The remote model catalog (website/static/api/model-catalog.json) now labels
exactly one entry per provider block with "default": true — z-ai/glm-5.2 for
both OpenRouter and Nous Portal. That labeled entry is the model Hermes
silently lands on when the user never picked one, and it can be rotated by
editing the manifest alone: no release needed.
- model_catalog.py: get_default_model_from_cache() reads the label from the
in-process/disk cache only — never triggers a network fetch, so hot
resolution paths (agent build, gateway session setup) stay network-free.
- models.py: get_preferred_silent_default_model() resolves catalog label
first, PREFERRED_SILENT_DEFAULT_MODEL constant second (offline/fresh
install). _PROVIDER_SILENT_DEFAULT_OVERRIDES dict replaced by
_SILENT_DEFAULT_PROVIDERS routing through the shared resolver.
fetch_openrouter_models() preserves the "default" badge through live
/v1/models refreshes so the picker shows it.
- scripts/build_model_catalog.py: generator emits the default label so
regeneration can't drop it.
- website/docs/reference/model-catalog.md: schema documents the new field.
- Salvaged from PR #61141 (@HumphreySun98): bare-provider /model switches
(/model nous) route through the cost-safe default instead of curated
entry [0].
- tests: catalog-label precedence, constant fallback, stale-label fallback,
cache-only (no network) guarantee, and a shipped-manifest contract test
pinning the labeled entry to PREFERRED_SILENT_DEFAULT_MODEL.
E2E (temp HERMES_HOME): fresh-install constant fallback, shipped-manifest
label read, release-free rotation (relabeled cache -> new default across
models.py, tui_gateway, and gateway empty-model paths) all verified.
When the current provider is a custom endpoint (custom or custom:*), the model
switch pipeline must NOT auto-switch to a native provider/OpenRouter based on a
static-catalog match. The user explicitly configured their own endpoint and the
same model name may be served there; silently rewriting model.provider destroys
their config.
- detect_static_provider_for_model(): skip the static-catalog scan when the
current provider is custom/custom:*
- switch_model() Step e: extend is_custom to cover custom:* so the
detect_provider_for_model() last-resort fallback cannot fire
Salvaged from #48351 by Elshayib (authorship preserved).
Fixes#48305
Completes the #45006 fix. PR-base commit (configured-provider routing) handles
the case where a typed model IS declared in user/custom provider config. This
commit closes the other root: when a typed model is NOT in any config and the
current provider is a soft-accepting one (openai-codex / xai-oauth), the
hidden-model soft-accept (#16172 / #19729) would accept ANY unknown name as a
hidden model — so `qwen3.5-4b` typed on a Codex-default session "succeeded" and
mislabeled the provider as "OpenAI Codex" (the exact reported symptom), then
400'd on the next turn.
Gate the soft-accept to slugs that plausibly belong to the provider's family
(openai-codex -> gpt-/codex-/o1/o3/o4; xai-oauth -> grok-). Family-shaped
unknown slugs are still soft-accepted (preserving the #16172 entitlement-gated
hidden-model intent); unrelated names are rejected with actionable guidance to
pin the right provider via `--provider <slug>` or the picker.
Adds TestCodexSoftAcceptPlausibilityGate (5 tests): unrelated names rejected on
codex/xai, family-shaped hidden slugs still accepted, real catalog models
unaffected. Verified load-bearing.
* feat(models): add deepseek-v4-flash to OpenRouter + Nous curated lists
deepseek/deepseek-v4-flash was already in the native deepseek provider
catalog but missing from the curated OpenRouter and Nous Portal picker
lists. Added it to both and regenerated the model-catalog.json manifest
(drift guard requires same-PR regeneration).
* refactor(models): trim redundant variants, group curated lists by maker
Remove claude-opus-4.7/4.6, gpt-5.4-nano, gpt-5.3-codex,
gemini-3-pro-image-preview, gemini-3.1-flash-lite-preview, grok-4.20,
and the older gemini-3-pro-preview (Nous). Reorder both OPENROUTER_MODELS
and _PROVIDER_MODELS[nous] into contiguous per-maker blocks with comment
headers. Regenerated model-catalog.json (openrouter 27, nous 20).
* feat(models): add gemini-3-pro-preview to OpenRouter + Nous curated lists
Adds google/gemini-3-pro-preview to both curated pickers (new on
OpenRouter, restored on Nous). Regenerated model-catalog.json
(openrouter 28, nous 21).
