docs(llm): fix stale references in protocols/shared.ts and gemini.ts

- subtractTokens JSDoc said the raw payload lives on Usage.native, but
  that field was renamed to providerMetadata earlier in this PR.
- totalTokens JSDoc still described the abandoned "additive" first-pass
  contract where inputTokens/outputTokens were non-cached / visible only.
  We landed on inclusive totals; the fallback already covers cache and
  reasoning.
- Removed a duplicate inline comment in Gemini's mapUsage — the
  function-level comment already explains the visible/reasoning sum and
  the undefined-when-incomplete rule.

packages/llm/src/protocols/anthropic-messages.ts

@@ -364,34 +364,56 @@ const mapFinishReason = (reason: string | null | undefined): FinishReason => {
   return "unknown"
 }
 
+// Anthropic reports the non-overlapping breakdown natively — its
+// `input_tokens` is the *non-cached* count per the Messages API docs, with
+// cache reads and writes as separate fields. We sum them to derive the
+// inclusive `inputTokens` the rest of the contract expects. Extended
+// thinking tokens are *not* broken out by Anthropic — they're billed as
+// part of `output_tokens`, so `reasoningTokens` stays `undefined` and
+// `outputTokens` carries the combined total.
 const mapUsage = (usage: AnthropicUsage | undefined): Usage | undefined => {
   if (!usage) return undefined
+  const nonCached = usage.input_tokens
+  const cacheRead = usage.cache_read_input_tokens ?? undefined
+  const cacheWrite = usage.cache_creation_input_tokens ?? undefined
+  const inputTokens = ProviderShared.sumTokens(nonCached, cacheRead, cacheWrite)
   return new Usage({
-    inputTokens: usage.input_tokens,
+    inputTokens,
     outputTokens: usage.output_tokens,
-    cacheReadInputTokens: usage.cache_read_input_tokens ?? undefined,
-    cacheWriteInputTokens: usage.cache_creation_input_tokens ?? undefined,
-    totalTokens: ProviderShared.totalTokens(usage.input_tokens, usage.output_tokens, undefined),
-    native: usage,
+    nonCachedInputTokens: nonCached,
+    cacheReadInputTokens: cacheRead,
+    cacheWriteInputTokens: cacheWrite,
+    totalTokens: ProviderShared.totalTokens(inputTokens, usage.output_tokens, undefined),
+    providerMetadata: { anthropic: usage },
   })
 }
 
 // Anthropic emits usage on `message_start` and again on `message_delta` — the
 // final delta carries the authoritative totals. Right-biased merge: each
-// field prefers `right` when defined, falls back to `left`. `totalTokens` is
-// recomputed from the merged input/output to stay consistent.
+// field prefers `right` when defined, falls back to `left`. `inputTokens` is
+// recomputed from the merged breakdown so the inclusive total stays
+// consistent with `nonCached + cacheRead + cacheWrite`.
 const mergeUsage = (left: Usage | undefined, right: Usage | undefined) => {
   if (!left) return right
   if (!right) return left
-  const inputTokens = right.inputTokens ?? left.inputTokens
+  const nonCachedInputTokens = right.nonCachedInputTokens ?? left.nonCachedInputTokens
+  const cacheReadInputTokens = right.cacheReadInputTokens ?? left.cacheReadInputTokens
+  const cacheWriteInputTokens = right.cacheWriteInputTokens ?? left.cacheWriteInputTokens
+  const inputTokens = ProviderShared.sumTokens(nonCachedInputTokens, cacheReadInputTokens, cacheWriteInputTokens)
   const outputTokens = right.outputTokens ?? left.outputTokens
   return new Usage({
     inputTokens,
     outputTokens,
-    cacheReadInputTokens: right.cacheReadInputTokens ?? left.cacheReadInputTokens,
-    cacheWriteInputTokens: right.cacheWriteInputTokens ?? left.cacheWriteInputTokens,
+    nonCachedInputTokens,
+    cacheReadInputTokens,
+    cacheWriteInputTokens,
     totalTokens: ProviderShared.totalTokens(inputTokens, outputTokens, undefined),
-    native: { ...left.native, ...right.native },
+    providerMetadata: {
+      anthropic: {
+        ...(left.providerMetadata?.["anthropic"] ?? {}),
+        ...(right.providerMetadata?.["anthropic"] ?? {}),
+      },
+    },
   })
 }
 

packages/llm/src/protocols/bedrock-converse.ts

@@ -363,15 +363,22 @@ const mapFinishReason = (reason: string): FinishReason => {
   return "unknown"
 }
 
+// AWS Bedrock Converse reports `inputTokens` (inclusive total) with
+// `cacheReadInputTokens` and `cacheWriteInputTokens` as subsets. Pass
+// the total through and derive the non-cached breakdown. Bedrock does
+// not break reasoning out of `outputTokens` for any current model.
 const mapUsage = (usage: BedrockUsageSchema | undefined): Usage | undefined => {
   if (!usage) return undefined
+  const cacheTotal = (usage.cacheReadInputTokens ?? 0) + (usage.cacheWriteInputTokens ?? 0)
+  const nonCached = ProviderShared.subtractTokens(usage.inputTokens, cacheTotal)
   return new Usage({
     inputTokens: usage.inputTokens,
     outputTokens: usage.outputTokens,
-    totalTokens: ProviderShared.totalTokens(usage.inputTokens, usage.outputTokens, usage.totalTokens),
+    nonCachedInputTokens: nonCached,
     cacheReadInputTokens: usage.cacheReadInputTokens,
     cacheWriteInputTokens: usage.cacheWriteInputTokens,
-    native: usage,
+    totalTokens: ProviderShared.totalTokens(usage.inputTokens, usage.outputTokens, usage.totalTokens),
+    providerMetadata: { bedrock: usage },
   })
 }
 

packages/llm/src/protocols/gemini.ts

@@ -281,15 +281,28 @@ const fromRequest = Effect.fn("Gemini.fromRequest")(function* (request: LLMReque
 // =============================================================================
 // Stream Parsing
 // =============================================================================
+// Gemini reports `promptTokenCount` (inclusive total) with a
+// `cachedContentTokenCount` subset. `candidatesTokenCount` is *exclusive*
+// of `thoughtsTokenCount` — visible-only, not a total — so we sum the two
+// to produce the inclusive `outputTokens` the rest of the contract expects.
+// Output is left undefined when the visible component is missing, so we
+// don't fabricate an inclusive number from a partial breakdown.
 const mapUsage = (usage: GeminiUsage | undefined) => {
   if (!usage) return undefined
+  const cached = usage.cachedContentTokenCount
+  const nonCached = ProviderShared.subtractTokens(usage.promptTokenCount, cached)
+  const outputTokens =
+    usage.candidatesTokenCount !== undefined
+      ? usage.candidatesTokenCount + (usage.thoughtsTokenCount ?? 0)
+      : undefined
   return new Usage({
     inputTokens: usage.promptTokenCount,
-    outputTokens: usage.candidatesTokenCount,
+    outputTokens,
+    nonCachedInputTokens: nonCached,
+    cacheReadInputTokens: cached,
     reasoningTokens: usage.thoughtsTokenCount,
-    cacheReadInputTokens: usage.cachedContentTokenCount,
-    totalTokens: ProviderShared.totalTokens(usage.promptTokenCount, usage.candidatesTokenCount, usage.totalTokenCount),
-    native: usage,
+    totalTokens: ProviderShared.totalTokens(usage.promptTokenCount, outputTokens, usage.totalTokenCount),
+    providerMetadata: { google: usage },
   })
 }
 

packages/llm/src/protocols/openai-chat.ts

@@ -290,15 +290,24 @@ const mapFinishReason = (reason: string | null | undefined): FinishReason => {
   return "unknown"
 }
 
+// OpenAI Chat reports `prompt_tokens` (inclusive total) with a
+// `cached_tokens` subset, and `completion_tokens` (inclusive total) with
+// a `reasoning_tokens` subset. We pass the inclusive totals through and
+// derive the non-cached breakdown so the `LLM.Usage` contract is
+// satisfied on both sides.
 const mapUsage = (usage: OpenAIChatEvent["usage"]): Usage | undefined => {
   if (!usage) return undefined
+  const cached = usage.prompt_tokens_details?.cached_tokens
+  const reasoning = usage.completion_tokens_details?.reasoning_tokens
+  const nonCached = ProviderShared.subtractTokens(usage.prompt_tokens, cached)
   return new Usage({
     inputTokens: usage.prompt_tokens,
     outputTokens: usage.completion_tokens,
-    reasoningTokens: usage.completion_tokens_details?.reasoning_tokens,
-    cacheReadInputTokens: usage.prompt_tokens_details?.cached_tokens,
+    nonCachedInputTokens: nonCached,
+    cacheReadInputTokens: cached,
+    reasoningTokens: reasoning,
     totalTokens: ProviderShared.totalTokens(usage.prompt_tokens, usage.completion_tokens, usage.total_tokens),
-    native: usage,
+    providerMetadata: { openai: usage },
   })
 }
 

