CLAUDE LABJP
2.2553.0 — Claude Desktop and Cowork both shipped over the weekend. Connector and extension tools no longer fail when an optional argument is left outCOMPACT — The Messages API gained a compaction parameter. Behind the compact-2026-09-04 beta header, you can now compress a conversation on your own schedule10/07 — The old management-configuration key spellings are accepted until noon PT on October 7, sixteen days away. Move your fleet past 1.15200.0 before switching orgPluginSettings to the array formGH.LINK — Cowork shows the GitHub integration as authenticated, yet there is no way to use it: it never registers as a connectorNEW — You are paying for Pro but no charges appear in the Console. Here is where to lookKB5129195 — September Windows updates that stopped Cowork from reaching files are fixed by Microsoft KB5129195. No Claude Desktop update is needed2.2553.0 — Claude Desktop and Cowork both shipped over the weekend. Connector and extension tools no longer fail when an optional argument is left outCOMPACT — The Messages API gained a compaction parameter. Behind the compact-2026-09-04 beta header, you can now compress a conversation on your own schedule10/07 — The old management-configuration key spellings are accepted until noon PT on October 7, sixteen days away. Move your fleet past 1.15200.0 before switching orgPluginSettings to the array formGH.LINK — Cowork shows the GitHub integration as authenticated, yet there is no way to use it: it never registers as a connectorNEW — You are paying for Pro but no charges appear in the Console. Here is where to lookKB5129195 — September Windows updates that stopped Cowork from reaching files are fixed by Microsoft KB5129195. No Claude Desktop update is needed
ARTICLES

All Articles

All (872) Claude AI (141) Claude Code (371) Cowork (63) API & SDK (297)
API & SDK/2026-07-01Advanced

When the Model Survives but One Parameter Expires: A Dated Deprecation Calendar for Claude API Requests

Your model ID can stay valid while a parameter you pinned quietly reaches its sunset date and takes the batch down with it. Here is a design that breaks a request into parts, gives each part its own expiry date, and catches the problem before the call goes out — with working TypeScript and real operational numbers.

API & SDK/2026-07-01Advanced

When Claude API Document Extraction Is Confidently Wrong — Field Notes on Catching Silent Errors with Invariants

In structured extraction from invoices and contracts, the real danger isn't a crash — it's a value that's silently wrong while the schema validates and confidence reads high. Field notes on invariants, two-pass extraction, and tracking field-level error rates.

API & SDK/2026-07-01Intermediate

A Fail-Closed Model Pricing Registry So New Models Don't Quietly Break Your Cost Math

When Opus 4.8 and Haiku 4.5 landed in the Messages API, rates scattered across my code silently skewed the cost rollup. Here is how to centralize per-model rates and fail closed on unknown models, with complete working code.

API & SDK/2026-06-30Advanced

The Same 429 Wears a Different Face on Each Route: Running Claude Safely over Anthropic Direct and Azure Foundry

With Claude now generally available on Microsoft Foundry, a two-route setup is realistic even for solo developers. Here is how to fold the route-by-route differences in 429s and retry-after into one normalized error type and a single backoff policy.

API & SDK/2026-06-30Advanced

When a Tool Result Is Too Big and Melts Your Context Window: Designing Cursor-Based Pagination

When a list tool returns hundreds of rows at once, an agent's context can collapse in a single call. Here is a cursor-based pagination design that keeps tool output small and protects your token budget, with working code.

API & SDK/2026-06-29Advanced

Stop rebuilding intermediate files every request: reuse the Code Execution container to carry pipeline state

How to reuse the Code Execution container across requests by passing its container ID, so generated files and intermediate results carry over to the next step. Includes the execution-time billing trap and how to handle container_expired safely, with working code.

API & SDK/2026-06-29Advanced

Let Claude Actually See the Images Your Tools Return — Use Image Blocks in tool_result and Cut Tokens by Roughly 10x

Stuffing a base64 string into a tool_result makes the same image cost roughly 10–20x more tokens. Here is how to return it as an image content block instead, with SDK code, a token-cost estimate, and the gotchas I hit in production.

API & SDK/2026-06-29Advanced

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.

API & SDK/2026-06-28Advanced

Did That Post Actually Go Through? Safely Retrying an Interrupted MCP Write Without Double-Executing

When an MCP write tool call is interrupted by a dropped connection, you can't tell whether the server ran it. Here's why naive retries cause double-execution, and a working wrapper that uses idempotency keys and a reconcile read to retry safely — with examples from an unattended pipeline.

API & SDK/2026-06-28Advanced

Measure Streaming CPU and Dropped Chunks to Stabilize Long Batch Jobs

You start an overnight batch, and by morning only half of it finished. The culprits were CPU pinned during streaming and a quiet connection drop. Here is a monitor wrapper that measures stream CPU and throughput, and resumes from interruptions.

API & SDK/2026-06-28Advanced

Every Tool Call Succeeds, Yet Nothing Moves Forward: Detecting Stagnation in Unattended Agents

No errors, yet the agent keeps replaying the same move while your budget quietly drains. Here is how to detect a success-but-no-progress loop using a progress oracle and action fingerprints, with a working Python implementation that halts safely.

API & SDK/2026-06-28Advanced

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.