fix: disable experimental API betas by default, reduce side query token usage, standardize Headers type (#281)

* fix: disable experimental API betas by default to prevent 500 errors

Tool search (defer_loading), global cache scope, and context management
betas require internal Anthropic server-side support. External accounts
receive 500 Internal Server Error when these are sent.

Set CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=true by default in the CLI
entrypoint. Users with internal access can opt back in with =false.

Also includes: cache key stability fixes (Sonnet 1M latch, system-before-
messages key ordering, resume fingerprint isMeta skip), sideQuery default
cleanup, and /dream command.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* refactor: standardize API headers to Headers type and enable tengu feature flags by default

* fix: address PR review — dream lock, MCP betas guard, redundant Partial

- Call recordConsolidation() programmatically in /dream instead of
  delegating to model prompt (unreliable)
- Add CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS guard to MCP entrypoint
  (was only in CLI entrypoint, causing 500s in MCP server mode)
- Remove redundant ? markers from SecretValueSource Partial<{}> type

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/services/api/claude.ts

@@ -1466,6 +1466,10 @@ async function* queryModel(
     }
   }
 
+  // Latch Sonnet 1M experiment at query start so mid-retry GB refreshes
+  // don't flip the beta header and bust the cache key.
+  const sonnet1mExpLatched = getSonnet1mExpTreatmentEnabled(options.model)
+
   const effort = resolveAppliedEffort(options.model, options.effortValue)
 
   if (feature('PROMPT_CACHE_BREAK_DETECTION')) {
@@ -1549,11 +1553,9 @@ async function* queryModel(
   const paramsFromContext = (retryContext: RetryContext) => {
     const betasParams = [...betas]
 
-    // Append 1M beta dynamically for the Sonnet 1M experiment.
-    if (
-      !betasParams.includes(CONTEXT_1M_BETA_HEADER) &&
-      getSonnet1mExpTreatmentEnabled(retryContext.model)
-    ) {
+    // Append 1M beta from the latched experiment state (computed once before
+    // the closure to avoid mid-retry GB flips changing the cache key).
+    if (!betasParams.includes(CONTEXT_1M_BETA_HEADER) && sonnet1mExpLatched) {
       betasParams.push(CONTEXT_1M_BETA_HEADER)
     }
 
@@ -1709,6 +1711,13 @@ async function* queryModel(
 
     return {
       model: normalizeModelStringForAPI(options.model),
+      // IMPORTANT: `system` must appear before `messages` in the object literal.
+      // JSON.stringify preserves insertion order. The native Bun attestation
+      // (Attestation.zig) overwrites the FIRST `cch=00000` sentinel in the
+      // serialized body. If `messages` is serialized first and conversation
+      // history contains this literal string, the wrong occurrence is replaced,
+      // producing a different system prompt on each request and breaking cache.
+      system,
       messages: addCacheBreakpoints(
         messagesForAPI,
         enablePromptCaching,
@@ -1718,7 +1727,6 @@ async function* queryModel(
         consumedPinnedEdits,
         options.skipCacheWrite,
       ),
-      system,
       tools: allTools,
       tool_choice: options.toolChoice,
       ...(useBetas && { betas: betasParams }),

src/services/api/codexShim.ts

@@ -563,7 +563,7 @@ export async function performCodexRequest(options: {
     throw APIError.generate(
       response.status, errorResponse,
       `Codex API error ${response.status}: ${errorBody}`,
-      response.headers as unknown as Record<string, string>,
+      response.headers as unknown as Headers,
     )
   }
 
@@ -646,7 +646,7 @@ export async function collectCodexCompletedResponse(
     if (event.event === 'response.failed') {
       const msg = event.data?.response?.error?.message ??
         event.data?.error?.message ?? 'Codex response failed'
-      throw APIError.generate(500, undefined, msg, {} as Record<string, string>)
+      throw APIError.generate(500, undefined, msg, new Headers())
     }
 
     if (
@@ -661,7 +661,7 @@ export async function collectCodexCompletedResponse(
   if (!completedResponse) {
     throw APIError.generate(
       500, undefined, 'Codex response ended without a completed payload',
-      {} as Record<string, string>,
+      new Headers(),
     )
   }
 
@@ -820,7 +820,7 @@ export async function* codexStreamToAnthropic(
     if (event.event === 'response.failed') {
       const msg = payload?.response?.error?.message ??
         payload?.error?.message ?? 'Codex response failed'
-      throw APIError.generate(500, undefined, msg, {} as Record<string, string>)
+      throw APIError.generate(500, undefined, msg, new Headers())
     }
   }
 

src/services/api/openaiShim.ts

@@ -41,6 +41,13 @@ import {
 import { sanitizeSchemaForOpenAICompat } from '../../utils/schemaSanitizer.js'
 import { redactSecretValueForDisplay } from '../../utils/providerProfile.js'
 
+type SecretValueSource = Partial<{
+  OPENAI_API_KEY: string
+  CODEX_API_KEY: string
+  GEMINI_API_KEY: string
+  GOOGLE_API_KEY: string
+}>
+
 const GITHUB_MODELS_DEFAULT_BASE = 'https://models.github.ai/inference'
 const GITHUB_API_VERSION = '2022-11-28'
 const GITHUB_429_MAX_RETRIES = 3
@@ -750,7 +757,7 @@ class OpenAIShimMessages {
           ? ` or place a Codex auth.json at ${credentials.authPath}`
           : ''
         const safeModel =
-          redactSecretValueForDisplay(request.requestedModel, process.env) ??
+          redactSecretValueForDisplay(request.requestedModel, process.env as SecretValueSource) ??
           'the requested model'
         throw new Error(
           `Codex auth is required for ${safeModel}. Set CODEX_API_KEY${authHint}.`,
@@ -941,13 +948,13 @@ class OpenAIShimMessages {
         response.status,
         errorResponse,
         `OpenAI API error ${response.status}: ${errorBody}${rateHint}`,
-        response.headers as unknown as Record<string, string>,
+        response.headers as unknown as Headers,
       )
     }
 
     throw APIError.generate(
       500, undefined, 'OpenAI shim: request loop exited unexpectedly',
-      {} as Record<string, string>,
+      new Headers(),
     )
   }