packages/llm/src/protocols/openai-responses.ts

@@ -276,15 +276,23 @@ const fromRequest = Effect.fn("OpenAIResponses.fromRequest")(function* (request:
 // =============================================================================
 // Stream Parsing
 // =============================================================================
+// OpenAI Responses reports `input_tokens` (inclusive total) with a
+// `cached_tokens` subset, and `output_tokens` (inclusive total) with a
+// `reasoning_tokens` subset. Pass the totals through and derive the
+// non-cached breakdown.
 const mapUsage = (usage: OpenAIResponsesUsage | null | undefined) => {
   if (!usage) return undefined
+  const cached = usage.input_tokens_details?.cached_tokens
+  const reasoning = usage.output_tokens_details?.reasoning_tokens
+  const nonCached = ProviderShared.subtractTokens(usage.input_tokens, cached)
   return new Usage({
     inputTokens: usage.input_tokens,
     outputTokens: usage.output_tokens,
-    reasoningTokens: usage.output_tokens_details?.reasoning_tokens,
-    cacheReadInputTokens: usage.input_tokens_details?.cached_tokens,
+    nonCachedInputTokens: nonCached,
+    cacheReadInputTokens: cached,
+    reasoningTokens: reasoning,
     totalTokens: ProviderShared.totalTokens(usage.input_tokens, usage.output_tokens, usage.total_tokens),
-    native: usage,
+    providerMetadata: { openai: usage },
   })
 }
 

packages/llm/src/protocols/shared.ts

@@ -42,6 +42,11 @@ export interface ToolAccumulator {
  * supplied total; otherwise falls back to `inputTokens + outputTokens` only
  * when at least one is defined. Returns `undefined` when neither input nor
  * output is known so routes don't publish a misleading `0`.
+ *
+ * Under the `LLM.Usage` contract, `inputTokens` and `outputTokens` are
+ * inclusive totals, so the computed fallback already covers cache reads /
+ * writes and reasoning — used mainly for Anthropic-style providers that
+ * don't surface a top-level total.
  */
 export const totalTokens = (
   inputTokens: number | undefined,
@@ -53,6 +58,39 @@ export const totalTokens = (
   return (inputTokens ?? 0) + (outputTokens ?? 0)
 }
 
+/**
+ * Subtract `subtrahend` from `total`, clamping to zero if the provider
+ * reports a non-sensical breakdown (e.g. `cached_tokens > prompt_tokens`).
+ * Used by protocol mappers when deriving a non-overlapping breakdown field
+ * from a provider's inclusive total — `nonCachedInputTokens` from
+ * `inputTokens - cacheReadInputTokens - cacheWriteInputTokens`.
+ *
+ * If `total` is `undefined`, returns `undefined` (we don't fabricate
+ * counts). If `subtrahend` is `undefined`, returns `total` unchanged. The
+ * provider-native breakdown stays available on `Usage.providerMetadata`
+ * for debugging.
+ */
+export const subtractTokens = (
+  total: number | undefined,
+  subtrahend: number | undefined,
+): number | undefined => {
+  if (total === undefined) return undefined
+  if (subtrahend === undefined) return total
+  return Math.max(0, total - subtrahend)
+}
+
+/**
+ * Sum a list of optional token counts, returning `undefined` only when
+ * every value is `undefined` (so we don't fabricate a `0`). Used by
+ * protocol mappers to derive the inclusive `inputTokens` total from a
+ * provider that natively reports a non-overlapping breakdown
+ * (e.g. Anthropic, whose `input_tokens` is already non-cached only).
+ */
+export const sumTokens = (...values: ReadonlyArray<number | undefined>): number | undefined => {
+  if (values.every((value) => value === undefined)) return undefined
+  return values.reduce<number>((acc, value) => acc + (value ?? 0), 0)
+}
+
 export const eventError = (route: string, message: string, raw?: string) =>
   new LLMError({
     module: "ProviderShared",

packages/llm/src/schema/events.ts

@@ -3,15 +3,70 @@ import { ContentBlockID, FinishReason, ProtocolID, ProviderMetadata, ResponseID,
 import { ModelRef } from "./options"
 import { ToolResultValue } from "./messages"
 
+/**
+ * Token usage reported by an LLM provider.
+ *
+ * **Inclusive totals** (match AI SDK / OpenAI / LangChain convention — a
+ * reader from any of those ecosystems sees the number they expect):
+ *
+ * - `inputTokens` — total prompt tokens, *including* cached reads/writes.
+ * - `outputTokens` — total output tokens, *including* reasoning.
+ * - `totalTokens` — provider-supplied total, or `inputTokens + outputTokens`.
+ *
+ * **Non-overlapping breakdown** (every field is independently meaningful;
+ * consumers never have to subtract):
+ *
+ * - `nonCachedInputTokens` — the "fresh" portion of the prompt.
+ * - `cacheReadInputTokens` — input tokens served from cache.
+ * - `cacheWriteInputTokens` — input tokens written to cache.
+ * - `reasoningTokens` — subset of `outputTokens` spent on hidden reasoning.
+ *
+ * **Invariant**: `nonCachedInputTokens + cacheReadInputTokens +
+ * cacheWriteInputTokens = inputTokens`, and `reasoningTokens ≤ outputTokens`.
+ * Each protocol mapper computes whichever side it doesn't get natively,
+ * with `Math.max(0, …)` clamping for defense against provider bugs. Because
+ * every breakdown field is stored independently, downstream consumers can
+ * read whatever they need (cost-by-category, context-pressure, AI-SDK-style
+ * inclusive total) without ever subtracting — eliminating the underflow
+ * class of bug where a clamped difference would silently store the wrong
+ * value.
+ *
+ * **Semantics by provider**:
+ *
+ * - OpenAI Chat / Responses / Gemini / Bedrock: provider reports inclusive
+ *   `inputTokens` and an inclusive `outputTokens`; mapper subtracts to
+ *   derive the breakdown.
+ * - Anthropic: provider reports the breakdown natively (`input_tokens` is
+ *   non-cached only); mapper sums to derive the inclusive `inputTokens`.
+ *   Anthropic does *not* break extended-thinking out of `output_tokens`, so
+ *   `reasoningTokens` is `undefined` and `outputTokens` carries the
+ *   combined total — a documented limitation of the Anthropic API.
+ *
+ * `providerMetadata` always carries the provider's raw usage payload —
+ * keyed by provider name (`{ openai: ... }`, `{ anthropic: ... }`, etc.)
+ * — for fields we don't normalize and for billing-level audit trails.
+ * Matches the same escape-hatch field on `LLMEvent`.
+ */
 export class Usage extends Schema.Class<Usage>("LLM.Usage")({
   inputTokens: Schema.optional(Schema.Number),
   outputTokens: Schema.optional(Schema.Number),
-  reasoningTokens: Schema.optional(Schema.Number),
+  nonCachedInputTokens: Schema.optional(Schema.Number),
   cacheReadInputTokens: Schema.optional(Schema.Number),
   cacheWriteInputTokens: Schema.optional(Schema.Number),
+  reasoningTokens: Schema.optional(Schema.Number),
   totalTokens: Schema.optional(Schema.Number),
-  native: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
-}) {}
+  providerMetadata: Schema.optional(ProviderMetadata),
+}) {
+  /**
+   * Visible output tokens — `outputTokens` minus `reasoningTokens`, clamped
+   * to zero. The one place subtraction happens in this contract; the clamp
+   * means a provider reporting `reasoningTokens > outputTokens` produces a
+   * harmless zero rather than a negative that crashes downstream schemas.
+   */
+  get visibleOutputTokens() {
+    return Math.max(0, (this.outputTokens ?? 0) - (this.reasoningTokens ?? 0))
+  }
+}
 
 export const RequestStart = Schema.Struct({
   type: Schema.tag("request-start"),

packages/llm/test/fixtures/recordings/anthropic-messages/anthropic-haiku-4-5-text.json

@@ -0,0 +1,38 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "anthropic-messages/anthropic-haiku-4-5-text",
+    "recordedAt": "2026-05-11T02:02:03.804Z",
+    "provider": "anthropic",
+    "route": "anthropic-messages",
+    "transport": "http",
+    "model": "claude-haiku-4-5-20251001",
+    "tags": [
+      "prefix:anthropic-messages",
+      "provider:anthropic",
+      "text",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.anthropic.com/v1/messages",
+        "headers": {
+          "anthropic-version": "2023-06-01",
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"claude-haiku-4-5-20251001\",\"system\":[{\"type\":\"text\",\"text\":\"You are concise.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Reply exactly with: Hello!\"}]}],\"stream\":true,\"max_tokens\":40,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_01SvRWwb75gDuhBpVMHjnFaf\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"stop_reason\":null,\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":18,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":2,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}}   }\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}            }\n\nevent: ping\ndata: {\"type\": \"ping\"}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"Hello!\"}  }\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0          }\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"stop_details\":null},\"usage\":{\"input_tokens\":18,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":5}  }\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"          }\n\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/anthropic-messages/anthropic-haiku-4-5-tool-call.json

@@ -0,0 +1,39 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "anthropic-messages/anthropic-haiku-4-5-tool-call",
+    "recordedAt": "2026-05-11T02:02:04.363Z",
+    "provider": "anthropic",
+    "route": "anthropic-messages",
+    "transport": "http",
+    "model": "claude-haiku-4-5-20251001",
+    "tags": [
+      "prefix:anthropic-messages",
+      "provider:anthropic",
+      "tool",
+      "tool-call",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.anthropic.com/v1/messages",
+        "headers": {
+          "anthropic-version": "2023-06-01",
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"claude-haiku-4-5-20251001\",\"system\":[{\"type\":\"text\",\"text\":\"Call tools exactly as requested.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Call get_weather with city exactly Paris.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":80,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_01Lu38yDM3WD8QBQTcg3dBaF\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"stop_reason\":null,\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":677,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":16,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}}}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"tool_use\",\"id\":\"toolu_017Dqk9SAAsHHfiLKsUyitaQ\",\"name\":\"get_weather\",\"input\":{},\"caller\":{\"type\":\"direct\"}}   }\n\nevent: ping\ndata: {\"type\": \"ping\"}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"\"}    }\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\\\"cit\"}          }\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"y\\\": \\\"Paris\\\"}\"}           }\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null,\"stop_details\":null},\"usage\":{\"input_tokens\":677,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":33}      }\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"             }\n\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/anthropic-messages/anthropic-opus-4-7-tool-loop.json

