:
  uv sync --extra hindsight
  pip install hermes-agent[hindsight]

NixOS (with extraDependencyGroups):
  services.hermes-agent.extraDependencyGroups = [ "hindsight" ];

Closes NousResearch#8873

…arch#21817)

Expose the dependency-groups parameter from python.nix through
hermes-agent.nix and the NixOS module, allowing users to opt into
pyproject.toml optional extras (e.g. hindsight, voice, matrix) that
are resolved by uv inside the sealed venv.

Unlike extraPythonPackages (which appends to PYTHONPATH and requires
collision checking), extraDependencyGroups resolves the full dependency
graph in a single uv pass — no PYTHONPATH patching, no version
conflicts, no collision risk.

When to use which:
- extraDependencyGroups: enable a pyproject.toml optional extra
- extraPythonPackages: add an external Python plugin not in pyproject.toml

Usage:
  services.hermes-agent.extraDependencyGroups = [ "hindsight" ];

Or via overlay:
  pkgs.hermes-agent.override { extraDependencyGroups = [ "hindsight" ]; }

Refs: NousResearch#8873, NousResearch#9194

…NousResearch#23633)

The container entrypoint ran `chown -R` on $HERMES_HOME every start.
`chown` strips the setgid bit (kernel security behavior), destroying
the 2770 permissions the NixOS activation script sets for group access
by hostUsers. This caused PermissionError for interactive CLI users
even though they were in the hermes group.

Replace with `find ... ! -user $UID -exec chown` which only touches
files with wrong ownership, leaving correctly-owned directories and
their permission bits intact.

Affects: container.enable + container.hostUsers + addToSystemPackages

Related: NousResearch#19795, NousResearch#19788, NousResearch#9383

Pre-stages AUTHOR_MAP for 12 new contributors whose PRs are being salvaged
in the upcoming batch:

- 1RB        (NousResearch#25462)
- ayushere   (NousResearch#25342)
- domtriola  (NousResearch#25424)
- ephron-ren (NousResearch#25358)
- freqyfreqy (NousResearch#25423)
- fu576      (NousResearch#25369)
- kfa-ai     (NousResearch#25398)
- magic524   (NousResearch#25361)
- PaTTeeL    (NousResearch#25359)
- pearjelly  (NousResearch#25388)
- raymaylee  (NousResearch#25394)
- Tianyu199509 (NousResearch#25421)

The word "worktree" (a git subcommand feature for parallel checkouts)
was used interchangeably with "repository" in the LSP docs, causing
confusion. LSP only requires a git-initialized directory, not an actual
worktree.

Fixes two instances: section "When LSP runs" and the troubleshooting
"Editing a file outside any git repo" heading.

Xiaomi MiMo emits reasoning via OpenAI's reasoning_content field and
requires reasoning_content on every assistant tool-call message when
replaying history. Without echo-back, subsequent API calls fail with
HTTP 400 — same shape as DeepSeek and Kimi/Moonshot thinking modes.

Adds _needs_mimo_tool_reasoning() detection (provider == 'xiaomi',
'mimo' in model, or xiaomimimo.com base url) and wires it into the
_needs_thinking_reasoning_pad() check.

Salvage of NousResearch#25358 by @ephron-ren (manually re-applied — original branch
was severely stale against current main).

Discord introduced message_snapshots for forwarded messages — text and
attachments live inside snap.content / snap.attachments rather than on
the parent message. _handle_message wasn't reading them, so forwards
showed up empty.

Defensively extracts snapshot text (when raw_content is empty) and
appends snapshot attachments to the working all_attachments list used
for type detection and media routing. hasattr/getattr guards keep this
safe on older discord.py installs without the field.

Salvage of NousResearch#25462 by @1RB (manually re-applied — original branch was
stale against current main).

When the auxiliary client fallback chain reaches a provider that has no
credentials configured (no API key, no pool entry), the current code
just returns (None, None) which counts toward the per-call timeout
budget on the next attempt. Mark the provider unhealthy with a short
TTL so the chain advances quickly to the next viable option.

Closes NousResearch#25384.

Salvage of NousResearch#25395 by @AllynSheep.

- _read_process_cmdline: /proc and 'ps' are unavailable on Windows,
  so process cmdline was always empty. Add psutil fallback (already
  a hard dependency used by _pid_exists in the same module).

- _record_looks_like_gateway: argv paths use backslashes on Windows
  but patterns use forward slashes/dots, so the fallback record check
  always failed. Normalize backslashes to forward slashes before
  matching.

Together these caused get_running_pid() to return None on Windows
even when the gateway process is alive, making the dashboard report
gateway as 'stopped' despite it functioning normally.

…t manager

The Feishu adapter wrapped lark-oapi's Connect() callable to inject
ping_interval/ping_timeout overrides, but made the wrapper async. The
underlying library uses Connect() as an async context manager (async
with Connect(...) as ws:), which requires the call itself to be sync
and return an AsyncContextManager — making it async meant the wrapper
was awaited eagerly and ws never bound.

