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.
A Silent Drop to a Weaker Model Is Scarier Than an Error: Designing a Capability Floor for Claude API Fallback
When a model becomes unavailable in an unattended pipeline, automatically dropping to a weaker model is dangerous. Drawing on years of running automated indie pipelines, this is how to use per-task capability contracts and a degradation budget to decide where to stop.
Stop the Bill Before It Balloons: Designing API Key Blast Radius for Unattended Pipelines
Designing for leaks instead of pretending they won't happen: workspace-scoped keys, zero-downtime rotation, and a usage watchdog that flags spikes with a rolling baseline and median absolute deviation — wired into a scheduled run.
When Your Support AI Is Confidently Wrong in Production — Notes on Refusing Outside Its Grounding and Routing to Humans
A field-tested approach to the Claude API support agent that demos perfectly yet states non-existent facts in production. Covers deciding 'don't answer' at retrieval time, grounded generation, measuring confident-wrong rate, and tuning escalation precision.
I Edited One Line of a Tool Description and the Whole Prompt Cache Rebuilt — Where to Place cache_control Breakpoints
Hit rate suddenly flatlined at zero because a volatile block sat upstream of stable ones. This walks through how prefix-cache cascade invalidation works, how to reorder blocks from stable to volatile, and where to spend your four cache_control breakpoints — with code and decision tables.
When Stripe's Bill and Your Own Ledger Drift Apart: Field Notes on Metered Billing for Claude API
Usage-based billing for Claude API looks clean until month-end, when Stripe's total and your own usage ledger quietly disagree. Here are the field-tested patterns for idempotent meter events, reconciliation jobs, and pricing-change-proof credits.
My Morning Batch Was Missing the Prompt Cache Every Time — Warming Cadence and the Break-Even Math for the 1-Hour TTL
Jobs that run a few hours apart cold-miss the prompt cache even with a 1-hour TTL. Here is how to back out the right warming interval from the TTL, and how to write the break-even formula that decides whether warming pays off — with numbers from a four-site daily generation pipeline.
Claude API Streaming Breaks the "Everything Arrives" Assumption — Field Notes on Recovering from Partial Failure
Once concurrency climbs, Claude API streams disconnect mid-response, replay events, and emit half-finished tool arguments. Treating partial failure as the norm rather than an anomaly, here is how I rebuilt the implementation and monitoring to recover quietly.
Surviving the 90-Second Code Execution Cell Limit with Checkpointed Chunking
Claude's code execution tool now enforces a 90-second per-cell limit. Here is how to keep a long batch from getting cut off there: persist progress to the container filesystem and resume across cells, with working code for timing, idempotent checkpoints, and knowing when to offload.
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.
When Your Claude × Playwright Browser Agent Fails While Reporting Success — Verifying Actions and Catching UI Drift
A vision-driven Claude + Playwright browser agent fails quietly: it reports success while nothing actually changed. Here is how to stop trusting self-reports, verify each action against the goal, and detect UI drift before it breaks you.
When Your Claude API Response Cache Returns Stale Answers and Near-Miss Wrong Ones — Field Notes on Freshness and False-Hit Suppression
A Claude API response cache improves latency and cost immediately, but the problems that hurt in production are not average hit rate — they are stale hits and semantic false hits. Here is the key design, freshness management, false-hit suppression, and observability that keep a cache honest.