mirror of
https://github.com/katanemo/plano.git
synced 2026-07-23 16:51:04 +02:00
844f08bda7
* feat(routing): cache-aware routing and zero-config prompt caching
Reconcile prompt caching with intelligent routing: zero-config implicit
session affinity, cache_control preservation/injection across transforms,
cache-adjusted routing economics, and a response-driven cache-hit feedback loop.
* refactor(caching): model-aware cache markers, drop cache-aware routing
* feat(routing): session stickiness cache-regret cost gate
* refactor(routing): expose per-model input and cached rates
* fix(docker): patch libssh2 CVEs by upgrading after package install
* feat: record counterfactual route on vetoed session switches
Add opt-in session_stickiness.record_counterfactual that emits the
plano.switch.counterfactual_route OTEL attribute when the cache-regret
gate retains the previous model, capturing the route it would have taken
had the switch been allowed. Telemetry only; the candidate is never
dispatched. Includes schema, demo config, and a getting-started guide.
* refactor: group prompt-caching and session-stickiness logic into cohesive modules
Extract the two concerns interleaved in the LLM handler into dedicated
sibling modules for readability: prompt_caching.rs (cache-marker injection)
and session_stickiness.rs (session key/prefix-hash resolution, pin lookup,
cache-regret gate, and pin planning). handlers/llm/mod.rs is now a thin
orchestrator that calls them at clear phase boundaries. Behavior-preserving.
* refactor(routing): unify session routing into a cumulative switch budget
Replace observed_cache_hit + per-request threshold with time/provider-TTL
warmth and a per-session switch budget in a single session_router::route()
used by both the full-proxy and /routing decision paths.
* refactor(routing): move switch budget to routing.routing_budget and rename telemetry
* refactor(routing): drop negative-cost budget refund from routing_budget
* refactor(routing): express routing_budget as a percentage overhead cap
Replace the absolute seed_usd pool with max_overhead_pct (whole-number
percent) measured against the session's running never-switch baseline:
allow a paid switch only while cumulative switch spend stays within
max_overhead_pct% of what staying on the anchor would have cost. Track
baseline_usd and switch_spend_usd on the binding (monotonic, no refunds).
* refactor(observability): align routing-budget telemetry with the overhead cap
Rename the switch-decision reasons (within_budget/over_budget -> within_cap/
over_cap) and the session span attributes to match the percentage overhead-cap
model: budget_remaining_in_usd -> overhead_pct + switch_spend_in_usd +
baseline_in_usd, and switch threshold_in_usd -> overhead_ceiling_in_usd.
* feat(observability): emit per-request and cumulative session cost
Price each turn from the catalog rates and surface it as llm.usage.{input,
output,total}_cost_usd on the (llm) span, then accumulate into a conversation-
level session_cost_usd on the binding and emit plano.session.total_cost_in_usd
on the routing span. Cache-creation tokens are priced at the plain input rate,
and the OpenAI vs Anthropic prompt-token convention (cached folded in vs
reported separately) is captured at parse time so the cost math is correct for
both. Rates are resolved request-side since the response path is synchronous.
* refactor(routing): price the never-switch baseline against the session default model
Distinguish the session's default_model (the model it started on, i.e. what it
would have cost by never switching) from anchor_model (the model that handled
the latest request, which the session is warm on). The never-switch baseline now
grows at the default model's cached rate rather than the drifting anchor's, so
the overhead-cap denominator stays true to "% above never-switching"; switch cost
is still measured against the current anchor. Also rename estimate_context_tokens
-> actual_context_tokens (and est_context_tokens -> context_tokens) since the
router prefers the provider's real prompt-token count when the session is warm.
