@theokit/sdk 5.10.0 → 5.11.0

package/CHANGELOG.md

@@ -1,5 +1,64 @@
 # Changelog
 
+## 5.11.0
+
+### Minor Changes
+
+- [#734](https://github.com/usetheokit/theokit-sdk/pull/734) [`1f04344`](https://github.com/usetheokit/theokit-sdk/commit/1f0434491b706f7ea97f53d998fc33b300af1c33) Thanks [@usetheodev](https://github.com/usetheodev)! - Prompt caching now turns on for Anthropic models, and the cache counters they report reach the
+  turn's usage.
+  
+  For a model id that starts with `anthropic/` or `claude` (after an optional `openrouter/`,
+  `vertex/` or `bedrock/` prefix),
+  the agent loop sends the system prompt as text blocks: the configured prompt first, marked with
+  `cache_control: { type: "ephemeral" }`, then the `<active-memory>` block when memory adds one. The
+  Anthropic client sends the blocks as they are, and the OpenRouter client sends them as `content`
+  parts of the `system` message, with `cache_control` on the cacheable part. Every other provider
+  still receives one string. Bedrock ids (`anthropic.claude-…`) are not matched,
+  and their bodies do not change. Vertex Anthropic ids (`vertex/anthropic/claude-…`) are matched
+  and get the same blocks; no live Vertex response was measured for this change.
+  
+  Things a caller can observe:
+  
+  - **Billing.** Anthropic charges cache writes at 1.25 times the input price and cache reads at 0.1
+    times. A run with a single turn whose system prompt is above the model's caching minimum pays
+    the write premium and never reads the prefix back.
+  - **Order.** For these models the memory block now comes after the configured prompt instead of
+    before it. On a client that joins the blocks into one string, the text is the same and the order
+    is reversed.
+  - **What still misses the cache.** The cached prefix is the whole assembled prompt, so `<memory>`
+    facts, resolved skills or context that change between turns change block 1 and miss.
+  - **Counters.** The Anthropic streaming client reads `cache_read_input_tokens` and
+    `cache_creation_input_tokens` from `message_start`, where Anthropic reports them; a value in
+    `message_delta` still wins when it is above zero, and a zero there leaves the `message_start`
+    value in place. The non-streaming parser shared by the Bedrock and Vertex Anthropic clients now
+    returns both counters too.
+  - **Cost on the chat-completions client.** `prompt_tokens` there already includes the cached
+    slice, and the client used to report it whole as `inputTokens` beside `cacheReadTokens`, so the
+    estimated cost charged every cached token twice (about 8 times too high on a cached
+    OpenRouter Anthropic turn). `inputTokens` is now the uncached portion, as on the Anthropic
+    client, and `prompt_tokens_details.cache_write_tokens` is read into `cacheWriteTokens`. A
+    native OpenAI chat-completions run with a cache hit reports a lower `inputTokens` and a lower
+    cost than before. When a usage object carries both the nested `prompt_tokens_details` counts and the
+    Anthropic-style top-level ones, the nested count wins and a top-level count fills a nested
+    zero, the rule `normalizeUsage` already applied; the stream client used to let the top-level
+    field win.
+  - **Budget trackers.** A `BudgetTracker`'s `input` event now carries the whole prompt:
+    `inputTokens` plus `cacheReadTokens` and `cacheWriteTokens`. On the chat-completions client this
+    keeps the count a tracker saw before `inputTokens` became the uncached portion. On the Anthropic
+    clients, which always reported the uncached portion, a cached turn now counts its cached tokens
+    against `maxTokens`, and `createUsdBudgetTracker` prices them at the input rate, so a cost cap
+    trips earlier than the provider's bill would.
+  - **Input tokens on the Anthropic stream.** `input_tokens` is read from `message_start` too, so a
+    stream whose `message_delta` carries only `output_tokens` reports its uncached input instead of
+    none. A value above zero in `message_delta` still replaces it; a `null` or a zero there leaves
+    the `message_start` count.
+  - **Malformed Anthropic frames.** A `content_block_start`, `content_block_delta` or
+    `message_delta` frame that is not valid JSON now fails the turn with a retryable `NetworkError`
+    (`code: "stream_malformed_frame"`) instead of being skipped, which finished the turn with text
+    or tool input missing. Any other malformed frame is still skipped and reported on the
+    diagnostics channel. The error message and the diagnostic line name the event and the frame's
+    length, never its body, which can hold model output or tool input.
+
 ## 5.10.0
 
 ### Minor Changes

package/dist/{agent-TLRURB7W.cjs → agent-5DOR5T3E.cjs}

@@ -1,8 +1,8 @@
 'use strict';
 
