Follow Discord
Sweep 22 Oct 2026 · 21:04Z Build v2.1.309 528 read Stable v2.1.308 Latest v2.1.309 Next v2.1.309 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI
One capture · claude-code

One read of Claude Code CLIclaude-code-20260827T183702Z

7 pages moved out of 191 read.

Pages moved 7 significant first
Pages read 191 in this capture
Captured 18:37 UTC
Corpus hash e540d09b5638 corpus-hash

What this read moved

1-7 of 7

agent-sdk/hosting Changed · +1 / -10 lines

from line 157
157157 
158158### Container-based sandboxing
159159 
160Run the SDK inside a sandboxed container for process isolation, resource limits, network control, and an ephemeral filesystem. Several providers specialize in sandboxed container environments that fit the Agent SDK's model.
160Run the SDK inside a sandboxed container for process isolation, resource limits, network control, and an ephemeral filesystem.
161161 
162162Questions to answer when choosing a provider:
163163 
from line 166
166166* **Persistent storage**: whether the provider offers durable volumes or only ephemeral disk. The hybrid pattern needs durable storage somewhere, whether in the sandbox or alongside it.
167167* **Pricing model**: per-second, per-request, or flat hourly billing. Per-second pricing suits bursty ephemeral workloads. Hourly suits long-running sessions.
168168* **Networking**: support for custom egress rules, outbound proxies, and private VPC peering for regulated environments.
169 
170Providers to evaluate:
171 
172* [Modal Sandbox](https://modal.com/docs/guide/sandbox), with a [demo implementation](https://modal.com/docs/examples/claude-slack-gif-creator)
173* [Cloudflare Sandboxes](https://github.com/cloudflare/sandbox-sdk)
174* [Daytona](https://www.daytona.io/)
175* [E2B](https://e2b.dev/)
176* [Fly Machines](https://fly.io/docs/machines/)
177* [Vercel Sandbox](https://vercel.com/docs/functions/sandbox)
178169 
179170For self-hosted options such as Docker, gVisor, and Firecracker, and detailed isolation configuration, see [Isolation Technologies](/docs/en/agent-sdk/secure-deployment#isolation-technologies).
180171 

agent-sdk/observability Changed · +2 / -3 lines

from line 9
99* how many tokens were spent
1010* where failures occurred
1111 
12The Agent SDK can export this data as OpenTelemetry traces, metrics, and log events to any backend that accepts the OpenTelemetry Protocol (OTLP), such as Honeycomb, Datadog, Grafana, Langfuse, or a self-hosted collector.
12The Agent SDK can export this data as OpenTelemetry traces, metrics, and log events to any backend that accepts the OpenTelemetry Protocol (OTLP), whether a hosted observability platform or a self-hosted collector.
1313 
1414This guide explains how the SDK emits telemetry, how to configure the export, and how to tag and filter the data once it reaches your backend. To read token usage and cost directly from the SDK response stream instead of exporting to a backend, see [Track cost and usage](/docs/en/agent-sdk/cost-tracking).
1515 
from line 105
105105 The `console` exporter writes telemetry to standard output, which the SDK uses
106106 as its message channel. Do not set `console` as an exporter value when running
107107 through the SDK. To inspect telemetry locally, point
108 `OTEL_EXPORTER_OTLP_ENDPOINT` at a local collector or an all-in-one Jaeger
109 container instead.
108 `OTEL_EXPORTER_OTLP_ENDPOINT` at a local OpenTelemetry Collector instead.
110109</Note>
111110 
112111### Flush telemetry from short-lived calls

