mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-18 04:41:56 +00:00
feat(openrouter): wire Pareto Code router with min_coding_score knob (#22838)
Pick openrouter/pareto-code as your model and OpenRouter auto-routes each
request to the cheapest model meeting your coding-quality bar (ranked by
Artificial Analysis). The new openrouter.min_coding_score config key (0.0-1.0,
default 0.65) tunes the floor.
- hermes_cli/models.py: add openrouter/pareto-code to OPENROUTER_MODELS so
it shows up in the picker with a description
- hermes_cli/config.py: add openrouter.min_coding_score (default 0.65 — lands
on a mid-tier coder on the current Pareto frontier)
- plugins/model-providers/openrouter: emit extra_body.plugins =
[{id: pareto-router, min_coding_score: X}] when model is openrouter/pareto-code
AND the score is a valid float in [0.0, 1.0]
- agent/transports/chat_completions.py: same emission on the legacy flag
path (when no provider profile is loaded)
- run_agent.py: openrouter_min_coding_score kwarg + storage; plumbed into
both build_kwargs() invocations and the context-summary extra_body path
- cli.py: read openrouter.min_coding_score once at init, validate float in
[0,1], pass to AIAgent constructions (CLI + background-task paths)
- cron/scheduler.py, batch_runner.py, tools/delegate_tool.py,
tui_gateway/server.py: propagate the kwarg (mirrors providers_order
plumbing — subagents inherit, cron/batch read from config)
- tests: profile-level + transport-level coverage of the model gating,
unset/empty/out-of-range handling, and the legacy flag path
- docs: new 'OpenRouter Pareto Code Router' section in providers.md
Verified end-to-end against api.openrouter.ai: at score=0.65 we land on a
mid-tier coder, at omission we get the strongest. Score is silently dropped
on any model other than openrouter/pareto-code, so it's safe to leave set.
This commit is contained in:
parent
b349ae1e4c
commit
c7f0aab949
14 changed files with 222 additions and 0 deletions
|
|
@ -337,6 +337,7 @@ def _process_single_prompt(
|
|||
providers_ignored=config.get("providers_ignored"),
|
||||
providers_order=config.get("providers_order"),
|
||||
provider_sort=config.get("provider_sort"),
|
||||
openrouter_min_coding_score=config.get("openrouter_min_coding_score"),
|
||||
max_tokens=config.get("max_tokens"),
|
||||
reasoning_config=config.get("reasoning_config"),
|
||||
prefill_messages=config.get("prefill_messages"),
|
||||
|
|
@ -546,6 +547,7 @@ class BatchRunner:
|
|||
providers_ignored: List[str] = None,
|
||||
providers_order: List[str] = None,
|
||||
provider_sort: str = None,
|
||||
openrouter_min_coding_score: Optional[float] = None,
|
||||
max_tokens: int = None,
|
||||
reasoning_config: Dict[str, Any] = None,
|
||||
prefill_messages: List[Dict[str, Any]] = None,
|
||||
|
|
@ -595,6 +597,7 @@ class BatchRunner:
|
|||
self.providers_ignored = providers_ignored
|
||||
self.providers_order = providers_order
|
||||
self.provider_sort = provider_sort
|
||||
self.openrouter_min_coding_score = openrouter_min_coding_score
|
||||
self.max_tokens = max_tokens
|
||||
self.reasoning_config = reasoning_config
|
||||
self.prefill_messages = prefill_messages
|
||||
|
|
@ -873,6 +876,7 @@ class BatchRunner:
|
|||
"providers_ignored": self.providers_ignored,
|
||||
"providers_order": self.providers_order,
|
||||
"provider_sort": self.provider_sort,
|
||||
"openrouter_min_coding_score": self.openrouter_min_coding_score,
|
||||
"max_tokens": self.max_tokens,
|
||||
"reasoning_config": self.reasoning_config,
|
||||
"prefill_messages": self.prefill_messages,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue