CATCH #1650
DETECTED SEP 25, 2026 22:21 UTC
THE CATCHscore 7/10
EXHIBIT 1650 · URGENT
Sep 25, 2026 22:21 UTC
github_releases+pages
anthropics/claude-code
Anthropic's Claude Code v2.1.283 release includes new prompt auditing tools, model management settings (availableModelsMatch, deniedModels), and a 'mantle' upstream provider for Amazon Bedrock.
READY TO POST:
claude code just dropped v2.1.283! looks like new prompt auditing for older models and more control over which models are used with `availableModelsMatch` and `deniedModels`.
anthropic's claude code v2.1.283 release adds a 'mantle' upstream provider for amazon bedrock, plus new gateway hint headers for grouping user prompts.
EVIDENCE — the receipts
[MERGED across 2 sources: github_releases, pages]
shared signal: claude-code, claude-code-prompt-id
--- github_releases :: anthropics/claude-code ---
anthropics/claude-code release: v2.1.283
name: v2.1.283
published: 2026-09-25T21:50:12Z
url: https://github.com/anthropics/claude-code/releases/tag/v2.1.283
## What's changed
- Added `x-claude-code-prompt-id` to the gateway hint headers so LLM gateways can group the requests that serve one user prompt; opt in with `CLAUDE_CODE_GATEWAY_HINT_HEADERS=1`
- Added `availableModelsMatch` managed setting: with `"exact"`, an `availableModels` entry allows only the model version it names, so new releases stay blocked until listed
- Added `deniedModels` managed setting to block specific models, even when `availableModels` allows them
- Added MCP tool, WebFetch and WebSearch outputs to the `tool.output` OpenTelemetry span event when `OTEL_LOG_TOOL_CONTENT=1`
- Added `/doctor prompt-audit` (also `/checkup prompt-audit`) to audit your CLAUDE.md files, skills, agents and commands for prompting patterns written for older models
- Added click-to-expand for truncated messages from your other sessions in fullscreen mode
- Added `path` to `--plugin-dir` load-failure entries in the stream-json `system/init` `plugin_errors`, naming the directory that did not load
- Added an opt-in `load_test_mode` block to the Claude apps gateway config: requests are built and signed but not sent upstream, and clients get a canned reply, so a deployment can be load tested
- Added a `mantle` upstream provider to the Claude apps gateway for Amazon Bedrock's Mantle endpoint
- Fixed SDK sessions losing a deferred tool call or finished tool result when a turn ended early, a held approval prompt after a worker restart, and a non-streaming fallback's `result.usage`
- Fixed MCP progress notifications being discarded once a long-running tool call moved to the background; the background task now shows the latest progress
- Fixed stdio MCP servers being left runnin
caught by the 20-minute sweep ·
the live wire · all receipts