fix: preserve static custom provider models - #58453
Closed
lord-dubious wants to merge 1 commit into
Closed
Conversation
alt-glitch
added
type/bug
webdevtodayjason
added a commit
to webdevtodayjason/hermes-agent
that referenced
this pull request
Jul 4, 2026
…aces Per maintainer feedback on the interface-ideas thread: a context-engine plugin already owns the full compression policy (should_compress / compress / preflight on the ContextEngine ABC), and a ProviderProfile already owns its model catalog (models_url / fetch_models / fallback_models). Call both out explicitly — the queued PRs that patch core for these (NousResearch#58418, NousResearch#58444, NousResearch#58453) suggest contributors don't find the existing surface, which is the failure mode this guide exists to fix. Also adds both rows to the PR-shape → seam mapping table. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FWMcB7RPSYUpsXDfBgwjzM
Contributor
webdevtodayjason
added a commit
to webdevtodayjason/hermes-agent
that referenced
this pull request
Aug 3, 2026
…aces Per maintainer feedback on the interface-ideas thread: a context-engine plugin already owns the full compression policy (should_compress / compress / preflight on the ContextEngine ABC), and a ProviderProfile already owns its model catalog (models_url / fetch_models / fallback_models). Call both out explicitly — the queued PRs that patch core for these (NousResearch#58418, NousResearch#58444, NousResearch#58453) suggest contributors don't find the existing surface, which is the failure mode this guide exists to fix. Also adds both rows to the PR-shape → seam mapping table. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FWMcB7RPSYUpsXDfBgwjzM
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
3 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
[{id: ...}]rowsdiscover_models: falseContext
Some OpenAI-compatible gateways serve chat completions but do not expose a working
/modelsendpoint. In that case the desktop picker should still show the models explicitly configured underproviders:/custom_providers:rather than rendering an empty provider row.This keeps the fix in the backend inventory/model-switch path shared by Desktop, TUI, and gateway callers instead of adding a Desktop-only special case.
Test plan
venv/bin/python -m pytest -q tests/hermes_cli/test_model_switch_custom_providers.py tests/hermes_cli/test_inventory.pyvenv/bin/python -m ruff check hermes_cli/config.py hermes_cli/model_switch.py tests/hermes_cli/test_inventory.py tests/hermes_cli/test_model_switch_custom_providers.pygit diff --checkRefs #58393