fix(nous): surface Portal-flagged free models in picker even when curated list is stale#24082
Merged
Conversation
…ated list is stale
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.
Contributor
🔎 Lint report:
|
| Rule | Count |
|---|---|
unresolved-attribute |
1 |
invalid-argument-type |
1 |
First entries
tests/hermes_cli/test_model_catalog.py:374: [unresolved-attribute] unresolved-attribute: Attribute `loader` is not defined on `None` in union `ModuleSpec | None`
tests/hermes_cli/test_model_catalog.py:372: [invalid-argument-type] invalid-argument-type: Argument to function `module_from_spec` is incorrect: Expected `ModuleSpec`, found `ModuleSpec | None`
✅ Fixed issues: none
Unchanged: 4305 pre-existing issues carried over.
Diagnostics are surfaced as warnings — this check never fails the build.
This was referenced May 12, 2026
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…ated list is stale (NousResearch#24082) 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.
jsboige
pushed a commit
to jsboige/hermes-agent
that referenced
this pull request
May 14, 2026
…ated list is stale (NousResearch#24082) 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.
AlexFoxD
pushed a commit
to AlexFoxD/hermes-agent
that referenced
this pull request
May 21, 2026
…ated list is stale (NousResearch#24082) 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.
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…ated list is stale (NousResearch#24082) 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.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Free-tier users see 'No free models currently available.' in
hermes modeland the post-login picker even thoughqwen/qwen3.6-plusis free on the Portal right now. Three independent breakages compound; this PR fixes all three.Root causes
website/static/api/model-catalog.jsonwas not regenerated when_PROVIDER_MODELS['nous']was updated. Users fetching the docs-hosted manifest got a list that didn't includeqwen/qwen3.6-plus._resolve_nous_pricing_credentials()returned('', '')on any auth blip →get_pricing_for_provider('nous') == {}→ every curated model fell through the free-tier filter as 'paid' → 'No free models currently available'. The/v1/modelspricing endpoint is public; gating it behind a token that may have expired was wrong.Changes
hermes_cli/models.py: newunion_with_portal_free_recommendations()augments curated list with/api/nous/recommended-modelsfreeRecommendedModelsentries, synthesizing free pricing entries so partition keeps them. Portal becomes source of truth for free-tier surfacing.hermes_cli/models.py:_resolve_nous_pricing_credentials()falls back to public inference base URL when runtime credential resolution fails.hermes_cli/auth.py+hermes_cli/main.py: both free-tier picker call sites wired through the new union helper.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 fails CI when_PROVIDER_MODELS['nous']orOPENROUTER_MODELSis edited without re-runningscripts/build_model_catalog.py.Validation
_PROVIDER_MODELSwithout rebuilding manifesttest_models,test_model_catalog,test_auth_nous_provider).