@askalf/dario 5.5.48 → 5.5.49

package/dist/cc-template.d.ts

@@ -505,38 +505,6 @@ export declare const EXTENDED_CACHE_TTL_BETA = "extended-cache-ttl-2025-04-11";
  * is off or the beta is already present.
  */
 export declare function withForced1hBeta(beta: string, env?: Record<string, string | undefined>): string;
-/**
- * Place CC-style prompt-cache breakpoints on the conversation. The system
- * prompt is already cached at build time (2 system breakpoints); this adds a
- * rolling breakpoint on the last user message plus an anchor on the previous
- * one — total 4, the Anthropic max.
- *
- * Placement mirrors a live capture of CC v2.1.203 (dario#678):
- *
- *  - Tools carry NO breakpoint. Real CC sends its tool array unstamped —
- *    Anthropic renders tools -> system -> messages, so the system breakpoints
- *    already cache the tools prefix. Stamping the last tool (pre-4.8.142) both
- *    diverged from CC's wire shape and spent the fourth slot the conversation
- *    anchor below needs.
- *
- *  - The rolling breakpoint goes on the last USER message, not the last
- *    message. CC skips trailing role:"system" injections (agent-type updates
- *    etc.); stamping "the last message" meant any turn ending in one wrote no
- *    conversation entry at all, and the next request re-paid the entire
- *    history as fresh input.
- *
- *  - The previous user message is anchored too. Anthropic's cache lookup
- *    walks back at most ~20 content blocks from a breakpoint; one parallel-
- *    tool turn (N tool_use + N tool_result blocks) can exceed that alone, and
- *    the rolling breakpoint then can't reach the prior turn's entry — the
- *    whole conversation re-bills at cache-WRITE cost every fan-out turn,
- *    which is the dario#678 burn ("read every file" sessions draining the
- *    Max window ~10x faster than direct CC). The anchor sits exactly where
- *    the previous request's rolling breakpoint was, so the lookup hits it
- *    positionally with no walk-back.
- *
- * Exported for unit testing.
- */
 export declare function applyCcPromptCaching(ccRequest: Record<string, unknown>, cacheControl: CacheControl): void;
 /**
  * Drop later tools whose exact name already appeared. Upstream rejects the

package/dist/cc-template.js

@@ -1446,6 +1446,13 @@ export function withForced1hBeta(beta, env = process.env) {
  *
  * Exported for unit testing.
  */
+/**
+ * A text block upstream treats as empty. `cache_control` on one of these is a
+ * hard 400, so breakpoint placement must skip them.
+ */
+function isEmptyTextBlock(block) {
+    return block?.type === 'text' && (typeof block.text !== 'string' || block.text === '');
+}
 export function applyCcPromptCaching(ccRequest, cacheControl) {
     // Tools — strip any stray client breakpoints (they'd count against the
     // 4-breakpoint budget) without mutating shared element objects
@@ -1475,7 +1482,18 @@ export function applyCcPromptCaching(ccRequest, cacheControl) {
             if (!Array.isArray(msg.content) || msg.content.length === 0)
                 continue;
             const blocks = msg.content;
-            blocks[blocks.length - 1] = { ...blocks[blocks.length - 1], cache_control: cacheControl };
+            // Walk back past empty text blocks. Upstream rejects the whole request
+            // with 400 "cache_control cannot be set for empty text blocks", so a
+            // trailing empty text block would otherwise kill every request from
+            // that turn onward (dario#1066). A turn with nothing else to stamp is
+            // skipped rather than stamped illegally — it keeps its cache entry via
+            // the next turn's anchor.
+            let bi = blocks.length - 1;
+            while (bi >= 0 && isEmptyTextBlock(blocks[bi]))
+                bi--;
+            if (bi < 0)
+                continue;
+            blocks[bi] = { ...blocks[bi], cache_control: cacheControl };
             stamped++;
         }
     }
@@ -1659,6 +1677,32 @@ export function buildCCRequest(clientBody, billingTag, cacheControl, identity, o
             }
         }
     }
+    // ── Drop empty text blocks from history ──
+    // Upstream rejects empty text blocks OUTRIGHT — stamped or not — and treats
+    // whitespace-only text the same way ("messages: text content blocks must be
+    // non-empty"; with a breakpoint on it, "cache_control cannot be set for
+    // empty text blocks"). One such block entering the transcript mid-run
+    // therefore killed every subsequent request of the session (dario#1066).
+    // Filtering here fixes the REQUEST, which no breakpoint guard can: skipping
+    // the stamp still leaves the illegal block on the wire.
+    for (const msg of messages) {
+        if (!Array.isArray(msg.content))
+            continue;
+        msg.content = msg.content.filter((b) => !(b.type === 'text' && (typeof b.text !== 'string' || b.text.trim() === '')));
+    }
+    // A USER turn left with no blocks is dropped — but only MID-conversation,
+    // where the API combines the now-adjacent same-role turns and where the
+    // #1066 session-killer lives (the empty turn sits in history, so every
+    // later request carries it). The FINAL turn is deliberately left in place
+    // per the dario#1033 decision below: popping it would expose the assistant
+    // turn behind it and convert an honest "content must contain at least one
+    // block" into a misleading prefill rejection.
+    for (let i = messages.length - 2; i >= 0; i--) {
+        const m = messages[i];
+        if (m.role === 'user' && Array.isArray(m.content) && m.content.length === 0) {
+            messages.splice(i, 1);
+        }
+    }
     // ── Drop trailing empty turns ──
     // An assistant turn that was thinking-only before the strip above becomes
     // content: []. Forwarding that shape makes Anthropic interpret the request

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@askalf/dario",
-  "version": "5.5.48",
+  "version": "5.5.49",
   "description": "Use your Claude Pro/Max subscription in any tool — Cursor, Cline, Aider, the Agent SDK, your scripts — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint.",
   "type": "module",
   "bin": {