mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

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

10
hermes_cli/model_switch.py
View file

@ -771,7 +771,10 @@ def switch_model(
if provider_changed or explicit_provider:
try:
runtime = resolve_runtime_provider(requested=target_provider)
runtime = resolve_runtime_provider(
requested=target_provider,
target_model=new_model,
)
api_key = runtime.get("api_key", "")
base_url = runtime.get("base_url", "")
api_mode = runtime.get("api_mode", "")
@ -788,7 +791,10 @@ def switch_model(
)
else:
try:
runtime = resolve_runtime_provider(requested=current_provider)
runtime = resolve_runtime_provider(
requested=current_provider,
target_model=new_model,
)
api_key = runtime.get("api_key", "")
base_url = runtime.get("base_url", "")
api_mode = runtime.get("api_mode", "")

29
hermes_cli/runtime_provider.py
View file

@ -183,8 +183,16 @@ def _resolve_runtime_from_pool_entry(
requested_provider: str,
model_cfg: Optional[Dict[str, Any]] = None,
pool: Optional[CredentialPool] = None,
target_model: Optional[str] = None,
) -> Dict[str, Any]:
model_cfg = model_cfg or _get_model_config()
# When the caller is resolving for a specific target model (e.g. a /model
# mid-session switch), prefer that over the persisted model.default. This
# prevents api_mode being computed from a stale config default that no
# longer matches the model actually being used — the bug that caused
# opencode-zen /v1 to be stripped for chat_completions requests when
# config.default was still a Claude model.
effective_model = (target_model or model_cfg.get("default") or "")
base_url = (getattr(entry, "runtime_base_url", None) or getattr(entry, "base_url", None) or "").rstrip("/")
api_key = getattr(entry, "runtime_api_key", None) or getattr(entry, "access_token", "")
api_mode = "chat_completions"
@ -230,7 +238,7 @@ def _resolve_runtime_from_pool_entry(
api_mode = configured_mode
elif provider in ("opencode-zen", "opencode-go"):
from hermes_cli.models import opencode_model_api_mode
api_mode = opencode_model_api_mode(provider, model_cfg.get("default", ""))
api_mode = opencode_model_api_mode(provider, effective_model)
else:
# Auto-detect Anthropic-compatible endpoints (/anthropic suffix,
# Kimi /coding, api.openai.com → codex_responses, api.x.ai →
@ -724,8 +732,18 @@ def resolve_runtime_provider(
requested: Optional[str] = None,
explicit_api_key: Optional[str] = None,
explicit_base_url: Optional[str] = None,
target_model: Optional[str] = None,
) -> Dict[str, Any]:
"""Resolve runtime provider credentials for agent execution."""
"""Resolve runtime provider credentials for agent execution.
target_model: Optional override for model_cfg.get("default") when
computing provider-specific api_mode (e.g. OpenCode Zen/Go where different
models route through different API surfaces). Callers performing an
explicit mid-session model switch should pass the new model here so
api_mode is derived from the model they are switching TO, not the stale
persisted default. Other callers can leave it None to preserve existing
behavior (api_mode derived from config).
"""
requested_provider = resolve_requested_provider(requested)
custom_runtime = _resolve_named_custom_runtime(
@ -807,6 +825,7 @@ def resolve_runtime_provider(
requested_provider=requested_provider,
model_cfg=model_cfg,
pool=pool,
target_model=target_model,
)
if provider == "nous":
@ -1025,7 +1044,11 @@ def resolve_runtime_provider(
api_mode = configured_mode
elif provider in ("opencode-zen", "opencode-go"):
from hermes_cli.models import opencode_model_api_mode
api_mode = opencode_model_api_mode(provider, model_cfg.get("default", ""))
# Prefer the target_model from the caller (explicit mid-session
# switch) over the stale model.default; see _resolve_runtime_from_pool_entry
# for the same rationale.
_effective = target_model or model_cfg.get("default", "")
api_mode = opencode_model_api_mode(provider, _effective)
else:
# Auto-detect Anthropic-compatible endpoints by URL convention
# (e.g. https://api.minimax.io/anthropic, https://dashscope.../anthropic)