@@ -0,0 +1,59 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "anthropic-messages/anthropic-opus-4-7-tool-loop",
+    "recordedAt": "2026-05-11T02:02:07.788Z",
+    "provider": "anthropic",
+    "route": "anthropic-messages",
+    "transport": "http",
+    "model": "claude-opus-4-7",
+    "tags": [
+      "prefix:anthropic-messages",
+      "provider:anthropic",
+      "flagship",
+      "tool",
+      "tool-loop",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.anthropic.com/v1/messages",
+        "headers": {
+          "anthropic-version": "2023-06-01",
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"claude-opus-4-7\",\"system\":[{\"type\":\"text\",\"text\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is the weather in Paris?\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":80}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"model\":\"claude-opus-4-7\",\"id\":\"msg_01GK5kgi8AuVfRCnQFcXEfV8\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"stop_reason\":null,\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":812,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":0,\"service_tier\":\"standard\",\"inference_geo\":\"global\"}} }\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"tool_use\",\"id\":\"toolu_01BnVDAp13NU8ZdJ9JeJ7byF\",\"name\":\"get_weather\",\"input\":{},\"caller\":{\"type\":\"direct\"}}}\n\nevent: ping\ndata: {\"type\": \"ping\"}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"\"}        }\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\\\"c\"}      }\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"ity\\\": \\\"\"}        }\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"Paris\"} }\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"\\\"}\"}         }\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0       }\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null,\"stop_details\":null},\"usage\":{\"input_tokens\":812,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":66}   }\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"          }\n\n"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.anthropic.com/v1/messages",
+        "headers": {
+          "anthropic-version": "2023-06-01",
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"claude-opus-4-7\",\"system\":[{\"type\":\"text\",\"text\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is the weather in Paris?\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"tool_use\",\"id\":\"toolu_01BnVDAp13NU8ZdJ9JeJ7byF\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"toolu_01BnVDAp13NU8ZdJ9JeJ7byF\",\"content\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":80}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"model\":\"claude-opus-4-7\",\"id\":\"msg_01237VTnjPeYSRh31UjXWaEa\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"stop_reason\":null,\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":909,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":8,\"service_tier\":\"standard\",\"inference_geo\":\"global\"}}       }\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}               }\n\nevent: ping\ndata: {\"type\": \"ping\"}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"Paris is sunny.\"}     }\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0      }\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"stop_details\":null},\"usage\":{\"input_tokens\":909,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":12}      }\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"       }\n\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/anthropic-messages/rejects-malformed-assistant-tool-order.json

@@ -0,0 +1,35 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "anthropic-messages/rejects-malformed-assistant-tool-order",
+    "recordedAt": "2026-05-11T02:01:44.544Z",
+    "tags": [
+      "prefix:anthropic-messages",
+      "provider:anthropic",
+      "protocol:anthropic-messages",
+      "tool",
+      "sad-path"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.anthropic.com/v1/messages",
+        "headers": {
+          "anthropic-version": "2023-06-01",
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"claude-haiku-4-5-20251001\",\"messages\":[{\"role\":\"assistant\",\"content\":[{\"type\":\"tool_use\",\"id\":\"call_1\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}},{\"type\":\"text\",\"text\":\"I will check the weather.\"}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_1\",\"content\":\"{\\\"temperature\\\":\\\"72F\\\"}\"}]},{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Use that result to answer briefly.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get weather\",\"input_schema\":{\"type\":\"object\",\"properties\":{}}}],\"stream\":true,\"max_tokens\":4096}"
+      },
+      "response": {
+        "status": 400,
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"type\":\"error\",\"error\":{\"type\":\"invalid_request_error\",\"message\":\"messages.1: `tool_use` ids were found without `tool_result` blocks immediately after: call_1. Each `tool_use` block must have a corresponding `tool_result` block in the next message.\"},\"request_id\":\"req_011CauxVdQf3N2PPFJ5aH8Bh\"}"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/gemini/gemini-2-5-flash-text.json

@@ -0,0 +1,37 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "gemini/gemini-2-5-flash-text",
+    "recordedAt": "2026-05-11T02:02:08.410Z",
+    "provider": "google",
+    "route": "gemini",
+    "transport": "http",
+    "model": "gemini-2.5-flash",
+    "tags": [
+      "prefix:gemini",
+      "provider:google",
+      "text",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:streamGenerateContent?alt=sse",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"contents\":[{\"role\":\"user\",\"parts\":[{\"text\":\"Reply exactly with: Hello!\"}]}],\"systemInstruction\":{\"parts\":[{\"text\":\"You are concise.\"}]},\"generationConfig\":{\"maxOutputTokens\":80,\"temperature\":0}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"Hello!\"}],\"role\": \"model\"},\"finishReason\": \"STOP\",\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 11,\"candidatesTokenCount\": 2,\"totalTokenCount\": 13,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 11}],\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-2.5-flash\",\"responseId\": \"nzgBatP3OZmW-8YP567bqQs\"}\r\n\r\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/gemini/gemini-2-5-flash-tool-call.json

@@ -0,0 +1,38 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "gemini/gemini-2-5-flash-tool-call",
+    "recordedAt": "2026-05-11T02:02:09.308Z",
+    "provider": "google",
+    "route": "gemini",
+    "transport": "http",
+    "model": "gemini-2.5-flash",
+    "tags": [
+      "prefix:gemini",
+      "provider:google",
+      "tool",
+      "tool-call",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:streamGenerateContent?alt=sse",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"contents\":[{\"role\":\"user\",\"parts\":[{\"text\":\"Call get_weather with city exactly Paris.\"}]}],\"systemInstruction\":{\"parts\":[{\"text\":\"Call tools exactly as requested.\"}]},\"tools\":[{\"functionDeclarations\":[{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"required\":[\"city\"],\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}}}}]}],\"toolConfig\":{\"functionCallingConfig\":{\"mode\":\"ANY\",\"allowedFunctionNames\":[\"get_weather\"]}},\"generationConfig\":{\"maxOutputTokens\":80,\"temperature\":0}}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream"
+        },
+        "body": "data: {\"candidates\": [{\"content\": {\"parts\": [{\"functionCall\": {\"name\": \"get_weather\",\"args\": {\"city\": \"Paris\"}},\"thoughtSignature\": \"CiQBDDnWx/X6sWeX2joSugyWO3L/lt0AgIPCvhpqf3845fj+H70KXwEMOdbHB/cnaqYCro0pU+yLWoA55jhuwoLmTcnYm4Qzcm5DuW/v0NUyz8RDx6DFh61juENveUztly6yc6/XiWJHtsgncd9YgcZhuQKqtp5KZTkGYpT3g6v3yP9GK4AoCoUBAQw51sePh3WuWovHnwIotKLVZiU9pwh34k4FY7ugPOxyDAG9j69cy7BYYzSchI10LEjLoLlCMZuNIPootBgI02QWY/4h2PIv33BAADrFPM2T3aE4cAuMoa3GCu2nztJ/95junDhIhuXZSQ/Mh9EVxpx7ml99Z7Hxb7OtDsSZZLeCBuGmSw==\"}],\"role\": \"model\"},\"finishReason\": \"STOP\",\"index\": 0,\"finishMessage\": \"Model generated function call(s).\"}],\"usageMetadata\": {\"promptTokenCount\": 55,\"candidatesTokenCount\": 15,\"totalTokenCount\": 115,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 55}],\"thoughtsTokenCount\": 45,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-2.5-flash\",\"responseId\": \"oDgBauj6HZ3B-8YPpaOc6QU\"}\r\n\r\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/openai-chat/openai-chat-gpt-4o-mini-text.json

@@ -0,0 +1,37 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "openai-chat/openai-chat-gpt-4o-mini-text",
+    "recordedAt": "2026-05-11T02:01:46.536Z",
+    "provider": "openai",
+    "route": "openai-chat",
+    "transport": "http",
+    "model": "gpt-4o-mini",
+    "tags": [
+      "prefix:openai-chat",
+      "provider:openai",
+      "text",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.openai.com/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gpt-4o-mini\",\"messages\":[{\"role\":\"system\",\"content\":\"You are concise.\"},{\"role\":\"user\",\"content\":\"Reply exactly with: Hello!\"}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":40,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "data: {\"id\":\"chatcmpl-DeAFmC9UiBnVu6dAjBvWVBVypm2gc\",\"object\":\"chat.completion.chunk\",\"created\":1778464906,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_3ef558a83f\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":\"\",\"refusal\":null},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"wHajUz1js\"}\n\ndata: {\"id\":\"chatcmpl-DeAFmC9UiBnVu6dAjBvWVBVypm2gc\",\"object\":\"chat.completion.chunk\",\"created\":1778464906,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_3ef558a83f\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"Hello\"},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"lVHzGq\"}\n\ndata: {\"id\":\"chatcmpl-DeAFmC9UiBnVu6dAjBvWVBVypm2gc\",\"object\":\"chat.completion.chunk\",\"created\":1778464906,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_3ef558a83f\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"!\"},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"3gaQRWEjE7\"}\n\ndata: {\"id\":\"chatcmpl-DeAFmC9UiBnVu6dAjBvWVBVypm2gc\",\"object\":\"chat.completion.chunk\",\"created\":1778464906,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_3ef558a83f\",\"choices\":[{\"index\":0,\"delta\":{},\"logprobs\":null,\"finish_reason\":\"stop\"}],\"usage\":null,\"obfuscation\":\"vuKPZ\"}\n\ndata: {\"id\":\"chatcmpl-DeAFmC9UiBnVu6dAjBvWVBVypm2gc\",\"object\":\"chat.completion.chunk\",\"created\":1778464906,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_3ef558a83f\",\"choices\":[],\"usage\":{\"prompt_tokens\":21,\"completion_tokens\":2,\"total_tokens\":23,\"prompt_tokens_details\":{\"cached_tokens\":0,\"audio_tokens\":0},\"completion_tokens_details\":{\"reasoning_tokens\":0,\"audio_tokens\":0,\"accepted_prediction_tokens\":0,\"rejected_prediction_tokens\":0}},\"obfuscation\":\"kfFsssdujmM\"}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/openai-chat/openai-chat-gpt-4o-mini-tool-call.json

@@ -0,0 +1,38 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "openai-chat/openai-chat-gpt-4o-mini-tool-call",
+    "recordedAt": "2026-05-11T02:01:47.484Z",
+    "provider": "openai",
+    "route": "openai-chat",
+    "transport": "http",
+    "model": "gpt-4o-mini",
+    "tags": [
+      "prefix:openai-chat",
+      "provider:openai",
+      "tool",
+      "tool-call",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.openai.com/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gpt-4o-mini\",\"messages\":[{\"role\":\"system\",\"content\":\"Call tools exactly as requested.\"},{\"role\":\"user\",\"content\":\"Call get_weather with city exactly Paris.\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}],\"tool_choice\":{\"type\":\"function\",\"function\":{\"name\":\"get_weather\"}},\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":80,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "data: {\"id\":\"chatcmpl-DeAFnVMdELyuymMRlTqN5dBdM7eGd\",\"object\":\"chat.completion.chunk\",\"created\":1778464907,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_d88f6e55bb\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"index\":0,\"id\":\"call_sH8T7MPdJXS5KJginKrzexL5\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"\"}}],\"refusal\":null},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"d0rJ\"}\n\ndata: {\"id\":\"chatcmpl-DeAFnVMdELyuymMRlTqN5dBdM7eGd\",\"object\":\"chat.completion.chunk\",\"created\":1778464907,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_d88f6e55bb\",\"choices\":[{\"index\":0,\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"{\\\"\"}}]},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"hL82erd6bBoy91\"}\n\ndata: {\"id\":\"chatcmpl-DeAFnVMdELyuymMRlTqN5dBdM7eGd\",\"object\":\"chat.completion.chunk\",\"created\":1778464907,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_d88f6e55bb\",\"choices\":[{\"index\":0,\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"city\"}}]},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"e3aoKH4tvJlXW\"}\n\ndata: {\"id\":\"chatcmpl-DeAFnVMdELyuymMRlTqN5dBdM7eGd\",\"object\":\"chat.completion.chunk\",\"created\":1778464907,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_d88f6e55bb\",\"choices\":[{\"index\":0,\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"\\\":\\\"\"}}]},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"T8EzFVNaUCLE\"}\n\ndata: {\"id\":\"chatcmpl-DeAFnVMdELyuymMRlTqN5dBdM7eGd\",\"object\":\"chat.completion.chunk\",\"created\":1778464907,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_d88f6e55bb\",\"choices\":[{\"index\":0,\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"Paris\"}}]},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"lelRBxF08Zes\"}\n\ndata: {\"id\":\"chatcmpl-DeAFnVMdELyuymMRlTqN5dBdM7eGd\",\"object\":\"chat.completion.chunk\",\"created\":1778464907,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_d88f6e55bb\",\"choices\":[{\"index\":0,\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"\\\"}\"}}]},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"F1xO8sVMyZt4BU\"}\n\ndata: {\"id\":\"chatcmpl-DeAFnVMdELyuymMRlTqN5dBdM7eGd\",\"object\":\"chat.completion.chunk\",\"created\":1778464907,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_d88f6e55bb\",\"choices\":[{\"index\":0,\"delta\":{},\"logprobs\":null,\"finish_reason\":\"stop\"}],\"usage\":null,\"obfuscation\":\"YL3pl\"}\n\ndata: {\"id\":\"chatcmpl-DeAFnVMdELyuymMRlTqN5dBdM7eGd\",\"object\":\"chat.completion.chunk\",\"created\":1778464907,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_d88f6e55bb\",\"choices\":[],\"usage\":{\"prompt_tokens\":67,\"completion_tokens\":5,\"total_tokens\":72,\"prompt_tokens_details\":{\"cached_tokens\":0,\"audio_tokens\":0},\"completion_tokens_details\":{\"reasoning_tokens\":0,\"audio_tokens\":0,\"accepted_prediction_tokens\":0,\"rejected_prediction_tokens\":0}},\"obfuscation\":\"7cov9qkofwo\"}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/openai-chat/openai-chat-gpt-4o-mini-tool-loop.json

@@ -0,0 +1,56 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "openai-chat/openai-chat-gpt-4o-mini-tool-loop",
+    "recordedAt": "2026-05-11T02:01:50.433Z",
+    "provider": "openai",
+    "route": "openai-chat",
+    "transport": "http",
+    "model": "gpt-4o-mini",
+    "tags": [
+      "prefix:openai-chat",
+      "provider:openai",
+      "tool",
+      "tool-loop",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.openai.com/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gpt-4o-mini\",\"messages\":[{\"role\":\"system\",\"content\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris?\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":80,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "data: {\"id\":\"chatcmpl-DeAFo2rbsuuMn0ftzxwfDpqnYANrT\",\"object\":\"chat.completion.chunk\",\"created\":1778464908,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"index\":0,\"id\":\"call_HrDZhrMUauvVddKWzVQFJ69Q\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"\"}}],\"refusal\":null},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"aAqC\"}\n\ndata: {\"id\":\"chatcmpl-DeAFo2rbsuuMn0ftzxwfDpqnYANrT\",\"object\":\"chat.completion.chunk\",\"created\":1778464908,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"{\\\"\"}}]},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"haZ3pKk14oDay0\"}\n\ndata: {\"id\":\"chatcmpl-DeAFo2rbsuuMn0ftzxwfDpqnYANrT\",\"object\":\"chat.completion.chunk\",\"created\":1778464908,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"city\"}}]},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"ZUJHQytFyDezp\"}\n\ndata: {\"id\":\"chatcmpl-DeAFo2rbsuuMn0ftzxwfDpqnYANrT\",\"object\":\"chat.completion.chunk\",\"created\":1778464908,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"\\\":\\\"\"}}]},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"3buqnStPteyG\"}\n\ndata: {\"id\":\"chatcmpl-DeAFo2rbsuuMn0ftzxwfDpqnYANrT\",\"object\":\"chat.completion.chunk\",\"created\":1778464908,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"Paris\"}}]},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"7epPqHEU3OeA\"}\n\ndata: {\"id\":\"chatcmpl-DeAFo2rbsuuMn0ftzxwfDpqnYANrT\",\"object\":\"chat.completion.chunk\",\"created\":1778464908,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"\\\"}\"}}]},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"gSU5gyl9K7sUCv\"}\n\ndata: {\"id\":\"chatcmpl-DeAFo2rbsuuMn0ftzxwfDpqnYANrT\",\"object\":\"chat.completion.chunk\",\"created\":1778464908,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{},\"logprobs\":null,\"finish_reason\":\"tool_calls\"}],\"usage\":null,\"obfuscation\":\"P3oSvByfy60JCsz\"}\n\ndata: {\"id\":\"chatcmpl-DeAFo2rbsuuMn0ftzxwfDpqnYANrT\",\"object\":\"chat.completion.chunk\",\"created\":1778464908,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[],\"usage\":{\"prompt_tokens\":71,\"completion_tokens\":14,\"total_tokens\":85,\"prompt_tokens_details\":{\"cached_tokens\":0,\"audio_tokens\":0},\"completion_tokens_details\":{\"reasoning_tokens\":0,\"audio_tokens\":0,\"accepted_prediction_tokens\":0,\"rejected_prediction_tokens\":0}},\"obfuscation\":\"5AhQ5ToYra\"}\n\ndata: [DONE]\n\n"
+      }
+    },
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.openai.com/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"gpt-4o-mini\",\"messages\":[{\"role\":\"system\",\"content\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"},{\"role\":\"user\",\"content\":\"What is the weather in Paris?\"},{\"role\":\"assistant\",\"content\":null,\"tool_calls\":[{\"id\":\"call_HrDZhrMUauvVddKWzVQFJ69Q\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"}}]},{\"role\":\"tool\",\"tool_call_id\":\"call_HrDZhrMUauvVddKWzVQFJ69Q\",\"content\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":80,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "data: {\"id\":\"chatcmpl-DeAFpaPsUwxt5hjwGgC4BBmlALxwR\",\"object\":\"chat.completion.chunk\",\"created\":1778464909,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":\"\",\"refusal\":null},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"2QWjdWPSe\"}\n\ndata: {\"id\":\"chatcmpl-DeAFpaPsUwxt5hjwGgC4BBmlALxwR\",\"object\":\"chat.completion.chunk\",\"created\":1778464909,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"Paris\"},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"sm5IpQ\"}\n\ndata: {\"id\":\"chatcmpl-DeAFpaPsUwxt5hjwGgC4BBmlALxwR\",\"object\":\"chat.completion.chunk\",\"created\":1778464909,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\" is\"},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"cWsGxqHw\"}\n\ndata: {\"id\":\"chatcmpl-DeAFpaPsUwxt5hjwGgC4BBmlALxwR\",\"object\":\"chat.completion.chunk\",\"created\":1778464909,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\" sunny\"},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"8hNCi\"}\n\ndata: {\"id\":\"chatcmpl-DeAFpaPsUwxt5hjwGgC4BBmlALxwR\",\"object\":\"chat.completion.chunk\",\"created\":1778464909,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\".\"},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null,\"obfuscation\":\"4yKCNDRcwq\"}\n\ndata: {\"id\":\"chatcmpl-DeAFpaPsUwxt5hjwGgC4BBmlALxwR\",\"object\":\"chat.completion.chunk\",\"created\":1778464909,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[{\"index\":0,\"delta\":{},\"logprobs\":null,\"finish_reason\":\"stop\"}],\"usage\":null,\"obfuscation\":\"NvRgg\"}\n\ndata: {\"id\":\"chatcmpl-DeAFpaPsUwxt5hjwGgC4BBmlALxwR\",\"object\":\"chat.completion.chunk\",\"created\":1778464909,\"model\":\"gpt-4o-mini-2024-07-18\",\"service_tier\":\"default\",\"system_fingerprint\":\"fp_c83829e916\",\"choices\":[],\"usage\":{\"prompt_tokens\":103,\"completion_tokens\":5,\"total_tokens\":108,\"prompt_tokens_details\":{\"cached_tokens\":0,\"audio_tokens\":0},\"completion_tokens_details\":{\"reasoning_tokens\":0,\"audio_tokens\":0,\"accepted_prediction_tokens\":0,\"rejected_prediction_tokens\":0}},\"obfuscation\":\"4s7mLtNpZ\"}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/openai-compatible-chat/deepseek-chat-text.json