Restoring the sync wrapper preserves the protocol while still injecting
the overrides.

Salvage of NousResearch#25388 by @pearjelly (manually re-applied — original branch
was severely stale against current main).

Cross-provider delegation (e.g. MiniMax parent → DeepSeek child) must not
inherit the parent's api_mode, because each provider uses a different API
surface: MiniMax uses 'anthropic_messages' while DeepSeek uses
'chat_completions'. Inheriting the wrong mode causes 404 errors.

When the effective provider differs from the parent's provider, derive
api_mode from the target provider's defaults instead (None triggers
re-derivation).

Refs: Bug NousResearch#20558, PR NousResearch#20563

…-length detection

When auxiliary.compression.provider is "auto", the compression model
reuses the main model's provider and base_url.  The main model's
context_length was correctly picking up custom_providers per-model
overrides (via _custom_providers stored during __init__), but the
auxiliary compression model's context-length detection path in
_check_compression_model_feasibility was not passing custom_providers,
causing it to skip step 0b and fall through to models.dev.

This meant that for providers like NVIDIA NIM where the user has a
per-model context_length in custom_providers (e.g. 196608 for
minimax-m2.7), the auxiliary model would use the models.dev value
(204800) instead of the user-configured one — a subtle discrepancy
that could lead to silent compression issues when the auxiliary model
doesn't actually support the detected context length.

Fix: pass self._custom_providers (already stored as an instance attr
during __init__) to the get_model_context_length() call for the
auxiliary compression model.

Background review fork redirected stdout/stderr around run_conversation()
so its iteration messages stay silent.  But the memory-provider teardown
(shutdown_memory_provider() and review_agent.close()) fired in the outer
finally block AFTER the redirect_stdout context exited — so provider
teardown prints (Honcho disconnect, Hindsight sync, etc.) leaked into
the parent terminal at end of every turn.

Moves the teardown inside the redirect_stdout scope on the success path
(and nulls review_agent so the finally safety-net skips double-shutdown).
The finally block is rewritten as an exception-path safety net that
re-opens a devnull redirect, since the original 'with' context has
already exited by the time finally runs.

Salvage of NousResearch#25342 by @ayushere (manually re-applied + merged conflict
with current main's set_thread_tool_whitelist wiring).

Add NovitaAI as a first-class provider with dedicated model selection
flow, live pricing, and authoritative context length resolution.

- Register provider in PROVIDER_REGISTRY, HERMES_OVERLAYS, and all
  alias/label maps (ID: novita, aliases: novita-ai, novitaai)
- Add dedicated _model_flow_novita() with 3-tier model list fallback:
  Novita API → models.dev → static curated list
- Fetch live pricing from /v1/models with correct unit conversion
  (input_token_price_per_m is 0.0001 USD per Mtok)
- Add Novita-specific context length resolution (step 4b) in
  get_model_context_length(), prioritized over models.dev/OpenRouter
- Register api.novita.ai in _URL_TO_PROVIDER to prevent early return
  from the custom-endpoint code path
- Add models.dev mapping (novita → novita-ai)
- Add default auxiliary model (deepseek/deepseek-v3-0324)
- Add NOVITA_API_KEY to test isolation (conftest.py)
- Update docs: providers page, env vars reference, CLI reference,
  .env.example, README, and landing page

…ntry

Follow-up to Alex-wuhu's NovitaAI provider commit. Adds:

- _pricing_cache hit/write in _fetch_novita_pricing (was missing — every
  pricing fetch was re-hitting the network), mirroring the
  fetch_ai_gateway_pricing pattern. force_refresh now also propagates
  from get_pricing_for_provider.
- TestNovitaProvider in tests/hermes_cli/test_api_key_providers.py
  covering profile load, alias resolution, registry auto-registration,
  model list parity between main.py and models.py, _URL_TO_PROVIDER,
  _PROVIDER_PREFIXES, context_size in _CONTEXT_LENGTH_KEYS, pricing
  unit conversion, and pricing cache behavior.
- AUTHOR_MAP entry for yanglongwei06@gmail.com → @Alex-yang00.

This reverts commit 3386016.

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

Removed custom provider mappings for OpenAI and related models.

Introduce _run_headless_loop(stdin=None) to process newline-delimited prompts in --no-gui mode (preserves leading/trailing spaces, skips blank lines, sets _agent_running around chat and correctly propagates interrupts/errors).

Add _finalize_run() to centralize CLI shutdown logic: mark exit, interrupt running agent, shutdown voice recorder, cleanup temp recordings, unregister callbacks, close session DB, invoke on_session_end hook for interrupted sessions, run global cleanup and print exit summary. Replace duplicated cleanup blocks by calling _finalize_run() from run() and error paths.

Tests updated: import io and pytest; new TestHeadlessRun validates headless input handling and ensures finalize is called on normal completion and on exceptions.

…xD/hermes-agent into fix/headless-mode-windows