Same Output, Different Path — Guarding Agent Trajectories with Invariants
When the default model changes, your final output can stay correct while the path your agent takes quietly shifts. Here is a trajectory regression harness built on recorded tool traces and deterministic invariants, with working code and measured numbers.
When Context Editing Made My Agent Re-run the Same Search — Field Notes on Clear Boundaries and Cache Invalidation
After turning on Context Editing to auto-clear tool results, the agent forgot what it had just read, re-ran the same tool, and the cache rebuilt every turn so costs went up. Field notes on instrumenting the silent regression and setting trigger, keep, and clear_at_least from measured data.
Generating localized App Store listing metadata within character limits using the Claude API
Raw translations overflow App Store Connect's character limits. Generate per-locale listing metadata within them using Claude API structured output and a repair loop.
Putting a Ceiling on the pause_turn Loop: Running Long Server Tools Safely Unattended
A production design for continuing pause_turn safely in unattended runs, where long server tools like web_search and code execution are involved. Covers branching all four stop_reason values in one loop, capping continuations and wall-clock time, and accumulating usage across paused segments.
Don't Carry Search Results Twice: Trimming Consumed Blocks with response_inclusion
When an agent runs dynamic filtering, output tokens balloon because the raw search-result blocks a code execution call already consumed get echoed back into the response. Here is when response_inclusion: excluded is safe to use, when you must keep full, with implementation and a decision table.
Stabilizing Claude API Structured Responses in Production — Notes on tool_use, JSON Schema, and Layered Validation
Getting Claude to return JSON takes a few lines. Keeping that JSON usable in production is a different problem. Here is the layered design I landed on after running a wallpaper classification pipeline through Claude API, built around tool_use, JSON Schema, and domain validation.
Why tool_result could not be submitted Keeps Coming Back, and How to Build a Recovery Handler That Actually Holds
Run a Claude agent long enough and one day it starts: 'tool_result could not be submitted', back to back, and retries change nothing. The error message hides four completely different root causes. Here is what I learned debugging this across the six auto-publishing pipelines I run as an indie developer, with the TypeScript recovery handler I now ship in production.
Compressing Tool Results in Claude Agents — Aggregating Large Responses Without Bloating Context
When a database returns 8,000 rows, a scrape returns 200KB of HTML, or a file read returns several megabytes, dropping the raw payload into your Claude tool result wrecks both cost and quality. This guide presents a three-layer compression architecture — schema projection, summarization, and reference handles — with TypeScript examples from a production agent pipeline.
Debugging Claude API Tool Use Schema Errors: 3 Patterns I've Hit and How to Fix Them
A practical guide to diagnosing Claude API Tool Use errors—from schema definition mistakes to invalid_tool_use blocks and Claude ignoring your tools entirely. Based on real implementation experience.
Type-Safe Claude API Tool Calling with Zod: Patterns for TypeScript Developers
How to implement Claude API tool calling with TypeScript and Zod for full type safety. Covers schema-to-API conversion, runtime validation, and three common pitfalls with practical code examples.
Claude API × Python in Practice: Building an AI Assistant with Tool Calling and Streaming
A practical guide to combining Claude API's Tool Use and Streaming in Python. Build a working AI assistant with real tool execution, complete source code included, plus a breakdown of the tricky parts that trip up most developers.
Let Claude Diagnose Its Own Tool Errors — Building a Self-Correction Loop with the Anthropic API
Learn how to handle Tool Use failures gracefully by feeding error details back to Claude using the is_error flag, enabling self-diagnosis and automatic retry. Includes working Python code and production antipatterns to avoid.