@@ -0,0 +1,37 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "openai-compatible-chat/deepseek-chat-text",
+    "recordedAt": "2026-05-11T02:02:10.220Z",
+    "provider": "deepseek",
+    "route": "openai-compatible-chat",
+    "transport": "http",
+    "model": "deepseek-chat",
+    "tags": [
+      "prefix:openai-compatible-chat",
+      "provider:deepseek",
+      "text",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.deepseek.com/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"deepseek-chat\",\"messages\":[{\"role\":\"system\",\"content\":\"You are concise.\"},{\"role\":\"user\",\"content\":\"Reply exactly with: Hello!\"}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":40,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream; charset=utf-8"
+        },
+        "body": "data: {\"id\":\"159019a5-f981-4103-8b3c-2be37cefc505\",\"object\":\"chat.completion.chunk\",\"created\":1778464929,\"model\":\"deepseek-v4-flash\",\"system_fingerprint\":\"fp_058df29938_prod0820_fp8_kvcache_20260402\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":\"\"},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null}\n\ndata: {\"id\":\"159019a5-f981-4103-8b3c-2be37cefc505\",\"object\":\"chat.completion.chunk\",\"created\":1778464929,\"model\":\"deepseek-v4-flash\",\"system_fingerprint\":\"fp_058df29938_prod0820_fp8_kvcache_20260402\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"Hello\"},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null}\n\ndata: {\"id\":\"159019a5-f981-4103-8b3c-2be37cefc505\",\"object\":\"chat.completion.chunk\",\"created\":1778464929,\"model\":\"deepseek-v4-flash\",\"system_fingerprint\":\"fp_058df29938_prod0820_fp8_kvcache_20260402\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"!\"},\"logprobs\":null,\"finish_reason\":null}],\"usage\":null}\n\ndata: {\"id\":\"159019a5-f981-4103-8b3c-2be37cefc505\",\"object\":\"chat.completion.chunk\",\"created\":1778464929,\"model\":\"deepseek-v4-flash\",\"system_fingerprint\":\"fp_058df29938_prod0820_fp8_kvcache_20260402\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\"},\"logprobs\":null,\"finish_reason\":\"stop\"}],\"usage\":{\"prompt_tokens\":14,\"completion_tokens\":2,\"total_tokens\":16,\"prompt_tokens_details\":{\"cached_tokens\":0},\"prompt_cache_hit_tokens\":0,\"prompt_cache_miss_tokens\":14}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/openai-compatible-chat/togetherai-llama-3-3-70b-text.json

@@ -0,0 +1,37 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "openai-compatible-chat/togetherai-llama-3-3-70b-text",
+    "recordedAt": "2026-05-11T02:02:13.341Z",
+    "provider": "togetherai",
+    "route": "openai-compatible-chat",
+    "transport": "http",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
+    "tags": [
+      "prefix:openai-compatible-chat",
+      "provider:togetherai",
+      "text",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.together.xyz/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"meta-llama/Llama-3.3-70B-Instruct-Turbo\",\"messages\":[{\"role\":\"system\",\"content\":\"You are concise.\"},{\"role\":\"user\",\"content\":\"Reply exactly with: Hello!\"}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":40,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream;charset=utf-8"
+        },
+        "body": "data: {\"id\":\"oibreET-3pDw3Z-9f9d9996ce37066b\",\"object\":\"chat.completion.chunk\",\"created\":1778464931,\"choices\":[{\"index\":0,\"text\":\"Hello\",\"logprobs\":null,\"finish_reason\":null,\"seed\":null,\"delta\":{\"token_id\":9906,\"role\":\"assistant\",\"content\":\"Hello\"}}],\"model\":\"meta-llama/Llama-3.3-70B-Instruct-Turbo\",\"usage\":null}\n\ndata: {\"id\":\"oibreET-3pDw3Z-9f9d9996ce37066b\",\"object\":\"chat.completion.chunk\",\"created\":1778464931,\"choices\":[{\"index\":0,\"text\":\"!\",\"logprobs\":null,\"finish_reason\":null,\"seed\":null,\"delta\":{\"token_id\":null,\"role\":\"assistant\",\"content\":\"!\"}}],\"model\":\"meta-llama/Llama-3.3-70B-Instruct-Turbo\",\"usage\":null}\n\ndata: {\"id\":\"oibreET-3pDw3Z-9f9d9996ce37066b\",\"object\":\"chat.completion.chunk\",\"created\":1778464931,\"choices\":[{\"index\":0,\"text\":\"\",\"logprobs\":null,\"finish_reason\":\"stop\",\"seed\":12144769634208630000,\"delta\":{\"token_id\":128009,\"role\":\"assistant\",\"content\":\"\"}}],\"model\":\"meta-llama/Llama-3.3-70B-Instruct-Turbo\",\"usage\":{\"prompt_tokens\":45,\"completion_tokens\":3,\"total_tokens\":48,\"cached_tokens\":0}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/openai-compatible-chat/togetherai-llama-3-3-70b-tool-call.json

@@ -0,0 +1,38 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "openai-compatible-chat/togetherai-llama-3-3-70b-tool-call",
+    "recordedAt": "2026-05-11T02:02:14.453Z",
+    "provider": "togetherai",
+    "route": "openai-compatible-chat",
+    "transport": "http",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
+    "tags": [
+      "prefix:openai-compatible-chat",
+      "provider:togetherai",
+      "tool",
+      "tool-call",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "http",
+      "request": {
+        "method": "POST",
+        "url": "https://api.together.xyz/v1/chat/completions",
+        "headers": {
+          "content-type": "application/json"
+        },
+        "body": "{\"model\":\"meta-llama/Llama-3.3-70B-Instruct-Turbo\",\"messages\":[{\"role\":\"system\",\"content\":\"Call tools exactly as requested.\"},{\"role\":\"user\",\"content\":\"Call get_weather with city exactly Paris.\"}],\"tools\":[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}}],\"tool_choice\":{\"type\":\"function\",\"function\":{\"name\":\"get_weather\"}},\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":80,\"temperature\":0}"
+      },
+      "response": {
+        "status": 200,
+        "headers": {
+          "content-type": "text/event-stream;charset=utf-8"
+        },
+        "body": "data: {\"id\":\"oibreu3-6Ng1vN-9f9d99a9ba73066b\",\"object\":\"chat.completion.chunk\",\"created\":1778464933,\"choices\":[{\"index\":0,\"role\":\"assistant\",\"text\":\"\",\"logprobs\":null,\"finish_reason\":null,\"delta\":{\"token_id\":null,\"role\":\"assistant\",\"content\":\"\"}}],\"model\":\"meta-llama/Llama-3.3-70B-Instruct-Turbo\"}\n\ndata: {\"id\":\"oibreu3-6Ng1vN-9f9d99a9ba73066b\",\"object\":\"chat.completion.chunk\",\"created\":1778464933,\"choices\":[{\"index\":0,\"text\":\"\",\"logprobs\":null,\"finish_reason\":null,\"delta\":{\"token_id\":null,\"role\":\"assistant\",\"content\":\"\",\"tool_calls\":[{\"index\":0,\"id\":\"call_jue52dtu6iozr0ny9rq357u5\",\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"arguments\":\"\"}}]}}],\"model\":\"meta-llama/Llama-3.3-70B-Instruct-Turbo\"}\n\ndata: {\"id\":\"oibreu3-6Ng1vN-9f9d99a9ba73066b\",\"object\":\"chat.completion.chunk\",\"created\":1778464933,\"choices\":[{\"index\":0,\"text\":\"\",\"logprobs\":null,\"finish_reason\":\"tool_calls\",\"delta\":{\"token_id\":null,\"role\":\"assistant\",\"content\":\"\",\"tool_calls\":[{\"index\":0,\"function\":{\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"}}]}}],\"model\":\"meta-llama/Llama-3.3-70B-Instruct-Turbo\"}\n\ndata: {\"id\":\"oibreu3-6Ng1vN-9f9d99a9ba73066b\",\"object\":\"chat.completion.chunk\",\"created\":1778464933,\"choices\":[{\"index\":0,\"text\":\"\",\"logprobs\":null,\"finish_reason\":\"tool_calls\",\"seed\":17440360718047570000,\"delta\":{\"token_id\":128009,\"role\":\"assistant\",\"content\":\"\"}}],\"model\":\"meta-llama/Llama-3.3-70B-Instruct-Turbo\",\"usage\":{\"prompt_tokens\":194,\"completion_tokens\":19,\"total_tokens\":213,\"cached_tokens\":0}}\n\ndata: [DONE]\n\n"
+      }
+    }
+  ]
+}