* test(models): use claude-opus-4.8 in OpenRouter fetch fixtures
The two TestFetchOpenRouterModels tests mocked a live OpenRouter
response with claude-opus-4.6 and relied on it surviving the curated-list
filter. Since 4.6 was removed from OPENROUTER_MODELS, those models got
filtered out and the recommended tag shifted. Swap the fixture to
claude-opus-4.8 (still curated, still first in the Anthropic block).
These tests asserted that hardcoded curated model lists/constants still
contained specific model strings (e.g. 'glm-5' in provider_model_ids('zai'),
exact context-length values per model key, PROVIDER_TO_MODELS_DEV entries).
They mirror a constant rather than exercise logic, so they only ever break
when models are added/retired and never catch a real bug.
Removed 22 such functions across 7 files (149 deletions, 0 additions).
Behavioral siblings are kept: live-catalog-wins, fallback ordering,
substring/longest-match resolution, normalization, credential discovery,
and probe-tier stepping all still tested.
Updates curated picker lists for both the OpenRouter fallback snapshot
(`OPENROUTER_MODELS`) and the Nous Portal list (`_PROVIDER_MODELS['nous']`).
Regenerates website/static/api/model-catalog.json via
`scripts/build_model_catalog.py` to keep the docs-hosted manifest in
sync (drift guard in `test_in_repo_lists_match_manifest`).
tests/hermes_cli/test_models.py fixtures updated — they pinned the
old model id as their live-fetch sample.
Six days after #23937 (608 fixes) the codebase had accumulated 241 new
PLR6201 violations. Same mechanical `x in (...)` → `x in {...}` fix,
same zero-risk profile: set lookup is O(1) vs O(n) for tuple and the
two are semantically equivalent for hashable scalar membership tests.
All 241 instances fixed via `ruff check --select PLR6201 --fix
--unsafe-fixes`, zero remaining. Every changed value is a hashable
scalar (str/int/None/enum/signal); no risk of unhashable runtime
errors. No behavior change.
Test plan:
- 119 files changed, +244/-244 (net zero) — exactly one-line edits
- `ruff check` clean afterward
- Compile checks pass on the largest touched files (cli.py, run_agent.py,
gateway/run.py, gateway/platforms/discord.py, model_tools.py)
- Subset broad test run on tests/gateway/ tests/hermes_cli/ tests/agent/
tests/tools/: 18187 passed, 59 pre-existing failures (verified against
origin/main with the same shape — identical failure count, identical
category — all xdist test-order flakes unrelated to this change)
Follows the same template as PR #23937 ([tracker: #23972](https://github.com/NousResearch/hermes-agent/issues/23972)).
Free-tier users were seeing 'No free models currently available.' in the
`hermes model` and post-login pickers even though qwen/qwen3.6-plus is
free on the Portal right now. Three independent breakages compounded:
1. The docs-hosted catalog manifest at website/static/api/model-catalog.json
was not regenerated when _PROVIDER_MODELS['nous'] was updated, so users
fetching the manifest got a list that didn't include qwen/qwen3.6-plus.
2. _resolve_nous_pricing_credentials() returned ('', '') on any auth blip,
collapsing get_pricing_for_provider('nous') to {} and making every
curated model fall through the free-tier filter as 'paid'.
3. Even with healthy pricing, the picker only ever showed models from the
in-repo curated list intersected with live pricing — a Portal-flagged
free model not yet in the curated list could never appear.
Changes:
- hermes_cli/models.py: new union_with_portal_free_recommendations() that
augments the curated list with Portal freeRecommendedModels entries
(with synthetic free pricing so partition keeps them). The Portal's
/api/nous/recommended-models endpoint is now the source of truth for
free-tier surfacing — old Hermes builds will see new free models
without a CLI release.
- hermes_cli/models.py: _resolve_nous_pricing_credentials() falls back to
the public inference base URL when runtime cred resolution fails.
The /v1/models endpoint exposes pricing without auth, so silently
returning {} just because a refresh token expired was wrong.
- hermes_cli/auth.py + hermes_cli/main.py: both free-tier picker call
sites call union_with_portal_free_recommendations() before partition.
- tests/hermes_cli/test_models.py: 7 tests covering union behaviour
(prepend, dedup, end-to-end with stale pricing, empty/missing/error
payloads, invalid entries).
- tests/hermes_cli/test_model_catalog.py: drift guard
TestManifestMatchesInRepoLists fails CI when _PROVIDER_MODELS['nous']
or OPENROUTER_MODELS is edited without re-running
scripts/build_model_catalog.py. Verified empirically that removing a
manifest entry triggers an assertion with an actionable error message.
Validation:
- 133/133 targeted tests pass (test_models, test_model_catalog,
test_auth_nous_provider).