monitoring-usage Changed · +8 / -8 lines

from line 1276
12761276 
12771277### For metrics
12781278 
1279* **Time series databases (for example, Prometheus)**: Rate calculations, aggregated metrics
1280* **Columnar stores (for example, ClickHouse)**: Complex queries, unique user analysis
1281* **Full-featured observability platforms (for example, Honeycomb, Datadog, Grafana Cloud)**: Advanced querying, visualization, alerting
1279* **Time series databases**: Rate calculations, aggregated metrics
1280* **Columnar stores**: Complex queries, unique user analysis
1281* **Full-featured observability platforms**: Advanced querying, visualization, alerting
12821282 
12831283### For events/logs
12841284 
1285* **Log aggregation systems (for example, Elasticsearch, Loki)**: Full-text search, log analysis
1286* **Columnar stores (for example, ClickHouse)**: Structured event analysis
1287* **Full-featured observability platforms (for example, Honeycomb, Datadog, Grafana Cloud)**: Correlation between metrics and events
1285* **Log aggregation systems**: Full-text search, log analysis
1286* **Columnar stores**: Structured event analysis
1287* **Full-featured observability platforms**: Correlation between metrics and events
12881288 
12891289### For traces
12901290 
12911291Choose a backend that supports distributed trace storage and span correlation:
12921292 
1293* **Distributed tracing systems (for example, Jaeger, Zipkin, Grafana Tempo)**: Span visualization, request waterfalls, latency analysis
1294* **Full-featured observability platforms (for example, Honeycomb, Datadog, Grafana Cloud)**: Trace search and correlation with metrics and logs
1293* **Distributed tracing systems**: Span visualization, request waterfalls, latency analysis
1294* **Full-featured observability platforms**: Trace search and correlation with metrics and logs
12951295 
12961296For organizations requiring Daily/Weekly/Monthly Active User (DAU/WAU/MAU) metrics, consider backends that support efficient unique value queries.
12971297 