packages/llm/test/fixtures/recordings/openai-responses-websocket/openai-responses-websocket-gpt-4-1-mini-tool-loop.json

@@ -0,0 +1,143 @@
+{
+  "version": 1,
+  "metadata": {
+    "name": "openai-responses-websocket/openai-responses-websocket-gpt-4-1-mini-tool-loop",
+    "recordedAt": "2026-05-11T02:02:03.284Z",
+    "provider": "openai",
+    "route": "openai-responses-websocket",
+    "transport": "websocket",
+    "model": "gpt-4.1-mini",
+    "tags": [
+      "prefix:openai-responses-websocket",
+      "provider:openai",
+      "transport:websocket",
+      "tool",
+      "tool-loop",
+      "golden"
+    ]
+  },
+  "interactions": [
+    {
+      "transport": "websocket",
+      "open": {
+        "url": "wss://api.openai.com/v1/responses",
+        "headers": {}
+      },
+      "client": [
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-4.1-mini\",\"input\":[{\"role\":\"system\",\"content\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"},{\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]}],\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"store\":false,\"max_output_tokens\":80,\"temperature\":0}"
+        }
+      ],
+      "server": [
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.created\",\"response\":{\"id\":\"resp_0f8d81b5d3287513016a013897415481a28585571d6710366f\",\"object\":\"response\",\"created_at\":1778464919,\"status\":\"in_progress\",\"background\":false,\"completed_at\":null,\"error\":null,\"frequency_penalty\":0.0,\"incomplete_details\":null,\"instructions\":null,\"max_output_tokens\":80,\"max_tool_calls\":null,\"model\":\"gpt-4.1-mini-2025-04-14\",\"moderation\":null,\"output\":[],\"parallel_tool_calls\":true,\"presence_penalty\":0.0,\"previous_response_id\":null,\"prompt_cache_key\":null,\"prompt_cache_retention\":\"in_memory\",\"reasoning\":{\"effort\":null,\"summary\":null},\"safety_identifier\":null,\"service_tier\":\"auto\",\"store\":false,\"temperature\":0.0,\"text\":{\"format\":{\"type\":\"text\"},\"verbosity\":\"medium\"},\"tool_choice\":\"auto\",\"tools\":[{\"type\":\"function\",\"description\":\"Get current weather for a city.\",\"name\":\"get_weather\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":true}],\"top_logprobs\":0,\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":null,\"user\":null,\"metadata\":{}},\"sequence_number\":0}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.in_progress\",\"response\":{\"id\":\"resp_0f8d81b5d3287513016a013897415481a28585571d6710366f\",\"object\":\"response\",\"created_at\":1778464919,\"status\":\"in_progress\",\"background\":false,\"completed_at\":null,\"error\":null,\"frequency_penalty\":0.0,\"incomplete_details\":null,\"instructions\":null,\"max_output_tokens\":80,\"max_tool_calls\":null,\"model\":\"gpt-4.1-mini-2025-04-14\",\"moderation\":null,\"output\":[],\"parallel_tool_calls\":true,\"presence_penalty\":0.0,\"previous_response_id\":null,\"prompt_cache_key\":null,\"prompt_cache_retention\":\"in_memory\",\"reasoning\":{\"effort\":null,\"summary\":null},\"safety_identifier\":null,\"service_tier\":\"auto\",\"store\":false,\"temperature\":0.0,\"text\":{\"format\":{\"type\":\"text\"},\"verbosity\":\"medium\"},\"tool_choice\":\"auto\",\"tools\":[{\"type\":\"function\",\"description\":\"Get current weather for a city.\",\"name\":\"get_weather\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":true}],\"top_logprobs\":0,\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":null,\"user\":null,\"metadata\":{}},\"sequence_number\":1}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.output_item.added\",\"item\":{\"id\":\"fc_0f8d81b5d3287513016a01389815f081a2a68583ed9b19c405\",\"type\":\"function_call\",\"status\":\"in_progress\",\"arguments\":\"\",\"call_id\":\"call_wRJoUdcb6w5SIpieBFOKxF6z\",\"name\":\"get_weather\"},\"output_index\":0,\"sequence_number\":2}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.function_call_arguments.delta\",\"delta\":\"{\\\"\",\"item_id\":\"fc_0f8d81b5d3287513016a01389815f081a2a68583ed9b19c405\",\"obfuscation\":\"EAdvUfYaysnNd3\",\"output_index\":0,\"sequence_number\":3}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.function_call_arguments.delta\",\"delta\":\"city\",\"item_id\":\"fc_0f8d81b5d3287513016a01389815f081a2a68583ed9b19c405\",\"obfuscation\":\"b0QWJJlscLyl\",\"output_index\":0,\"sequence_number\":4}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.function_call_arguments.delta\",\"delta\":\"\\\":\\\"\",\"item_id\":\"fc_0f8d81b5d3287513016a01389815f081a2a68583ed9b19c405\",\"obfuscation\":\"m5EV1wzceCkjb\",\"output_index\":0,\"sequence_number\":5}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.function_call_arguments.delta\",\"delta\":\"Paris\",\"item_id\":\"fc_0f8d81b5d3287513016a01389815f081a2a68583ed9b19c405\",\"obfuscation\":\"QM3FjPoN9Gi\",\"output_index\":0,\"sequence_number\":6}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.function_call_arguments.delta\",\"delta\":\"\\\"}\",\"item_id\":\"fc_0f8d81b5d3287513016a01389815f081a2a68583ed9b19c405\",\"obfuscation\":\"lug74orAYXtg0e\",\"output_index\":0,\"sequence_number\":7}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.function_call_arguments.done\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"item_id\":\"fc_0f8d81b5d3287513016a01389815f081a2a68583ed9b19c405\",\"output_index\":0,\"sequence_number\":8}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.output_item.done\",\"item\":{\"id\":\"fc_0f8d81b5d3287513016a01389815f081a2a68583ed9b19c405\",\"type\":\"function_call\",\"status\":\"completed\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"call_id\":\"call_wRJoUdcb6w5SIpieBFOKxF6z\",\"name\":\"get_weather\"},\"output_index\":0,\"sequence_number\":9}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.completed\",\"response\":{\"id\":\"resp_0f8d81b5d3287513016a013897415481a28585571d6710366f\",\"object\":\"response\",\"created_at\":1778464919,\"status\":\"completed\",\"background\":false,\"completed_at\":1778464920,\"error\":null,\"frequency_penalty\":0.0,\"incomplete_details\":null,\"instructions\":null,\"max_output_tokens\":80,\"max_tool_calls\":null,\"model\":\"gpt-4.1-mini-2025-04-14\",\"moderation\":null,\"output\":[{\"id\":\"fc_0f8d81b5d3287513016a01389815f081a2a68583ed9b19c405\",\"type\":\"function_call\",\"status\":\"completed\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\",\"call_id\":\"call_wRJoUdcb6w5SIpieBFOKxF6z\",\"name\":\"get_weather\"}],\"parallel_tool_calls\":true,\"presence_penalty\":0.0,\"previous_response_id\":null,\"prompt_cache_key\":null,\"prompt_cache_retention\":\"in_memory\",\"reasoning\":{\"effort\":null,\"summary\":null},\"safety_identifier\":null,\"service_tier\":\"default\",\"store\":false,\"temperature\":0.0,\"text\":{\"format\":{\"type\":\"text\"},\"verbosity\":\"medium\"},\"tool_choice\":\"auto\",\"tools\":[{\"type\":\"function\",\"description\":\"Get current weather for a city.\",\"name\":\"get_weather\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":true}],\"top_logprobs\":0,\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":{\"input_tokens\":69,\"input_tokens_details\":{\"cached_tokens\":0},\"output_tokens\":15,\"output_tokens_details\":{\"reasoning_tokens\":0},\"total_tokens\":84},\"user\":null,\"metadata\":{}},\"sequence_number\":10}"
+        }
+      ]
+    },
+    {
+      "transport": "websocket",
+      "open": {
+        "url": "wss://api.openai.com/v1/responses",