- Live E2E against the real Portal:
- Stale curated list ['claude-opus','claude-sonnet','gpt-5.4'] (no
qwen) → after union: ['qwen/qwen3.6-plus', ...] →
partition(free_tier=True): selectable=['qwen/qwen3.6-plus'].
- Simulated expired refresh token → anon fetch returns 403 pricing
entries including qwen/qwen3.6-plus -> {prompt:0, completion:0}.
- ruff: clean.
- expand short model aliases like sonnet/opus via static catalogs during startup runtime resolution
- keep startup alias resolution network-free and add regression tests in models and tui gateway suites
Wire the auxiliary client (compaction, vision, session search, web extract)
to the Nous Portal's curated recommended-models endpoint when running on
Nous Portal, with a TTL-cached fetch that mirrors how we pull /models for
pricing.
hermes_cli/models.py
- fetch_nous_recommended_models(portal_base_url, force_refresh=False)
10-minute TTL cache, keyed per portal URL (staging vs prod don't
collide). Public endpoint, no auth required. Returns {} on any
failure so callers always get a dict.
- get_nous_recommended_aux_model(vision, free_tier=None, ...)
Tier-aware pick from the payload:
- Paid tier → paidRecommended{Vision,Compaction}Model, falling back
to freeRecommended* when the paid field is null (common during
staged rollouts of new paid models).
- Free tier → freeRecommended* only, never leaks paid models.
When free_tier is None, auto-detects via the existing
check_nous_free_tier() helper (already cached 3 min against
/api/oauth/account). Detection errors default to paid so we never
silently downgrade a paying user.
agent/auxiliary_client.py — _try_nous()
- Replaces the hardcoded xiaomi/mimo free-tier branch with a single call
to get_nous_recommended_aux_model(vision=vision).
- Falls back to _NOUS_MODEL (google/gemini-3-flash-preview) when the
Portal is unreachable or returns a null recommendation.
- The Portal is now the source of truth for aux model selection; the
xiaomi allowlist we used to carry is effectively dead.
Tests (15 new)
- tests/hermes_cli/test_models.py::TestNousRecommendedModels
Fetch caching, per-portal keying, network failure, force_refresh;
paid-prefers-paid, paid-falls-to-free, free-never-leaks-paid,
auto-detect, detection-error → paid default, null/blank modelName
handling.
- tests/agent/test_auxiliary_client.py::TestNousAuxiliaryRefresh
_try_nous honors Portal recommendation for text + vision, falls
back to google/gemini-3-flash-preview on None or exception.
Behavior won't visibly change today — both tier recommendations currently
point at google/gemini-3-flash-preview — but the moment the Portal ships
a better paid recommendation, subscribers pick it up within 10 minutes
without a Hermes release.
Drop _NOUS_ALLOWED_FREE_MODELS + filter_nous_free_models and its two call
sites. Whatever Nous Portal prices as free now shows up in the picker as-is
— no local allowlist gatekeeping. Free-tier partitioning (paid vs free in
the menu) still runs via partition_nous_models_by_tier.
* feat(models): hide OpenRouter models that don't advertise tool support
Port from Kilo-Org/kilocode#9068.
hermes-agent is tool-calling-first — every provider path assumes the
model can invoke tools. Models whose OpenRouter supported_parameters
doesn't include 'tools' (e.g. image-only or completion-only models)
cannot be driven by the agent loop and fail at the first tool call.
Filter them out of fetch_openrouter_models() so they never appear in
the model picker (`hermes model`, setup wizard, /model slash command).
Permissive when the field is missing — OpenRouter-compatible gateways
(Nous Portal, private mirrors, older snapshots) don't always populate
supported_parameters. Treat missing as 'unknown → allow' rather than
silently emptying the picker on those gateways. Only hide models
whose supported_parameters is an explicit list that omits tools.
Tests cover: tools present → kept, tools absent → dropped, field
missing → kept, malformed non-list → kept, non-dict item → kept,
empty list → dropped.
* refactor(acp): validate method_id against advertised provider in authenticate()
Previously authenticate() accepted any method_id whenever the server had
provider credentials configured. This was not a vulnerability under the
personal-assistant trust model (ACP is stdio-only, local-trust — anything
that can reach the transport is already code-execution-equivalent to the
user), but it was sloppy API hygiene: the advertised auth_methods list
from initialize() was effectively ignored.
Now authenticate() only returns AuthenticateResponse when method_id
matches the currently-advertised provider (case-insensitive). Mismatched
or missing method_id returns None, consistent with the no-credentials
case.
