Docs search: logs / Claude Code source intelligence

optimizing-for-cost-and-intelligence Claude Developer Platform · in the page about-claude/models/optimizing-for-cost-and-intelligence …too. The method stays the same: 1. Pull a few tasks from production logs, weighted like real traffic, and [write outcome checks](https://platform.claude.com/docs/en/test-and-evaluate/develop-tests)…

legal-summarization Claude Developer Platform · in the page about-claude/use-case-guides/legal-summarization …ls are available in the [AWS launch blog](https://aws.amazon.com/blogs/machine-learning/fine-tune-anthropics-claude-3-haiku-in-amazon-bedrock-to-boost-model-accuracy-and-quality/) . </Tip> <Ca…

deploy-helm Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/deploy-helm …ed-mcp-servers) for the request shapes. If that fails, check the pod logs (`kubectl -n mcp-tunnel logs deploy/mcp-tunnel -c mcp-proxy` and `-c cloudflared`) and consult [Troubleshooting](https://plat…

quickstart Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/quickstart …> ```bash docker compose up -d docker compose logs mcp-proxy | grep "route configured" docker compose logs cloudflared | grep "Registered tunnel connection" ```…

security Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/security …/mcp-tunnels/concepts#components)'s primary SSRF defense. * **Monitor logs.** Alert on warnings, errors, and unusual traffic patterns from the tunnel stack. * **Rotate credentials.** Rotate the server…

troubleshooting Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/troubleshooting ….claude.com/docs/en/agents-and-tools/mcp-tunnels/concepts#components) logs `No ingress rules were defined` | cloudflared has no local target.…

browser-use-sdk Claude Developer Platform · in the page agents-and-tools/tool-use/browser-use-sdk …'t include a URL, and a line for each of the first three dismissed dialogs, then a count of any others. When any tab is open, exactly one must be active. Every member that takes a `tab_id` must act o…

browser-use-tool Claude Developer Platform · in the page agents-and-tools/tool-use/browser-use-tool …_network` because not every browser automation stack can supply those logs and they widen what page-controlled content reaches Claude. Enable each one with `configs` (for example, `"configs": {"file_u…

computer-use-tool Claude Developer Platform · in the page agents-and-tools/tool-use/computer-use-tool …Always carefully review and verify Claude's computer use actions and logs. Do not use Claude for tasks requiring perfect precision or sensitive user information without human oversight. ## Data rete…

Process results programmatically Claude Developer Platform · in the page agents-and-tools/tool-use/programmatic-tool-calling …Data filtering ```python server_id = "srv-01" log_text = await fetch_logs({"server_id": server_id}) errors = [line for line in log_text.splitlines() if "ERROR" in line] print(f"Found {len(errors)} er…

Log at info level Claude Developer Platform · in the page agents-and-tools/tool-use/tool-runner …ython, its type and message), not the full stack trace. What the SDK logs is language-specific. The Python SDK logs the full exception, including its stack trace, through the standard `logging` modul…

MCP Tunnels Claude Developer Platform · in the page api/beta/organization/mcp_tunnels …Exposed as `POST` so the token does not appear in intermediary access logs. ### Path parameters - `tunnel_id: string` ID of the Tunnel. ### Headers - `"anthropic-version": optional string` T…

Reveal Tunnel Token Claude Developer Platform · in the page api/beta/organization/mcp_tunnels/reveal_token …Exposed as `POST` so the token does not appear in intermediary access logs. ## Path parameters - `tunnel_id: string` ID of the Tunnel. ## Headers - `"anthropic-version": optional string` The…

Tunnels Claude Developer Platform · in the page api/beta/tunnels …. Exposed as POST so the token does not appear in intermediary access logs. ### Path parameters - `tunnel_id: string` ID of the tunnel (`tnl_...`). ### Headers - `"anthropic-version": optional…