+        "headers": {}
+      },
+      "client": [
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.create\",\"model\":\"gpt-4.1-mini\",\"input\":[{\"role\":\"system\",\"content\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"},{\"role\":\"user\",\"content\":[{\"type\":\"input_text\",\"text\":\"What is the weather in Paris?\"}]},{\"type\":\"function_call\",\"call_id\":\"call_wRJoUdcb6w5SIpieBFOKxF6z\",\"name\":\"get_weather\",\"arguments\":\"{\\\"city\\\":\\\"Paris\\\"}\"},{\"type\":\"function_call_output\",\"call_id\":\"call_wRJoUdcb6w5SIpieBFOKxF6z\",\"output\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}],\"tools\":[{\"type\":\"function\",\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"store\":false,\"max_output_tokens\":80,\"temperature\":0}"
+        }
+      ],
+      "server": [
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.created\",\"response\":{\"id\":\"resp_0767cfe3f5d98b2a016a0138994258819485d082e5c78849a4\",\"object\":\"response\",\"created_at\":1778464921,\"status\":\"in_progress\",\"background\":false,\"completed_at\":null,\"error\":null,\"frequency_penalty\":0.0,\"incomplete_details\":null,\"instructions\":null,\"max_output_tokens\":80,\"max_tool_calls\":null,\"model\":\"gpt-4.1-mini-2025-04-14\",\"moderation\":null,\"output\":[],\"parallel_tool_calls\":true,\"presence_penalty\":0.0,\"previous_response_id\":null,\"prompt_cache_key\":null,\"prompt_cache_retention\":\"in_memory\",\"reasoning\":{\"effort\":null,\"summary\":null},\"safety_identifier\":null,\"service_tier\":\"auto\",\"store\":false,\"temperature\":0.0,\"text\":{\"format\":{\"type\":\"text\"},\"verbosity\":\"medium\"},\"tool_choice\":\"auto\",\"tools\":[{\"type\":\"function\",\"description\":\"Get current weather for a city.\",\"name\":\"get_weather\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":true}],\"top_logprobs\":0,\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":null,\"user\":null,\"metadata\":{}},\"sequence_number\":0}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.in_progress\",\"response\":{\"id\":\"resp_0767cfe3f5d98b2a016a0138994258819485d082e5c78849a4\",\"object\":\"response\",\"created_at\":1778464921,\"status\":\"in_progress\",\"background\":false,\"completed_at\":null,\"error\":null,\"frequency_penalty\":0.0,\"incomplete_details\":null,\"instructions\":null,\"max_output_tokens\":80,\"max_tool_calls\":null,\"model\":\"gpt-4.1-mini-2025-04-14\",\"moderation\":null,\"output\":[],\"parallel_tool_calls\":true,\"presence_penalty\":0.0,\"previous_response_id\":null,\"prompt_cache_key\":null,\"prompt_cache_retention\":\"in_memory\",\"reasoning\":{\"effort\":null,\"summary\":null},\"safety_identifier\":null,\"service_tier\":\"auto\",\"store\":false,\"temperature\":0.0,\"text\":{\"format\":{\"type\":\"text\"},\"verbosity\":\"medium\"},\"tool_choice\":\"auto\",\"tools\":[{\"type\":\"function\",\"description\":\"Get current weather for a city.\",\"name\":\"get_weather\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":true}],\"top_logprobs\":0,\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":null,\"user\":null,\"metadata\":{}},\"sequence_number\":1}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.output_item.added\",\"item\":{\"id\":\"msg_0767cfe3f5d98b2a016a01389b1434819493f3d33e0ec6973c\",\"type\":\"message\",\"status\":\"in_progress\",\"content\":[],\"role\":\"assistant\"},\"output_index\":0,\"sequence_number\":2}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.content_part.added\",\"content_index\":0,\"item_id\":\"msg_0767cfe3f5d98b2a016a01389b1434819493f3d33e0ec6973c\",\"output_index\":0,\"part\":{\"type\":\"output_text\",\"annotations\":[],\"logprobs\":[],\"text\":\"\"},\"sequence_number\":3}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.output_text.delta\",\"content_index\":0,\"delta\":\"Paris\",\"item_id\":\"msg_0767cfe3f5d98b2a016a01389b1434819493f3d33e0ec6973c\",\"logprobs\":[],\"obfuscation\":\"fWbkBKTZ5oG\",\"output_index\":0,\"sequence_number\":4}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.output_text.delta\",\"content_index\":0,\"delta\":\" is\",\"item_id\":\"msg_0767cfe3f5d98b2a016a01389b1434819493f3d33e0ec6973c\",\"logprobs\":[],\"obfuscation\":\"BGuPlDrPchXwG\",\"output_index\":0,\"sequence_number\":5}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.output_text.delta\",\"content_index\":0,\"delta\":\" sunny\",\"item_id\":\"msg_0767cfe3f5d98b2a016a01389b1434819493f3d33e0ec6973c\",\"logprobs\":[],\"obfuscation\":\"7THzde2pni\",\"output_index\":0,\"sequence_number\":6}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.output_text.delta\",\"content_index\":0,\"delta\":\".\",\"item_id\":\"msg_0767cfe3f5d98b2a016a01389b1434819493f3d33e0ec6973c\",\"logprobs\":[],\"obfuscation\":\"Eo38bSElfyNmljj\",\"output_index\":0,\"sequence_number\":7}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.output_text.done\",\"content_index\":0,\"item_id\":\"msg_0767cfe3f5d98b2a016a01389b1434819493f3d33e0ec6973c\",\"logprobs\":[],\"output_index\":0,\"sequence_number\":8,\"text\":\"Paris is sunny.\"}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.content_part.done\",\"content_index\":0,\"item_id\":\"msg_0767cfe3f5d98b2a016a01389b1434819493f3d33e0ec6973c\",\"output_index\":0,\"part\":{\"type\":\"output_text\",\"annotations\":[],\"logprobs\":[],\"text\":\"Paris is sunny.\"},\"sequence_number\":9}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.output_item.done\",\"item\":{\"id\":\"msg_0767cfe3f5d98b2a016a01389b1434819493f3d33e0ec6973c\",\"type\":\"message\",\"status\":\"completed\",\"content\":[{\"type\":\"output_text\",\"annotations\":[],\"logprobs\":[],\"text\":\"Paris is sunny.\"}],\"role\":\"assistant\"},\"output_index\":0,\"sequence_number\":10}"
+        },
+        {
+          "kind": "text",
+          "body": "{\"type\":\"response.completed\",\"response\":{\"id\":\"resp_0767cfe3f5d98b2a016a0138994258819485d082e5c78849a4\",\"object\":\"response\",\"created_at\":1778464921,\"status\":\"completed\",\"background\":false,\"completed_at\":1778464923,\"error\":null,\"frequency_penalty\":0.0,\"incomplete_details\":null,\"instructions\":null,\"max_output_tokens\":80,\"max_tool_calls\":null,\"model\":\"gpt-4.1-mini-2025-04-14\",\"moderation\":null,\"output\":[{\"id\":\"msg_0767cfe3f5d98b2a016a01389b1434819493f3d33e0ec6973c\",\"type\":\"message\",\"status\":\"completed\",\"content\":[{\"type\":\"output_text\",\"annotations\":[],\"logprobs\":[],\"text\":\"Paris is sunny.\"}],\"role\":\"assistant\"}],\"parallel_tool_calls\":true,\"presence_penalty\":0.0,\"previous_response_id\":null,\"prompt_cache_key\":null,\"prompt_cache_retention\":\"in_memory\",\"reasoning\":{\"effort\":null,\"summary\":null},\"safety_identifier\":null,\"service_tier\":\"default\",\"store\":false,\"temperature\":0.0,\"text\":{\"format\":{\"type\":\"text\"},\"verbosity\":\"medium\"},\"tool_choice\":\"auto\",\"tools\":[{\"type\":\"function\",\"description\":\"Get current weather for a city.\",\"name\":\"get_weather\",\"parameters\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false},\"strict\":true}],\"top_logprobs\":0,\"top_p\":1.0,\"truncation\":\"disabled\",\"usage\":{\"input_tokens\":99,\"input_tokens_details\":{\"cached_tokens\":0},\"output_tokens\":6,\"output_tokens_details\":{\"reasoning_tokens\":0},\"total_tokens\":105},\"user\":null,\"metadata\":{}},\"sequence_number\":11}"
+        }
+      ]
+    }
+  ]
+}