* feat(routing): track bounded route history and price returns to still-warm models
Record a bounded (LRU, capped) per-model visit history on the session binding
and use it to sharpen the switch-cost estimate: a return to a model still within
its cache window re-reads only the tokens appended since its last visit (at its
cached rate) instead of the whole context at the uncached rate, so an A->B->A
switch is no longer over-charged as a full re-ingest. History is carried through
the response-side refresh (refining the anchor's entry from real usage) and
cleared on prefix drift. Adds the plano.switch.candidate_warm_tokens span
attribute.
* refactor(routing): tidy test names and rename pin events to binding events
Shorten run-on test names and replace stale "pin" vocabulary in the session
binding metric (brightstaff_session_pin_events_total -> _binding_events_total),
dropping lifecycle event labels that are no longer emitted.
* feat(routing): price switch cost against uncached rates when caching is off
The overhead-cap gate previously always priced the anchor at its cached rate,
assuming a warm provider cache. When prompt caching is disabled there is no
warm cache to lose, so both the switch cost and the never-switch baseline are
now priced at the plain uncached input rate:
switch_cost = context_tokens x (candidate_uncached - anchor_uncached) / 1M.
* fix(brightstaff): bound pricing-feed fetch with timeouts and warn when session state runs without a tenant header
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(routing): validate the session overhead cap end-to-end across a multi-turn session
Co-authored-by: Cursor <cursoragent@cursor.com>
* docs(demos): fix stale pinning semantics and add routing_budget demo script
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Adil Hafeez <adil.hafeez@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
43 lines
2 KiB
Rust
43 lines
2 KiB
Rust
use std::collections::HashMap;
|
|
use std::sync::Arc;
|
|
|
|
use common::configuration::{
|
|
Agent, EffectivePromptCaching, EffectiveRoutingBudget, FilterPipeline, Listener, ModelAlias,
|
|
SpanAttributes,
|
|
};
|
|
use common::llm_providers::LlmProviders;
|
|
use tokio::sync::RwLock;
|
|
|
|
use crate::router::orchestrator::OrchestratorService;
|
|
use crate::state::StateStorage;
|
|
|
|
/// Shared application state bundled into a single Arc-wrapped struct.
|
|
///
|
|
/// Instead of cloning 8+ individual `Arc`s per connection, a single
|
|
/// `Arc<AppState>` is cloned once and passed to the request handler.
|
|
pub struct AppState {
|
|
pub orchestrator_service: Arc<OrchestratorService>,
|
|
pub model_aliases: Option<HashMap<String, ModelAlias>>,
|
|
pub llm_providers: Arc<RwLock<LlmProviders>>,
|
|
pub agents_list: Option<Vec<Agent>>,
|
|
pub listeners: Vec<Listener>,
|
|
pub state_storage: Option<Arc<dyn StateStorage>>,
|
|
pub llm_provider_url: String,
|
|
pub span_attributes: Option<SpanAttributes>,
|
|
/// Request header whose value populates the observability `distinct_id`
|
|
/// (e.g. PostHog). Sourced from `tracing.exporters[].distinct_id_header`.
|
|
/// `None` means LLM events are captured anonymously.
|
|
pub distinct_id_header: Option<String>,
|
|
/// Shared HTTP client for upstream LLM requests (connection pooling / keep-alive).
|
|
pub http_client: reqwest::Client,
|
|
pub filter_pipeline: Arc<FilterPipeline>,
|
|
/// When false, agentic signal analysis is skipped on LLM responses to save CPU.
|
|
/// Controlled by `overrides.disable_signals` in plano config.
|
|
pub signals_enabled: bool,
|
|
/// Instance-wide automatic prompt-caching settings, resolved once from the
|
|
/// top-level `prompt_caching` config. Disabled by default (opt-in).
|
|
pub prompt_caching: EffectivePromptCaching,
|
|
/// Per-session model-switch cost gate, resolved from `routing.routing_budget`.
|
|
/// Independent of prompt caching; `None` when not configured (off by default).
|
|
pub routing_budget: Option<EffectiveRoutingBudget>,
|
|
}
|