permissions Changed · +10 / -4 lines

from line 116
116116 
117117### Match by input parameter
118118 
119Deny and ask rules can match a top-level input parameter on any tool with `Tool(param:value)`. The rule matches when Claude calls the tool with that parameter set to that exact value. An allow rule for one parameter value wouldn't establish that the call is safe overall, so allow rules continue to use each tool's own specifier syntax. This works for any scalar parameter the tool accepts:
119Deny and ask rules can match a top-level input parameter on any built-in tool with `Tool(param:value)`.
120120 
121To match a parameter on an MCP tool, pass a deny rule with [`--disallowedTools`](/docs/en/cli-reference#cli-flags). When Claude Code loads a settings file, it skips any `mcp__` rule that has parentheses. Claude Code lists the skipped rule in the invalid-settings dialog when an interactive session starts, and in [`claude doctor`](/docs/en/debug-your-config#check-resolved-settings) output.
122 
123A parameter rule matches when Claude calls the tool with that parameter set to that exact value. An allow rule for one parameter value wouldn't establish that the call is safe overall, so allow rules continue to use each tool's own specifier syntax. This works for any scalar parameter the tool accepts:
124 
121125| Rule | Matches |
122126| :----------------------------- | :------------------------------------------- |
123127| `Agent(model:opus)` | Agent calls that request the Opus model tier |
from line 334
330334| Local settings at `.claude/settings.local.json` | `<original cwd>/path` |
331335| User settings at `~/.claude/settings.json` | `~/.claude/path` |
332336| A file passed with `--settings <file>` | `<directory of file>/path` |
333| CLI flags, `/permissions`, or session rules | `<original cwd>/path` |
337| CLI flags or session rules | `<original cwd>/path` |
334338 
339A rule you add through `/permissions` follows the row for the settings file you save it to.
340 
335341Local settings rules anchor at the directory you started Claude Code from, not at the repository root where Claude Code [stores the file](#permission-system) in v2.1.211 and later. In a session started at the repository root, the two directories are the same; in a [worktree](/docs/en/worktrees) session, a shared rule such as `Edit(/src/**)` matches that worktree's own `src/` directory.
336342 
337343A deny rule such as `Read(/secrets/**)` in user settings blocks `~/.claude/secrets/**`, not a `secrets` directory in your project. To write a rule in user settings that applies inside every project, use a `//` absolute path or a `~/` home-relative path instead.
from line 606
600606| [Hooks](/docs/en/hooks) in settings files, the [`env`](/docs/en/settings-reference#env) block and helper commands such as [`apiKeyHelper`](/docs/en/settings-reference#apikeyhelper), and a project skill's [hooks](/docs/en/hooks#hooks-in-skills-and-agents) and [`allowed-tools`](/docs/en/skills#pre-approve-tools-for-a-skill) | Used | Used. Workspace trust never gates a skill's `allowed-tools` in any session |
601607| `permissions.allow` rules and `additionalDirectories` in `.claude/settings.json` | Not used until you accept the trust dialog, which appears again listing them | Not used. Claude Code prints a [`this workspace has not been trusted`](/docs/en/errors#workspace-has-not-been-trusted) warning to stderr |
602608| Frontmatter hooks in a project [subagent](/docs/en/sub-agents#hooks-in-subagent-frontmatter), a project [`@skills-dir` plugin](/docs/en/plugins-reference#skills-directory-plugins), and [`extraKnownMarketplaces`](/docs/en/settings-reference#extraknownmarketplaces) entries from the repository or an `--add-dir` directory | Not used, and no dialog is offered | Not used |
603| Inline [`mcpServers`](/docs/en/sub-agents#scope-mcp-servers-to-a-subagent) in the frontmatter of a subagent from the repository or an `--add-dir` directory | Not used, and no dialog is offered | Not used |
609| Inline [`mcpServers`](/docs/en/sub-agents#scope-mcp-servers-to-a-subagent) in the frontmatter of a subagent from the repository or an `--add-dir` directory. Before v2.1.238, Claude Code loaded these servers in both situations | Not used, and no dialog is offered | Not used |
604610| Servers in `.mcp.json`, including ones the repository [approves in its own settings](/docs/en/mcp#project-server-approvals-and-workspace-trust) | Claude Code asks you before connecting them. The repository's own approvals don't count | Connected without asking, approved or not. The SDK loads them only when `settingSources` includes project settings. `claude mcp list` in the same folder still reports such a server as pending |
605| A [`headersHelper`](/docs/en/mcp#trust-a-folder-before-its-headershelper-runs) on a server in `.mcp.json` | Not run until you accept the trust dialog, which appears again naming where the helper is declared. Claude Code connects the server with its static `headers` alone until then | Not run. Claude Code connects the server with its static `headers` alone and prints a [`headersHelper not run`](/docs/en/errors#headershelper-not-run) line per server to stderr |
611| A [`headersHelper`](/docs/en/mcp#trust-a-folder-before-its-headershelper-runs) on a server in `.mcp.json`. Before v2.1.238, Claude Code ran the helper in both situations | Not run until you accept the trust dialog, which appears again naming where the helper is declared. Claude Code connects the server with its static `headers` alone until then | Not run. Claude Code connects the server with its static `headers` alone and prints a [`headersHelper not run`](/docs/en/errors#headershelper-not-run) line per server to stderr |
606612 
607613For the rows that need this exact folder trusted, trust it by hand: set `projects["<path>"].hasTrustDialogAccepted` to `true` in `~/.claude.json`, where `<path>` is the repository root, or the folder itself outside a repository. Claude Code prints the exact key in the debug log line for a skipped subagent hook or inline MCP server, in the stderr warning for skipped allow rules, and in the `headersHelper not run` line for a skipped helper.
608614 