-var chunkCVEQ5366_cjs = require('./chunk-CVEQ5366.cjs');
+var chunk5OHB5HJF_cjs = require('./chunk-5OHB5HJF.cjs');
 require('./chunk-J6GXS5A2.cjs');
-require('./chunk-FR6COQXZ.cjs');
+require('./chunk-N7ZIPW2N.cjs');
 require('./chunk-BUUUWQMB.cjs');
 require('./chunk-L3C6CCBG.cjs');
 require('./chunk-KIKKTW5O.cjs');
@@ -12,7 +12,7 @@ require('./chunk-GHX4P3V2.cjs');
 require('./chunk-TMKTSYDS.cjs');
 require('./chunk-ZD66GFH5.cjs');
 require('./chunk-NQVWSSX2.cjs');
-require('./chunk-QY3CIMUV.cjs');
+require('./chunk-BZKF7TXX.cjs');
 require('./chunk-CQYBJOB2.cjs');
 require('./chunk-YJNYDJ2T.cjs');
 require('./chunk-WPO3VCY4.cjs');
@@ -49,6 +49,7 @@ require('./chunk-C7GKRGKN.cjs');
 require('./chunk-TY56BKSK.cjs');
 require('./chunk-MPR2ISL2.cjs');
 require('./chunk-J5623RIV.cjs');
+require('./chunk-NWS2CS3Y.cjs');
 require('./chunk-3EE6LVWT.cjs');
 require('./chunk-SGC7LSHF.cjs');
 require('./chunk-HU666T3Q.cjs');
@@ -64,7 +65,7 @@ require('./chunk-6LHQPOMI.cjs');
 
 Object.defineProperty(exports, "Agent", {
   enumerable: true,
-  get: function () { return chunkCVEQ5366_cjs.Agent; }
+  get: function () { return chunk5OHB5HJF_cjs.Agent; }
 });
-//# sourceMappingURL=agent-TLRURB7W.cjs.map
-//# sourceMappingURL=agent-TLRURB7W.cjs.map
+//# sourceMappingURL=agent-5DOR5T3E.cjs.map
+//# sourceMappingURL=agent-5DOR5T3E.cjs.map

package/dist/{agent-TLRURB7W.cjs.map → agent-5DOR5T3E.cjs.map}

@@ -1 +1 @@
-{"version":3,"sources":[],"names":[],"mappings":"","file":"agent-TLRURB7W.cjs"}
+{"version":3,"sources":[],"names":[],"mappings":"","file":"agent-5DOR5T3E.cjs"}

package/dist/{agent-XTLAVVYC.js → agent-GWKRARAL.js}

@@ -1,6 +1,6 @@
-export { Agent } from './chunk-RTE2DD4S.js';
+export { Agent } from './chunk-4PHSVR2R.js';
 import './chunk-XKMVJ443.js';
-import './chunk-EXI7EHDN.js';
+import './chunk-7Y23B7XX.js';
 import './chunk-K2BQQ445.js';
 import './chunk-DPY2M74T.js';
 import './chunk-ZHWKT2NI.js';
@@ -10,7 +10,7 @@ import './chunk-H73MEMQB.js';
 import './chunk-OR6XIWLB.js';
 import './chunk-X3LOJJMO.js';
 import './chunk-IZDDSLL2.js';
-import './chunk-EVH3OUMY.js';
+import './chunk-74OA5DIM.js';
 import './chunk-SUVCHX4L.js';
 import './chunk-2XC6KDJM.js';
 import './chunk-TE6XVTOA.js';
@@ -47,6 +47,7 @@ import './chunk-ZDYDBXSD.js';
 import './chunk-X7EUUHXU.js';
 import './chunk-MQGSOKR3.js';
 import './chunk-GMRFAX4I.js';
+import './chunk-LZJXEPEQ.js';
 import './chunk-R7WIIPUR.js';
 import './chunk-I2ORT6QD.js';
 import './chunk-SVCPJRUB.js';
@@ -57,5 +58,5 @@ import './chunk-H3CVJSFC.js';
 import './chunk-Q7GYMXVC.js';
 import './chunk-B5MHRQJZ.js';
 import './chunk-CZJ6Q7CW.js';
-//# sourceMappingURL=agent-XTLAVVYC.js.map
-//# sourceMappingURL=agent-XTLAVVYC.js.map
+//# sourceMappingURL=agent-GWKRARAL.js.map
+//# sourceMappingURL=agent-GWKRARAL.js.map

package/dist/{agent-XTLAVVYC.js.map → agent-GWKRARAL.js.map}

@@ -1 +1 @@
-{"version":3,"sources":[],"names":[],"mappings":"","file":"agent-XTLAVVYC.js"}
+{"version":3,"sources":[],"names":[],"mappings":"","file":"agent-GWKRARAL.js"}

