Composite Routing¶
Routing algorithms composed together. One sets the configuration of another and hands off, so each algorithm runs where its evidence is strongest. The composition is not restricted to a tree: sequential, conditional, and turn-boundary shapes all fit the same route type.
What exists today¶
One pairing: a classifier sets the tier a stage router falls open to when
its own signals are not confident. The stage router's picker mode is unchanged,
and so is how it scores signals, escalates, and de-escalates. Both algorithms and the
relationship between them are fixed, and the configuration below names them
directly rather than composing arbitrary algorithms.
The classifier can use an LLM judge or a decision model. A decision model is configured through a decision client and target, separately from the capable and efficient completion targets.
The general form, where any algorithm can target another and set its configuration, is the direction rather than the current behaviour. Expect this route's configuration to change as more pairings are added.
Configuration¶
[routes.switchyard]
id = "switchyard"
type = "composite"
[routes.switchyard.classifier]
target = "judge"
base_threshold = 0.5
classify_trigger = "user_turn"
[routes.switchyard.stage]
capable_target = "strong"
efficient_target = "weak"
confidence_threshold = 0.5
[routes.switchyard.stage.tool_semantics]
observe = ["lookup_customer"]
mutate = ["update_inventory"]
plan = ["create_research_plan"]
new = ["send_message"]
[routes.switchyard.classifier] is required and takes the stage_router classifier fields.
classify_trigger sets how often the judge runs: user_turn re-picks the tier
whenever the user speaks, new_session picks once and holds it.
[routes.switchyard.stage] takes the stage settings, but accepts neither picker
nor a second classifier. The outer classifier supplies the default tier.
Custom tool_semantics remain stage-local and have the same additive behavior as
on a standalone stage route.
Decision model classifier¶
Use a decision target as the classifier. Keep the stage block above and replace its LLM classifier settings with:
[decision_clients.decisions]
format = "system_one"
endpoint = "https://openrouter.ai/api/alpha/decisions"
api_key_env = "OPENROUTER_API_KEY"
timeout_ms = 5000
[decision_targets.judge]
id = "inception/mercury-decide:free"
decision_client = "decisions"
[routes.switchyard.classifier]
target = "judge"
classify_trigger = "user_turn"
[routes.switchyard.classifier.decision]
cutoff = 0.4
candidates = { a = "strong", b = "weak" }
evidence = { description = "Add task-relevant evidence comparing a and b." }
Both candidates must be completion targets. The judge must be a decision target.
The classifier selects capable when probabilities.advantage exceeds cutoff.
Calibrate the cutoff for your tasks and models. Omit LLM-only settings such as
base_threshold, threshold_step and prompt when using a decision model.
On judge failure, the default is to retain the last classified tier or use
efficient for a new session. Set classifier.fail_open = false to return the error.
Sessions¶
The tier is retained per session, so send x-switchyard-session-id and each
conversation keeps its own. A client that sends no session ID can set
classifier.message_hash_fallback = true, which keys on the first user message
instead. Conversations that open with the same text then share a tier.
Example use¶
An interactive coding agent in auto-mode. The classifier reads the user turn and picks the tier. The stage router runs the tool execution loop on its own signals until the next user turn.