Raised by xeloxa via GHSA-g5pf-8w9m-h72x. Declined as a CVE
(ACP transport is stdio, local-trust model), but the correctness fix is
worth having on its own.
Automated dead code audit using vulture + coverage.py + ast-grep intersection,
confirmed by Opus deep verification pass. Every symbol verified to have zero
production callers (test imports excluded from reachability analysis).
Removes ~1,534 lines of dead production code across 46 files and ~1,382 lines
of stale test code. 3 entire files deleted (agent/builtin_memory_provider.py,
hermes_cli/checklist.py, tests/hermes_cli/test_setup_model_selection.py).
Co-authored-by: alt-glitch <balyan.sid@gmail.com>
check_nous_free_tier() now caches its result for 180 seconds to avoid
redundant Portal API calls during a session (auxiliary client init,
model selection, login flow all call it independently).
The TTL is short enough that an account upgrade from free to paid is
reflected within 3 minutes. clear_nous_free_tier_cache() is exposed
for explicit invalidation on login/logout.
Adds 4 tests for cache hit, TTL expiry, explicit clear, and TTL bound.
- Show pricing during initial Nous Portal login (was missing from
_login_nous, only shown in the already-logged-in hermes model path)
- Filter free models for paid subscribers: non-allowlisted free models
are hidden; allowlisted models (xiaomi/mimo-v2-pro, xiaomi/mimo-v2-omni)
only appear when actually priced as free
- Detect free-tier accounts via portal api/oauth/account endpoint
(monthly_charge == 0); free-tier users see only free models as
selectable, with paid models shown dimmed and unselectable
- Use xiaomi/mimo-v2-omni as the auxiliary vision model for free-tier
Nous users so vision_analyze and browser_vision work without paid
model access (replaces the default google/gemini-3-flash-preview)
- Unavailable models rendered via print() before TerminalMenu to avoid
simple_term_menu line-width padding artifacts; upgrade URL resolved
from auth state portal_base_url (supports staging/custom portals)
- Add 21 tests covering filter_nous_free_models, is_nous_free_tier,
and partition_nous_models_by_tier
OpenCode Zen and Go are mixed-API-surface providers — different models
behind them use different API surfaces (GPT on Zen uses codex_responses,
Claude on Zen uses anthropic_messages, MiniMax on Go uses
anthropic_messages, GLM/Kimi on Go use chat_completions).
Changes:
- Add normalize_opencode_model_id() and opencode_model_api_mode() to
models.py for model ID normalization and API surface routing
- Add _provider_supports_explicit_api_mode() to runtime_provider.py
to prevent stale api_mode from leaking across provider switches
- Wire opencode routing into all three api_mode resolution paths:
pool entry, api_key provider, and explicit runtime
- Add api_mode field to ModelSwitchResult for propagation through the
switch pipeline
- Consolidate _PROVIDER_MODELS from main.py into models.py (single
source of truth, eliminates duplicate dict)
- Add opencode normalization to setup wizard and model picker flows
- Add opencode block to _normalize_model_for_provider in CLI
- Add opencode-zen/go fallback model lists to setup.py
Tests: 160 targeted tests pass (26 new tests covering normalization,
api_mode routing per provider/model, persistence, and setup wizard
normalization).
Based on PR #3017 by SaM13997.
Co-authored-by: SaM13997 <139419381+SaM13997@users.noreply.github.com>
When typing /model deepseek-chat while on a different provider, the
model name now auto-resolves to the correct provider instead of
silently staying on the wrong one and causing API errors.
Detection priority:
1. Direct provider with credentials (e.g. DEEPSEEK_API_KEY set)
2. OpenRouter catalog match with proper slug remapping
3. Direct provider without creds (clear error beats silent failure)
Also adds DeepSeek as a first-class API-key provider — just set
DEEPSEEK_API_KEY and /model deepseek-chat routes directly.
Bare model names get remapped to proper OpenRouter slugs:
/model gpt-5.4 → openai/gpt-5.4
/model claude-opus-4.6 → anthropic/claude-opus-4.6
Salvages the concept from PR #1177 by @virtaava with credential
awareness and OpenRouter slug mapping added.
Co-authored-by: virtaava <virtaava@users.noreply.github.com>
- Renamed test method for clarity and added comprehensive tests for `SessionSource` including handling of numeric `chat_id`, missing optional fields, and invalid platforms.
- Introduced tests for session source descriptions based on chat types and names, ensuring accurate representation in prompts.
- Improved file tools tests by validating schema structures, ensuring no duplicate model IDs, and enhancing error handling in file operations.