Reveal Tunnel Token Claude Developer Platform · in the page api/beta/tunnels/reveal_token …. Exposed as POST so the token does not appear in intermediary access logs. ## Path parameters - `tunnel_id: string` ID of the tunnel (`tnl_...`). ## Headers - `"anthropic-version": optional st…

claude-in-amazon-bedrock Claude Developer Platform · in the page build-with-claude/claude-in-amazon-bedrock …ion.html). ## Monitoring and logging Claude in Amazon Bedrock emits logs to both CloudWatch and CloudTrail. Anthropic recommends retaining activity logs on at least a 30-day rolling basis to underst…

claude-in-microsoft-foundry Claude Developer Platform · in the page build-with-claude/claude-in-microsoft-foundry …r rates * **Azure Log Analytics:** Query and analyze request/response logs * **Cost Management:** Monitor and forecast costs associated with Claude usage Anthropic recommends logging your activity on…

claude-on-amazon-bedrock-legacy Claude Developer Platform · in the page build-with-claude/claude-on-amazon-bedrock-legacy …roducing Claude Sonnet 4.5 in Amazon Bedrock](https://aws.amazon.com/blogs/aws/introducing-claude-sonnet-4-5-in-amazon-bedrock-anthropics-most-intelligent-model-best-for-coding-and-complex-agents/) *…

claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …n this directory." * "Review progress.txt, tests.json, and the git logs." * "Manually run through a fundamental integration test before moving on to implementing new features." 5. **Provide ver…

thinking-troubleshooting Claude Developer Platform · in the page build-with-claude/thinking-troubleshooting …lock that is missing or out of order. That sentence is for people and logs. Its wording can change, so don't match on it in code. If the message stops after ``Invalid `signature` in `thinking` block`…

typescript Claude Developer Platform · in the page cli-sdks-libraries/sdks/typescript …might still be visible. #### Custom logger By default, this library logs to `globalThis.console`. You can also provide a custom logger. Most logging libraries are supported, including [pino](https:/…

access-transparency Claude Developer Platform · in the page manage-claude/access-transparency …gardless of whether Access Transparency is enabled. ### CMEK key-use logs are not a per-read record For organizations that also enable CMEK, your cloud KMS audit log (CloudTrail, Cloud Audit Logs, o…

cmek Claude Developer Platform · in the page manage-claude/cmek …performs against your key are recorded in your cloud provider's audit logs. The use of CMEK is optional. Eligible organizations can **opt in** to use customer-managed encryption keys instead of the d…

cmek-google-cloud-kms Claude Developer Platform · in the page manage-claude/cmek-google-cloud-kms …(`roles/cloudkms.admin` or equivalent). * Cloud KMS Data Access audit logs (Data Read and Data Write) turned on for the project, so that Cloud Logging records Anthropic's use of your key. They're off…

compliance-api Claude Developer Platform · in the page manage-claude/compliance-api …lap with the Compliance API; here is how to choose. ### Export audit logs The audit log export is a separate feature in [claude.ai > Organization settings > Data and privacy](https://claude.ai/admin…

before_id is the first_id from a previous response Claude Developer Platform · in the page manage-claude/compliance-integration-patterns …| | `actor.ip_address` | Network, VPN, and endpoint logs | | `actor.user_agent` | Endpoint and device inventory, and the client app that ma…

user-profiles-verification-portal Claude Developer Platform · in the page manage-claude/user-profiles-verification-portal …Verification Portal at `portal.anthropic.com`. After the end customer logs in, the portal shows them the name of your Anthropic organization and the profile's ID. <Steps> <Step title="Log in">…

workload-identity-federation Claude Developer Platform · in the page manage-claude/workload-identity-federation …Run `ant auth status` from inside the workload (or inspect SDK debug logs). Because `ANTHROPIC_API_KEY` sits above the federation tiers in the precedence chain, the API key still wins at this stage.…

secure-deployment Claude Developer Platform · in the page managed-agents/secure-deployment …ck of why it went idle. Store the events you want to keep in your own logs, and delete sessions you no longer need | [Security risks and sandbox boundaries](https://platf…

secure-deployment-monitoring Claude Developer Platform · in the page managed-agents/secure-deployment-monitoring …keeps its history. To keep a session's events, copy them to your own logs with the events API before you delete it. A `running` session cannot be deleted. See [Deleting a session](https://platform.cl…

spawn.sh: called once per claimed work item Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes …file is still gone; in log-only mode it runs the same checks but only logs what it would have deleted, which lets you watch what your workers would delete before you trust the enabled mode; when disab…

