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:
Teknium 2026-05-09 14:47:00 -07:00 committed by GitHub
parent b349ae1e4c
commit c7f0aab949
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 222 additions and 0 deletions

16
cli.py
View file

@ -2473,6 +2473,20 @@ class HermesCLI:
self._providers_order = pr.get("order")
self._provider_require_params = pr.get("require_parameters", False)
self._provider_data_collection = pr.get("data_collection")
# OpenRouter Pareto Code router knob — coding-score floor (0.0-1.0).
# Only applied when model.model == "openrouter/pareto-code".
# Empty string / None / out-of-range = unset (let OR pick strongest coder).
_or_cfg = CLI_CONFIG.get("openrouter", {}) or {}
_raw_score = _or_cfg.get("min_coding_score")
self._openrouter_min_coding_score: Optional[float] = None
if _raw_score not in (None, ""):
try:
_f = float(_raw_score)
if 0.0 <= _f <= 1.0:
self._openrouter_min_coding_score = _f
except (TypeError, ValueError):
pass
# Fallback provider chain — tried in order when primary fails after retries.
# Supports new list format (fallback_providers) and legacy single-dict (fallback_model).
@ -4031,6 +4045,7 @@ class HermesCLI:
provider_sort=self._provider_sort,
provider_require_parameters=self._provider_require_params,
provider_data_collection=self._provider_data_collection,
openrouter_min_coding_score=self._openrouter_min_coding_score,
session_id=self.session_id,
platform="cli",
session_db=self._session_db,
@ -7249,6 +7264,7 @@ class HermesCLI:
provider_sort=self._provider_sort,
provider_require_parameters=self._provider_require_params,
provider_data_collection=self._provider_data_collection,
openrouter_min_coding_score=self._openrouter_min_coding_score,
fallback_model=self._fallback_model,
)
# Silence raw spinner; route thinking through TUI widget when no foreground agent is active.