packages/llm/test/provider/anthropic-messages.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect } from "bun:test"
 import { Effect } from "effect"
-import { CacheHint, LLM, LLMError } from "../../src"
+import { CacheHint, LLM, LLMError, Usage } from "../../src"
 import { LLMClient } from "../../src/route"
 import * as AnthropicMessages from "../../src/protocols/anthropic-messages"
 import { it } from "../lib/effect"
@@ -110,10 +110,11 @@ describe("Anthropic Messages route", () => {
       expect(response.text).toBe("Hello!")
       expect(response.reasoning).toBe("thinking")
       expect(response.usage).toMatchObject({
-        inputTokens: 5,
+        inputTokens: 6,
         outputTokens: 2,
+        nonCachedInputTokens: 5,
         cacheReadInputTokens: 1,
-        totalTokens: 7,
+        totalTokens: 8,
       })
       expect(response.events.find((event) => event.type === "reasoning-end")).toMatchObject({
         providerMetadata: { anthropic: { signature: "sig_1" } },
@@ -152,7 +153,13 @@ describe("Anthropic Messages route", () => {
         {
           type: "request-finish",
           reason: "tool-calls",
-          usage: { inputTokens: 5, outputTokens: 1, totalTokens: 6, native: { input_tokens: 5, output_tokens: 1 } },
+          usage: new Usage({
+            inputTokens: 5,
+            outputTokens: 1,
+            nonCachedInputTokens: 5,
+            totalTokens: 6,
+            providerMetadata: { anthropic: { input_tokens: 5, output_tokens: 1 } },
+          }),
         },
       ])
     }),

packages/llm/test/provider/gemini.test.ts

@@ -1,6 +1,6 @@
 import { describe, expect } from "bun:test"
 import { Effect } from "effect"
-import { LLM, LLMError } from "../../src"
+import { LLM, LLMError, Usage } from "../../src"
 import { LLMClient } from "../../src/route"
 import * as Gemini from "../../src/protocols/gemini"
 import { it } from "../lib/effect"
@@ -198,9 +198,10 @@ describe("Gemini route", () => {
       expect(response.reasoning).toBe("thinking")
       expect(response.usage).toMatchObject({
         inputTokens: 5,
-        outputTokens: 2,
-        reasoningTokens: 1,
+        outputTokens: 3,
+        nonCachedInputTokens: 4,
         cacheReadInputTokens: 1,
+        reasoningTokens: 1,
         totalTokens: 7,
       })
       expect(response.events).toEqual([
@@ -210,20 +211,23 @@ describe("Gemini route", () => {
         {
           type: "request-finish",
           reason: "stop",
-          usage: {
+          usage: new Usage({
             inputTokens: 5,
-            outputTokens: 2,
-            reasoningTokens: 1,
+            outputTokens: 3,
+            nonCachedInputTokens: 4,
             cacheReadInputTokens: 1,
+            reasoningTokens: 1,
             totalTokens: 7,
-            native: {
-              promptTokenCount: 5,
-              candidatesTokenCount: 2,
-              totalTokenCount: 7,
-              thoughtsTokenCount: 1,
-              cachedContentTokenCount: 1,
+            providerMetadata: {
+              google: {
+                promptTokenCount: 5,
+                candidatesTokenCount: 2,
+                totalTokenCount: 7,
+                thoughtsTokenCount: 1,
+                cachedContentTokenCount: 1,
+              },
             },
-          },
+          }),
         },
       ])
     }),
@@ -257,12 +261,13 @@ describe("Gemini route", () => {
         {
           type: "request-finish",
           reason: "tool-calls",
-          usage: {
+          usage: new Usage({
             inputTokens: 5,
             outputTokens: 1,
+            nonCachedInputTokens: 5,
             totalTokens: 6,
-            native: { promptTokenCount: 5, candidatesTokenCount: 1 },
-          },
+            providerMetadata: { google: { promptTokenCount: 5, candidatesTokenCount: 1 } },
+          }),
         },
       ])
     }),

packages/llm/test/provider/openai-chat.test.ts

@@ -1,7 +1,7 @@
 import { describe, expect } from "bun:test"
 import { Effect, Schema, Stream } from "effect"
 import { HttpClientRequest } from "effect/unstable/http"
-import { LLM, LLMError } from "../../src"
+import { LLM, LLMError, Usage } from "../../src"
 import * as Azure from "../../src/providers/azure"
 import * as OpenAI from "../../src/providers/openai"
 import * as OpenAIChat from "../../src/protocols/openai-chat"
@@ -230,20 +230,23 @@ describe("OpenAI Chat route", () => {
         {
           type: "request-finish",
           reason: "stop",
-          usage: {
+          usage: new Usage({
             inputTokens: 5,
             outputTokens: 2,
-            reasoningTokens: 0,
+            nonCachedInputTokens: 4,
             cacheReadInputTokens: 1,
+            reasoningTokens: 0,
             totalTokens: 7,
-            native: {
-              prompt_tokens: 5,
-              completion_tokens: 2,
-              total_tokens: 7,
-              prompt_tokens_details: { cached_tokens: 1 },
-              completion_tokens_details: { reasoning_tokens: 0 },
+            providerMetadata: {
+              openai: {
+                prompt_tokens: 5,
+                completion_tokens: 2,
+                total_tokens: 7,
+                prompt_tokens_details: { cached_tokens: 1 },
+                completion_tokens_details: { reasoning_tokens: 0 },
+              },
             },
-          },
+          }),
         },
       ])
     }),

packages/llm/test/provider/openai-responses.test.ts

@@ -1,7 +1,7 @@
 import { describe, expect } from "bun:test"
 import { ConfigProvider, Effect, Layer, Stream } from "effect"
 import { Headers, HttpClientRequest } from "effect/unstable/http"
-import { LLM, LLMError } from "../../src"
+import { LLM, LLMError, Usage } from "../../src"
 import { Auth, LLMClient, RequestExecutor, WebSocketExecutor } from "../../src/route"
 import * as Azure from "../../src/providers/azure"
 import * as OpenAI from "../../src/providers/openai"
@@ -342,20 +342,23 @@ describe("OpenAI Responses route", () => {
           type: "request-finish",
           reason: "stop",
           providerMetadata: { openai: { responseId: "resp_1", serviceTier: "default" } },
-          usage: {
+          usage: new Usage({
             inputTokens: 5,
             outputTokens: 2,
-            reasoningTokens: 0,
+            nonCachedInputTokens: 4,
             cacheReadInputTokens: 1,
+            reasoningTokens: 0,
             totalTokens: 7,
-            native: {
-              input_tokens: 5,
-              output_tokens: 2,
-              total_tokens: 7,
-              input_tokens_details: { cached_tokens: 1 },
-              output_tokens_details: { reasoning_tokens: 0 },
+            providerMetadata: {
+              openai: {
+                input_tokens: 5,
+                output_tokens: 2,
+                total_tokens: 7,
+                input_tokens_details: { cached_tokens: 1 },
+                output_tokens_details: { reasoning_tokens: 0 },
+              },
             },
-          },
+          }),
         },
       ])
     }),
@@ -411,7 +414,13 @@ describe("OpenAI Responses route", () => {
         {
           type: "request-finish",
           reason: "tool-calls",
-          usage: { inputTokens: 5, outputTokens: 1, totalTokens: 6, native: { input_tokens: 5, output_tokens: 1 } },
+          usage: new Usage({
+            inputTokens: 5,
+            outputTokens: 1,
+            nonCachedInputTokens: 5,
+            totalTokens: 6,
+            providerMetadata: { openai: { input_tokens: 5, output_tokens: 1 } },
+          }),
         },
       ])
     }),

packages/llm/test/schema.test.ts

@@ -1,6 +1,7 @@
 import { describe, expect, test } from "bun:test"
 import { Schema } from "effect"
-import { ContentPart, LLMEvent, LLMRequest, ModelID, ModelLimits, ModelRef, ProviderID } from "../src/schema"
+import { ContentPart, LLMEvent, LLMRequest, ModelID, ModelLimits, ModelRef, ProviderID, Usage } from "../src/schema"
+import { ProviderShared } from "../src/protocols/shared"
 
 const model = new ModelRef({
   id: ModelID.make("fake-model"),
@@ -48,3 +49,30 @@ describe("llm schema", () => {
     expect(ContentPart.guards.media({ type: "text", text: "hi" })).toBe(false)
   })
 })
+
+describe("LLM.Usage", () => {
+  test("subtractTokens clamps non-sensical breakdowns to zero", () => {
+    // Defense against a provider reporting cached_tokens > prompt_tokens or
+    // reasoning_tokens > completion_tokens — the negative would otherwise
+    // round-trip through the pipeline and crash strict downstream schemas.
+    expect(ProviderShared.subtractTokens(5, 3)).toBe(2)
+    expect(ProviderShared.subtractTokens(5, 10)).toBe(0)
+    expect(ProviderShared.subtractTokens(5, undefined)).toBe(5)
+    expect(ProviderShared.subtractTokens(undefined, 3)).toBeUndefined()
+    expect(ProviderShared.subtractTokens(undefined, undefined)).toBeUndefined()
+  })
+
+  test("sumTokens returns undefined only when every input is undefined", () => {
+    expect(ProviderShared.sumTokens(1, 2, 3)).toBe(6)
+    expect(ProviderShared.sumTokens(1, undefined, 3)).toBe(4)
+    expect(ProviderShared.sumTokens(undefined, undefined, undefined)).toBeUndefined()
+    expect(ProviderShared.sumTokens()).toBeUndefined()
+  })
+
+  test("visibleOutputTokens clamps reasoning > output to zero", () => {
+    expect(new Usage({ outputTokens: 10, reasoningTokens: 4 }).visibleOutputTokens).toBe(6)
+    expect(new Usage({ outputTokens: 10 }).visibleOutputTokens).toBe(10)
+    expect(new Usage({ outputTokens: 4, reasoningTokens: 10 }).visibleOutputTokens).toBe(0)
+    expect(new Usage({}).visibleOutputTokens).toBe(0)
+  })
+})