self-hosted-sandboxes-memory Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-memory …MemorySyncDeletionsLogOnly`) | Runs the same checks but only logs what it would have deleted. Use it to watch what your workers would delete before you trust the enabled mode. | | `"disabled"…

self-hosted-sandboxes-operations Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-operations …tions#read-queue-depth). ### Memory stores fail to mount The worker logs mount and background sync failures rather than reporting them to the session. Only read-only refusals reach the agent, as too…

overview Claude Developer Platform · in the page release-notes/overview …to dynamically discover and load tools on-demand from large tool catalogs. * We've launched the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) in public beta for Cla…

claude-opus-4-7 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-7 …s from tools to answer rather than making the person look through the logs themselves. When a tool returns results, Claude uses those results to answer. Completeness here is about covering what was as…

Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …vice still refuses WSL sessions, open **Help > Troubleshooting > Show Logs in File Explorer** in Claude Desktop on that device, which saves a copy of its log folder to Downloads. Search `main.log` in…

Give Claude custom tools Claude Code CLI · in the page agent-sdk/custom-tools …path; in Python, the SDK drops audio blocks from the tool result and logs a warning. Claude receives each resource link block as a text block containing the link's name, URI, and description. In Typ…

Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …on](/docs/en/agent-sdk/python#hookinput) SDK references. This example logs a summary each time a subagent completes: ```python Python theme={null} async def subagent_tracker(input_data, tool_use_id,…

Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …gress proxy that enforces domain allowlists, injects credentials, and logs requests. See [Secure Deployment](/docs/en/agent-sdk/secure-deployment) for the full pattern. For inbound traffic, expose an…

Connect to external tools with MCP Claude Code CLI · in the page agent-sdk/mcp …* Pre-warming the server before starting your agent * Checking server logs for slow initialization causes In TypeScript, you can set the tool-call limit for a single [SDK MCP server](#sdk-mcp-servers…

Modifying system prompts Claude Code CLI · in the page agent-sdk/modifying-system-prompts …*: point [`ANTHROPIC_BASE_URL`](/docs/en/llm-gateway) at a proxy that logs request bodies. In a logged request, look in the `messages` array. A reminder appears inside a user message wrapped in `<sys…

Observability with OpenTelemetry Claude Code CLI · in the page agent-sdk/observability …ords for each prompt, API request, API error, and tool result | `OTEL_LOGS_EXPORTER` | | Traces | Spans for each interaction, model request, tool call, and hook (beta) | `OTEL_TRACES_EXPORTER` plus `C…

Agent SDK reference - Python Claude Code CLI · in the page agent-sdk/python …that blocks dangerous Bash commands like `rm -rf /`, and another that logs all tool usage for auditing. The security hook only runs on Bash commands (via the `matcher`), while the logging hook runs on…

Persist sessions to external storage Claude Code CLI · in the page agent-sdk/session-storage …e the original call may still land. If the batch still fails, the SDK logs the error, emits a `{ type: "system", subtype: "mirror_error" }` message into the iterator, drops the batch, and continues th…

Get structured output from agents Claude Code CLI · in the page agent-sdk/structured-outputs …esult you get when no attempt succeeds. If your application shows or logs tool calls, skip the ones named `StructuredOutput` so the mechanism doesn't appear as a step the agent chose. A `tool_result`…

Subagents in the SDK Claude Code CLI · in the page agent-sdk/subagents …within that subagent's execution context. The TypeScript version also logs the `agent_id` of each subagent message that carries one. ```python Python theme={null} import asyncio from claude_agent_sdk…

TypeScript SDK V2 session API (removed) Claude Code CLI · in the page agent-sdk/typescript-v2-preview …n, use `unstable_v2_prompt()`. This example sends a math question and logs the answer: ```typescript theme={null} import { unstable_v2_prompt } from "@anthropic-ai/claude-agent-sdk"; const result =…

Manage multiple agents with agent view Claude Code CLI · in the page agent-view …st work normally, since a human at the terminal can complete their dialogs. When nobody is attached, these commands can't open their dialogs, so the session appears under `Needs input` in agent view w…