Files
OmniRoute/open-sse/services/compression/stackedStepCore.ts
Praveen K Palaniswamy 65e81158ab fix(ollama): route models by advertised capability (#11088)
Landed with the design call resolved per the owner's pick — **option 1**: the synced store is now endpoint-agnostic (persistDiscoveredModels and managedModelImport no longer drop non-chat models at write time), and chat selectability moved to read time (auto-pool expansion in autoStrategy applies filterChatSelectableModels; the models-route projection already had its chatOnly filter). Your discovery test now passes end-to-end (3/3): /api/show capabilities persist per connection and image/embedding requests route through the advertising host.

Reconciliation notes: conflicted areas merged onto the current tip (adobe discovery import, requestedModel preflight signature, resolvedProvider fast-path coexists with the synced-route override — explicit resolution wins); carried base-red drains (#10055 memoization, #11071 test variants) dropped as already-landed; the managed-model-import exclusion test was propagated to the new contract (image/video models persist; the read filter still hides them from chat pickers — pinned by a new assertion). Full battery: 205/206 focused (the one red is a confirmed periodic-timer timing flake on the loaded devbox — 20/20 isolated), autoCombo vitest 30/30, combo suites 46/46, gates + typecheck clean.

Thank you @yourspraveen — the capability probe + routing design was right; it just needed the store contract opened up. Fixes #11087.
2026-08-23 11:45:01 -03:00

118 lines
5.2 KiB
TypeScript

/**
* Core telemetry + step-decision machinery for the stacked compression pipeline, extracted
* from `strategySelector.ts` so that god-file stays bounded. This module is a leaf: it depends
* only on the shared compression types, so it never participates in a cycle.
*
* It holds the per-run accumulator (`StackAccumulator` + `createStackAccumulator`), the TV1
* bail-out config + advance decision (`BailoutConfig` + `decideStep`), and the per-step
* telemetry fold (`mergeStackStep`). The sync/async stacked loops in `strategySelector.ts`
* consume these.
*/
import type { CompressionResult, CompressionStats } from "./types.ts";
/**
* TV1 — Opt-in bail-out configuration for the stacked pipeline.
* When enabled: a step that throws is silently skipped (verbatim kept); a step whose gain is
* below `minGainPercent` is also skipped. DEFAULT = disabled (byte-identical to pre-TV1).
*/
export interface BailoutConfig {
enabled: boolean;
/** Minimum savings percent required to advance currentBody. Default: 10. */
minGainPercent?: number;
}
/** Accumulates per-step telemetry across a stacked run (shared sync/async). */
export interface StackAccumulator {
techniques: Set<string>;
rules: Set<string>;
breakdown: NonNullable<CompressionStats["engineBreakdown"]>;
rtkRawOutputPointers: NonNullable<CompressionStats["rtkRawOutputPointers"]>;
validationWarnings: Set<string>;
validationErrors: Set<string>;
fallbackApplied: boolean;
}
export function createStackAccumulator(): StackAccumulator {
return {
techniques: new Set<string>(),
rules: new Set<string>(),
breakdown: [],
rtkRawOutputPointers: [],
validationWarnings: new Set<string>(),
validationErrors: new Set<string>(),
fallbackApplied: false,
};
}
/**
* TV1 — Pure helper that decides whether a completed step should advance `currentBody`. Called
* only when bail-out is ENABLED; the loops bypass it on the default-off path (zero cost). Returns
* `{ advance: true }` to accept the step, or `{ advance: false }` to skip it (verbatim kept).
*/
export function decideStep(
result: CompressionResult,
bailout: BailoutConfig
): { advance: boolean } {
if (!result.compressed) return { advance: false };
// Clamp: a negative minGainPercent would mean "always advance" (invalid state).
const minGain = Math.max(0, bailout.minGainPercent ?? 10);
const gain = result.stats?.savingsPercent ?? 0;
if (gain < minGain) return { advance: false };
return { advance: true };
}
/**
* A dispatched step whose engine found nothing eligible (e.g. session-dedup with no repeated
* blocks, ccr below its min-chars threshold) returns `stats: null` instead of throwing or
* advancing. Left unrecorded, that step vanishes from the pipeline's telemetry with zero trace —
* no `engineBreakdown` entry, no warning, no error (#6479, #6491). Surface it as a validation
* warning so operators can tell "engine ran but had nothing to do" apart from "engine never ran".
*/
function recordNullStatsStep(acc: StackAccumulator, engineId: string): void {
acc.validationWarnings.add(`${engineId}: skipped (no eligible content)`);
}
/** Folds one engine result into the accumulator (telemetry + breakdown entry). */
export function mergeStackStep(
acc: StackAccumulator,
engineId: string,
result: CompressionResult
): void {
if (!result.stats) {
// No-op engine (e.g. ccr / session-dedup found no candidate): stats is null so there is no
// telemetry to fold, but the engine still RAN — record a zero-savings breakdown entry so its
// identity survives. Without this the breakdown stays empty and ensureEngineBreakdown
// synthesizes a generic "stacked" 0% node, hiding which engine an operator actually asked for.
// Also surface a validation warning so operators can tell "engine ran but had nothing to do"
// apart from "engine never ran" (#6479, #6491).
recordNullStatsStep(acc, engineId);
acc.breakdown.push({
engine: engineId,
originalTokens: 0,
compressedTokens: 0,
savingsPercent: 0,
techniquesUsed: [],
});
return;
}
result.stats.techniquesUsed.forEach((technique) => acc.techniques.add(technique));
result.stats.rulesApplied?.forEach((rule) => acc.rules.add(rule));
result.stats.rtkRawOutputPointers?.forEach((pointer) => acc.rtkRawOutputPointers.push(pointer));
result.stats.validationWarnings?.forEach((warning) => acc.validationWarnings.add(warning));
result.stats.validationErrors?.forEach((error) => acc.validationErrors.add(error));
acc.fallbackApplied = acc.fallbackApplied || result.stats.fallbackApplied === true;
acc.breakdown.push({
engine: engineId,
originalTokens: result.stats.originalTokens,
compressedTokens: result.stats.compressedTokens,
savingsPercent: result.stats.savingsPercent,
techniquesUsed: result.stats.techniquesUsed,
...(result.stats.rulesApplied ? { rulesApplied: result.stats.rulesApplied } : {}),
...(result.stats.durationMs !== undefined ? { durationMs: result.stats.durationMs } : {}),
// O agregado do pipeline soma tokens de todas as engines; a contabilidade
// física do omniglyph só faz sentido no passo que a produziu.
...(result.stats.omniglyph ? { omniglyph: result.stats.omniglyph } : {}),
});
}