mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-26 01:01:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

fix(opencode): derive api_mode from target model, not stale config default (#15106)

Browse source 
/model kimi-k2.6 on opencode-zen (or glm-5.1 on opencode-go) returned OpenCode's
website 404 HTML page when the user's persisted model.default was a Claude or
MiniMax model. The switched-to chat_completions request hit
https://opencode.ai/zen (or /zen/go) with no /v1 suffix.

Root cause: resolve_runtime_provider() computed api_mode from
model_cfg.get('default') instead of the model being requested. With a Claude
default, it resolved api_mode=anthropic_messages, stripped /v1 from base_url
(required for the Anthropic SDK), then switch_model()'s opencode_model_api_mode
override flipped api_mode back to chat_completions without restoring /v1.

Fix: thread an optional target_model kwarg through resolve_runtime_provider
and _resolve_runtime_from_pool_entry. When the caller is performing an explicit
mid-session model switch (i.e. switch_model()), the target model drives both
api_mode selection and the conditional /v1 strip. Other callers (CLI init,
gateway init, cron, ACP, aux client, delegate, account_usage, tui_gateway) pass
nothing and preserve the existing config-default behavior.

Regression tests added in test_model_switch_opencode_anthropic.py use the REAL
resolver (not a mock) to guard the exact Quentin-repro scenario. Existing tests
that mocked resolve_runtime_provider with 'lambda requested:' had their mock
signatures widened to '**kwargs' to accept the new kwarg.
This commit is contained in:
Teknium 2026-04-24 04:58:46 -07:00 • committed by GitHub
parent 7634c1386f
commit 1eb29e6452
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 160 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/hermes_cli/test_ollama_cloud_auth.py
View file

@ -518,7 +518,7 @@ class TestSwitchModelDirectAliasOverride:
monkeypatch.setattr(
"hermes_cli.runtime_provider.resolve_runtime_provider",
lambda requested: {"api_key": "", "base_url": "", "api_mode": "openai_compat", "provider": "custom"},
lambda **kwargs: {"api_key": "", "base_url": "", "api_mode": "openai_compat", "provider": "custom"},
)
monkeypatch.setattr("hermes_cli.models.validate_requested_model",
@ -544,7 +544,7 @@ class TestSwitchModelDirectAliasOverride:
lambda raw, prov: ("custom", "local-model", "local"))
monkeypatch.setattr(
"hermes_cli.runtime_provider.resolve_runtime_provider",
lambda requested: {"api_key": "", "base_url": "", "api_mode": "openai_compat", "provider": "custom"},
lambda **kwargs: {"api_key": "", "base_url": "", "api_mode": "openai_compat", "provider": "custom"},
)
monkeypatch.setattr("hermes_cli.models.validate_requested_model",
lambda *a, **kw: {"accepted": True, "persist": True, "recognized": True, "message": None})