package/dist/{chunk-RTE2DD4S.js → chunk-4PHSVR2R.js}

@@ -1,5 +1,5 @@
 import { submit, emitRunEvent } from './chunk-XKMVJ443.js';
-import { enqueueSessionWrite, hydrateSession, persistTurnToTranscript, flushSessionWrites, appendSessionMessage, getSessionMessages, discardSession, clearSession } from './chunk-EXI7EHDN.js';
+import { enqueueSessionWrite, hydrateSession, persistTurnToTranscript, flushSessionWrites, appendSessionMessage, getSessionMessages, discardSession, clearSession } from './chunk-7Y23B7XX.js';
 import { IndexManager } from './chunk-DPY2M74T.js';
 import { currentPersonalityContext, warnPersonalitySwitchInsideFork } from './chunk-ZHWKT2NI.js';
 import { extractCodePlugins } from './chunk-2SFBB54R.js';
@@ -7,7 +7,7 @@ import { createOpenAiCompatibleRuntime } from './chunk-HI3W37FY.js';
 import { persistActiveMemoryTranscript } from './chunk-OR6XIWLB.js';
 import { resolveMaxFacts, writeSessionSummary, resolveMemoryRoot, MEMORY_KINDS, appendFact, readFacts, legacyMemoryJsonPath, memoryMdPath, appendFactToMarkdown } from './chunk-X3LOJJMO.js';
 import { FsSessionStore } from './chunk-IZDDSLL2.js';
-import { discoverProviderPlugins, validateApiKeyShape, getConfiguredBaseUrl, httpRequest, isFixtureApiKey, presentProviderCredentialEnvVars, buildDefaultSummarizer, shouldUseRealLocalRuntime, parseSseStream, CircuitBreaker, resolveRunProvider, mergeExplicitApiKey, resolveProviderChain, abortError, tryFirstEvent, relayStream, renderToolResultContentText } from './chunk-EVH3OUMY.js';
+import { discoverProviderPlugins, validateApiKeyShape, getConfiguredBaseUrl, httpRequest, isFixtureApiKey, presentProviderCredentialEnvVars, buildDefaultSummarizer, shouldUseRealLocalRuntime, parseSseStream, CircuitBreaker, resolveRunProvider, mergeExplicitApiKey, resolveProviderChain, abortError, tryFirstEvent, relayStream, renderToolResultContentText } from './chunk-74OA5DIM.js';
 import { resolveChildEnv } from './chunk-HKCKOAIO.js';
 import { DEFAULT_MAX_BYTES_PER_FILE, runDiscovery, truncateWithMarker } from './chunk-7QJYKVP6.js';
 import { warnFailureOnce, loadHookConfig, warnOnce } from './chunk-OPAKPEPG.js';
@@ -29,6 +29,7 @@ import { loadSubagents, pluginBundleDirs } from './chunk-ZDYDBXSD.js';
 import { reportUndeclaredSources, theokitConfigRoot, undefinedVariablesIn, getTheokitHome, adapterForConfigPath, adaptersForSurface, projectConfigRoots, pluginBundleRoots } from './chunk-X7EUUHXU.js';
 import { readWorkspaceDir, parseSimpleYaml } from './chunk-MQGSOKR3.js';
 import { resolveEffectiveContextWindow, CONTEXT_WINDOW_FLOOR, CONTEXT_WINDOW_MARGIN } from './chunk-GMRFAX4I.js';
+import { isAnthropicFamilyModel } from './chunk-LZJXEPEQ.js';
 import { parseModelId } from './chunk-R7WIIPUR.js';
 import { getProviderProfile } from './chunk-I2ORT6QD.js';
 import { getCatalogModelInfo, isPatchedModelKey } from './chunk-SVCPJRUB.js';
@@ -5804,14 +5805,27 @@ function stripThinkBlocks(content) {
 // src/internal/agent-loop/loop-llm-stream.ts
 function resolveSystemPromptWithMemoryAdditions(systemPrompt, additions) {
   if (additions === void 0 || additions.length === 0) return systemPrompt;
-  const block = `<active-memory>
-${escapeBlockBody(additions)}
-</active-memory>`;
+  const block = activeMemoryBlock(additions);
   if (systemPrompt === void 0 || systemPrompt.length === 0) return block;
   return `${block}
 
