common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

test(runtime_provider): lock in model-derivation precedence over stale api_mode

Browse Source 
PR #16888 swaps the opencode-zen/go resolver so that api_mode is always
re-derived from the effective model before the persisted api_mode is
consulted. That's the point of the fix — a stale anthropic_messages
from a previous minimax default must not survive a /model switch to a
chat_completions target (or vice versa) and strip /v1 from base_url.

The prior test asserted the opposite precedence — that a persisted
api_mode won over model-derived mode — and was added in #4508 to lock
in escape-hatch behavior. Under the new precedence that escape hatch
no longer exists for opencode (only for providers that genuinely
support both modes at a single endpoint — and for opencode the model
name is the unambiguous signal). Rename + invert the assertion to
document the intentional behavior change.

Refs #16878.
This commit is contained in:
Teknium
2026-04-28 01:11:22 -07:00
committed by Teknium
parent b52ceccfa8
commit 54e24f7758
1 changed files with 13 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
tests/hermes_cli/test_runtime_provider_resolution.py
View File

@@ -1170,7 +1170,18 @@ def test_opencode_go_glm_defaults_to_chat_completions(monkeypatch):
assert resolved["base_url"] == "https://opencode.ai/zen/go/v1"
def test_opencode_go_configured_api_mode_still_overrides_default(monkeypatch):
def test_opencode_go_model_derivation_beats_stale_persisted_api_mode(monkeypatch):
"""opencode-zen/go re-derive api_mode from the effective model on every
resolve, ignoring any persisted ``api_mode`` in config. Refs #16878 /
PR #16888: the persisted mode from the previous default model must not
leak across /model switches (a stale ``anthropic_messages`` on a
chat_completions target would strip /v1 from base_url and 404).
minimax-m2.5 is an Anthropic-routed model on opencode-go, so even when
the config claims ``api_mode: chat_completions`` the runtime must pick
``anthropic_messages`` — the model dictates the mode, not the stale
persisted setting.
"""
monkeypatch.setattr(rp, "resolve_provider", lambda *a, **k: "opencode-go")
monkeypatch.setattr(
rp,
@@ -1187,7 +1198,7 @@ def test_opencode_go_configured_api_mode_still_overrides_default(monkeypatch):
resolved = rp.resolve_runtime_provider(requested="opencode-go")
assert resolved["provider"] == "opencode-go"
assert resolved["api_mode"] == "chat_completions"
assert resolved["api_mode"] == "anthropic_messages"
def test_named_custom_provider_anthropic_api_mode(monkeypatch):