CLAUDE LABJP
2.1.278 — The auto mode classifier now runs server-side by default on the Claude API, Enterprise, Bedrock, Vertex and Foundry. You are not billed for the classifier, and /status gained an Auto mode server lineTASKOUT — The TaskOutput tool is gone. taskOutputMaxChars and TASK_MAX_OUTPUT_LENGTH no longer do anything, and background output is read with Read instead10/07 — The old management-configuration key spellings are accepted until noon PT on October 7, seventeen days from now. After that, entries that still use them stop working until you rewrite themBUNPANIC — Reports are coming in of the newest build crashing on launch alone. Earlier builds still run on the same machine, which points at the release rather than the environmentNEW — Deciding what belongs in Cowork and what belongs in Claude Code, using the approval boundary as the lineSONNET4.5 — A date in a deprecation table is a floor, not an end date. Sonnet 4.5 is still active and no deprecation notice has been posted2.1.278 — The auto mode classifier now runs server-side by default on the Claude API, Enterprise, Bedrock, Vertex and Foundry. You are not billed for the classifier, and /status gained an Auto mode server lineTASKOUT — The TaskOutput tool is gone. taskOutputMaxChars and TASK_MAX_OUTPUT_LENGTH no longer do anything, and background output is read with Read instead10/07 — The old management-configuration key spellings are accepted until noon PT on October 7, seventeen days from now. After that, entries that still use them stop working until you rewrite themBUNPANIC — Reports are coming in of the newest build crashing on launch alone. Earlier builds still run on the same machine, which points at the release rather than the environmentNEW — Deciding what belongs in Cowork and what belongs in Claude Code, using the approval boundary as the lineSONNET4.5 — A date in a deprecation table is a floor, not an end date. Sonnet 4.5 is still active and no deprecation notice has been posted
ARTICLES

All Articles

All (872) Claude AI (141) Claude Code (371) Cowork (63) API & SDK (297)
API & SDK/2026-08-01Advanced

Swapping Tools Mid-Conversation Without Losing Your Prompt Cache

Tools can now be added and removed between turns, but the tool block sits at the very front of the cache prefix. I measured 12 mutation patterns with fingerprints and built a stable-core plus volatile-tail registry with a guard that refuses unsafe changes.

API & SDK/2026-07-31Advanced

The 400-Character Preview That Was Still Holding On to a Megabyte

Truncating tool output in your own MCP server does not free the original. Node's sliced strings keep the parent alive. Here is the measured 13-character boundary, which flattening tricks actually work, and a heap-snapshot audit script that counts the retained parents for you.

API & SDK/2026-07-28Advanced

The Line That Disappears at 100K: Measuring What Tool-Output Spill Actually Keeps

When agent tool output passes 100,000 characters, the full text spills to a file and the model sees only a head-truncated preview. Here are measured survival rates from a real repository, and the output envelope I built to push decision-relevant lines to the front.

API & SDK/2026-07-26Advanced

Rebuilding a Remote MCP Server That Never Needed Mcp-Session-Id

The MCP spec release candidate drops the session header. Here is how I audited my own remote server for session coupling and moved it to signed cursors, with measurements.

API & SDK/2026-07-24Advanced

Running Four Sites From One Managed Agent Definition

A design for collapsing four near-identical Managed Agents into one base definition, using agent version pinning and session-local overrides — with a validated factory and the traps I hit along the way.

API & SDK/2026-07-24Advanced

When Memory Store Listings Returned Half the Rows: Migrating to agent-memory-2026-07-22

agent-memory-2026-07-22 changed memories.list: fixed ordering, stricter depth, segment-based path_prefix matching. How an audit quietly halved, an access layer that survives it, finding every call site with ast, and measured depth=1 traversal cost.

API & SDK/2026-07-19Advanced

When Prompt Caching Was On but the Bill Didn't Move — Field Notes on Instrumenting cache_read to Close the Hit-Rate Gap

You added cache_control but your Claude API bill barely changed. Before guessing at fixes, record cache_read and cache_creation on every request and split the hit-rate gap into three causes: non-deterministic prefixes, TTL expiry, and sub-threshold blocks.

API & SDK/2026-07-14Advanced

A Two-Stage Pre-Publish Gate for User-Facing AI Text in Consumer Apps

Design a two-stage pre-publish gate for short AI-generated text you ship to end users: a deterministic rule layer plus a Claude classifier, with fail-closed handling, generation-time vetting, and a cost model. Full implementation code included.

API & SDK/2026-07-13Advanced

Precision Lives in the Second Stage: Reranking a Personal Knowledge Search with Claude

Embedding search alone leaves 'semantically close but not the answer' passages at the top. This is a two-stage design that gathers candidates broadly, then lets Claude reorder them by answerability, with structured scoring, abstention, and a cost estimate.

API & SDK/2026-07-13Advanced

Coalescing Concurrent Claude API Calls: Single-Flight Against Duplicate Inference and Cache Stampede

A design for collapsing identical prompts that fire at the same instant into a single upstream Claude call, using single-flight (request coalescing). In-process and distributed implementations, jittered retries, and negative caching, with measured results.

API & SDK/2026-07-13Advanced

Full-Size or Downscaled? A Per-Image Resolution Rule for Opus 4.7's High-Resolution Vision

Opus 4.7 finally read the fine texture in my wallpapers, so I sent everything at full size. My weekly image tokens jumped 2.4x. Here is the preflight that decides resolution and model per image, with the measured savings.

API & SDK/2026-07-13Advanced

When Extended Thinking Flattened My Accuracy but Doubled the Bill — Field Notes on Measuring the Marginal Utility of Thinking Tokens

You pinned budget_tokens high 'to be safe,' accuracy barely moved, and the bill kept climbing. These field notes show how to ledger real thinking-token usage by p50/p95/hit-rate and measure how much accuracy each extra 1,000 thinking tokens actually buys.