 ${systemPrompt}`;
 }
+function activeMemoryBlock(additions) {
+  return `<active-memory>
+${escapeBlockBody(additions)}
+</active-memory>`;
+}
+function buildLoopSystem(systemPrompt, additions, modelId) {
+  if (!isAnthropicFamilyModel(modelId) || systemPrompt === void 0 || systemPrompt.length === 0) {
+    return resolveSystemPromptWithMemoryAdditions(systemPrompt, additions);
+  }
+  const blocks = [{ text: systemPrompt, cacheable: true }];
+  if (additions !== void 0 && additions.length > 0) {
+    blocks.push({ text: activeMemoryBlock(additions) });
+  }
+  return blocks;
+}
 function toLlmTool(tool) {
   return { name: tool.name, description: tool.description, inputSchema: tool.inputSchema };
 }
@@ -5850,9 +5864,10 @@ async function streamLlmTurn(inputs, ctx) {
     {
       model: inputs.model.id ?? "auto",
       ...(() => {
-        const effective = resolveSystemPromptWithMemoryAdditions(
+        const effective = buildLoopSystem(
           inputs.systemPrompt,
-          ctx.memorySystemPromptAdditions
+          ctx.memorySystemPromptAdditions,
+          inputs.model.id
         );
         return effective !== void 0 ? { system: effective } : {};
       })(),
@@ -6839,29 +6854,32 @@ async function runIteration(inputs, ctx) {
   const llmOutput = await streamLlmTurn(inputs, ctx);
   await inputs.pluginManager?.runPostLlmCallHooks(hookCtx);
   accumulateUsage(ctx.usage, llmOutput);
-  if (inputs.budgetTracker !== void 0) {
-    const modelId = inputs.model.id ?? "auto";
-    const inputT = llmOutput.inputTokens ?? 0;
-    const outputT = llmOutput.outputTokens ?? 0;
-    try {
-      if (inputT > 0) {
-        inputs.budgetTracker.track({
-          tokens: inputT,
-          model: modelId,
-          type: "input"
-        });
-      }
-      if (outputT > 0) {
-        inputs.budgetTracker.track({
-          tokens: outputT,
-          model: modelId,
-          type: "output"
-        });
-      }
-    } catch {
+  trackTurnUsage(inputs, llmOutput);
+  return continueOrTerminate(inputs, ctx, llmOutput);
+}
+function trackTurnUsage(inputs, llmOutput) {
+  const tracker = inputs.budgetTracker;
+  if (tracker === void 0) return;
+  const modelId = inputs.model.id ?? "auto";
+  const inputT = (llmOutput.inputTokens ?? 0) + (llmOutput.cacheReadTokens ?? 0) + (llmOutput.cacheWriteTokens ?? 0);
+  const outputT = llmOutput.outputTokens ?? 0;
+  try {
+    if (inputT > 0) {
+      tracker.track({
+        tokens: inputT,
+        model: modelId,
+        type: "input"
+      });
+    }
+    if (outputT > 0) {
+      tracker.track({
+        tokens: outputT,
+        model: modelId,
+        type: "output"
+      });
     }
+  } catch {
   }
-  return continueOrTerminate(inputs, ctx, llmOutput);
 }
 async function transformLlmOutputText(inputs, text, ctx) {
   return inputs.pluginManager !== void 0 ? inputs.pluginManager.runTransformLlmOutputHooks(text, ctx) : text;
@@ -11066,7 +11084,7 @@ var Agent = class _Agent {
    */
   static async compact(agentId, options = {}) {
     const reg = await requireLocalAgent(agentId, "compact");
-    const { compactSessionTranscript, buildDefaultSummarizer: buildDefaultSummarizer2 } = await import('./compact-session-PVAWTKKL.js');
+    const { compactSessionTranscript, buildDefaultSummarizer: buildDefaultSummarizer2 } = await import('./compact-session-F2UDGZCN.js');
     const { cwd, model, store } = await openLocalStore(reg);
     return enqueueSessionWrite(
       cwd,
@@ -11096,7 +11114,7 @@ var Agent = class _Agent {
    */
   static async injectSessionTurn(agentId, turn) {
     const reg = await requireLocalAgent(agentId, "injectSessionTurn");
-    const { injectSessionTurn } = await import('./inject-session-O24XGRR6.js');
+    const { injectSessionTurn } = await import('./inject-session-E5UDFVLI.js');
     const { cwd, model, store } = await openLocalStore(reg);
     await injectSessionTurn({
       store,
@@ -11254,5 +11272,5 @@ async function openLocalStore(reg) {
 }
 
 export { Agent, AgentBuilder, DEFAULT_AGENTIC_MODEL_ID, MEMORY_EMBEDDING_ADAPTERS, Tool, ToolError, UsageAccumulator, computeCost, generateCronId, getPricingEntry, managedSettingsPathFor, openRouterMemoryEmbeddingProviderAdapter, readManagedSettings, resolveSessionDir };
-//# sourceMappingURL=chunk-RTE2DD4S.js.map
-//# sourceMappingURL=chunk-RTE2DD4S.js.map
+//# sourceMappingURL=chunk-4PHSVR2R.js.map
+//# sourceMappingURL=chunk-4PHSVR2R.js.map