admin-setup Changed · +1 / -1 lines

from line 66
6666* Deploy `wslInheritsWindowsSettings: true` through the HKLM registry or the `C:\Program Files\ClaudeCode` file so WSL sessions inherit the same policy as host sessions.
6767* Verify by running `/status` inside a WSL session: the `Setting sources` line should show `Enterprise managed settings` with the Windows source you deployed, `(HKLM)` or `(file)`.
6868 
69Processes inside the WSL 2 utility VM aren't visible to Windows-side endpoint detection sensors. If you use CrowdStrike Falcon, enable the Falcon sensor for Linux on WSL 2 with the two exclusions CrowdStrike's WSL documentation requires, for the WSL virtual machine process and the VM disk image, so in-distro process and file activity is observable. Claude Code's [OpenTelemetry tool-execution telemetry](/docs/en/monitoring-usage) is emitted identically for WSL and native sessions.
69Processes inside the WSL 2 utility VM aren't visible to Windows-side endpoint detection sensors. To observe in-distro process and file activity, check your endpoint detection vendor's WSL guidance for a Linux sensor you can run inside the distribution and the exclusions it needs. Claude Code's [OpenTelemetry tool-execution telemetry](/docs/en/monitoring-usage) is emitted identically for WSL and native sessions.
7070 
7171## Decide what to enforce
7272 

claude-apps-gateway Changed · +1 / -1 lines

from line 26
2626* **Credentials**: the upstream API key or cloud credential lives only in your infrastructure. Developers authenticate with corporate SSO and receive short-lived bearer tokens, so offboarding happens in your IdP. Deprovision a user and their gateway access expires within the session lifetime, one hour by default.
2727* **Access control**: your IdP groups map to model allowlists and [managed settings](/docs/en/managed-settings) policies. The gateway enforces model access server-side, rejecting requests for non-granted models, and selects each group's managed settings policy, which the CLI applies at the [managed settings tier](/docs/en/settings#settings-precedence). Different teams get different models, tools, and permissions, and a developer can't override what their policy locks.
2828* **Settings delivery**: the gateway delivers managed settings to signed-in clients itself, taking the place of [server-managed settings](/docs/en/server-managed-settings) from the claude.ai admin console.
29* **Telemetry**: each configured destination, such as Datadog, Splunk, or ClickHouse, receives [OpenTelemetry Protocol (OTLP) metrics](/docs/en/monitoring-usage) with token counts, model, user identity, and latency by default, with logs and traces as per-destination opt-ins.
29* **Telemetry**: each configured destination receives [OpenTelemetry Protocol (OTLP) metrics](/docs/en/monitoring-usage) with token counts, model, user identity, and latency by default, with logs and traces as per-destination opt-ins.
3030* **Upstream routing**: clients speak the Anthropic Messages API to the gateway, and the gateway translates for each upstream, whether Amazon Bedrock, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Google Cloud's Agent Platform, Microsoft Foundry, or the Anthropic API, with failover between them. You can change regions, providers, or failover order without developers noticing or reconfiguring.
3131 
3232<Frame>

network-config Changed · +1 / -1 lines

from line 55
5555 
5656## CA certificate store
5757 
58By default, Claude Code trusts both its bundled Mozilla CA certificates and your operating system's certificate store. Reading the OS store requires a runtime with `tls.getCACertificates`: the native installer always has it, and npm installs need Node 22.15 or later. On older Node versions, only the bundled set and `NODE_EXTRA_CA_CERTS` apply. Enterprise TLS-inspection proxies such as CrowdStrike Falcon and Zscaler work without additional configuration when their root certificate is installed in the OS trust store and the runtime can read it.
58By default, Claude Code trusts both its bundled Mozilla CA certificates and your operating system's certificate store. Reading the OS store requires a runtime with `tls.getCACertificates`: the native installer always has it, and npm installs need Node 22.15 or later. On older Node versions, only the bundled set and `NODE_EXTRA_CA_CERTS` apply. Enterprise TLS-inspection proxies work without additional configuration when their root certificate is installed in the OS trust store and the runtime can read it.
5959 
6060`CLAUDE_CODE_CERT_STORE` accepts a comma-separated list of sources. Recognized values are `bundled` for the Mozilla CA set shipped with Claude Code and `system` for the operating system trust store. The default is `bundled,system`.
6161 
Feedback