Error reference changederrors
Nearest release: v2.1.290, published 4 hours after upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 5 Oct 2026 13:55 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 5 Oct 2026 14:07 UTC.
Upstream edited
Recorded here
Lines+26added
Lines−0removed
From line
181
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits187to this page, all time
The whole hunk
from line 181, old and new numbered
/
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 181
181181| `<model>'s safeguards flagged this message` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |
182182| `<model>'s safeguards flagged this session` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |
183183| `<model> has safety measures that flagged this message for a cybersecurity topic` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) |
184| `` Details: `[reasoning_extraction]` `` | [Request errors](#safeguards-flagged-a-request-for-claudes-reasoning) |
184185| `API Error: Output blocked by content filtering policy` | [Request errors](#output-blocked-by-content-filtering-policy) |
185186| `Installation was killed before it could finish (exit code 137)` | [Installation errors](#installation-was-killed-before-it-could-finish) |
186187| `The connection dropped while downloading the update` | [Installation errors](#the-connection-dropped-while-downloading-the-update) |
from line 2656
26552656
26562657The API declined to respond because content in the conversation triggered a [Usage Policy](https://www.anthropic.com/legal/aup) check.
26572658
2659If the message includes the line `` Details: `[reasoning_extraction]` ``, see [Safeguards flagged a request for Claude's reasoning](#safeguards-flagged-a-request-for-claudes-reasoning).
2660
26582661The message includes a Request ID and a Message ID you can quote to support if you believe the refusal is incorrect.
26592662
26602663```text theme={null}
from line 2686
26832686API Error: Opus 4.8's safeguards flagged this message. Our intentionally broad safeguards allow us to deliver more capabilities faster, but can sometimes flag legitimate cybersecurity work. Apply to the Cyber Verification Program to reduce these interruptions. Send feedback with /feedback or learn more: https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude
26842687```
26852688
2689If the message includes the line `` Details: `[reasoning_extraction]` ``, see [Safeguards flagged a request for Claude's reasoning](#safeguards-flagged-a-request-for-claudes-reasoning).
2690
26862691The message links to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude), which grants access for legitimate cybersecurity work. On Opus 5.5 and Sonnet 5.5, the message opens with `<model>'s safeguards flagged this session` instead. When the flagged category has a fallback model available, Claude Code [switches models](/docs/en/model-config#automatic-model-fallback) rather than showing this error.
26872692
26882693On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), and [Microsoft Foundry](/docs/en/microsoft-foundry), a cybersecurity flag produces the [Usage Policy refusal](#usage-policy-refusal) message instead.
from line 2702
26972702* If your request wasn't about a cybersecurity topic, run `/feedback` to report the false positive
26982703* To keep working in the same session, press Esc twice or run `/rewind` to step back to a checkpoint before the turn that triggered the flag, then take a different approach. See [Checkpointing](/docs/en/checkpointing).
26992704
2705<h3 id="safeguards-flagged-a-request-for-claudes-reasoning">
2706 Safeguards flagged a request for Claude's reasoning
2707</h3>
2708
2709The API declined the request because safeguards flagged it as asking the model to reproduce its internal reasoning in the response. The API names this [refusal category](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) `reasoning_extraction`, and the refusal message includes this line:
2710
2711```text theme={null}
2712Details: `[reasoning_extraction]`
2713```
2714
2715Before v2.1.234, refusal messages didn't include the `Details` line.
2716
2717**What to do:**
2718
2719* Remove or reword any instruction that asks Claude to write out its thinking or reasoning verbatim or in a fixed format, such as a `<thinking>` section, a scratchpad section, or a `reasoning` field in JSON output. The instruction can be in your prompt or in a customization that Claude Code loads with it, such as CLAUDE.md, a skill, a subagent prompt, an output style, or an MCP tool description.
2720* To check whether a customization is the trigger, run [`claude --safe-mode`](/docs/en/cli-reference#cli-flags) in your terminal to start a session with customizations disabled, then send the same prompt
2721* After you change a customization, start a new session
2722* To reword a prompt you already sent, see [Rewind and summarize](/docs/en/checkpointing#rewind-and-summarize)
2723* You can still ask Claude to explain its answer. Ask for a short explanation, the evidence behind a result, or a summary of the actions it took. To read summaries of Claude's thinking, see [`showThinkingSummaries`](/docs/en/settings-reference#showthinkingsummaries).
2724* For more examples, and what to do if a reworded request is still declined, see [Keep reasoning in thinking blocks](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#keep-reasoning-in-thinking-blocks)
2725
27002726### Output blocked by content filtering policy
27012727
27022728The API's output content filter stopped the response Claude was generating. The message text comes from the API:
from line 2790
27642790This message requires Claude Code v2.1.198 or later. You combined `--bg` with `-p` or `--print` in the same `claude` invocation. `--bg` starts a [background session](/docs/en/agent-view#from-your-shell) that you later attach to with `claude agents`, while `--print` runs [non-interactively](/docs/en/headless) and never starts the interactive session that `claude agents` attaches to. Before v2.1.198 this combination silently created a background job that could never be attached to.
27652791
27662792```text theme={null}
2767--bg and --print conflict: --print never starts the interactive session that `claude agents` attaches to, so the job would be unattachable. The prompt is the positional — drop --print: `claude --bg '<task>'`.
2768```
2769
2770**What to do:**
2771
2772* Drop `-p` or `--print`. `--bg` takes the prompt as its positional argument, so `claude --bg "<task>"` is the complete command. See [Dispatch new agents from your shell](/docs/en/agent-view#from-your-shell).
2773* To run the prompt non-interactively and print the result instead of creating a background session, drop `--bg` and run `claude -p "<task>"`
2774
2775<h3 id="conflict-between-a-system-prompt-flag-and-its-file-form">
2776 Conflict between a system prompt flag and its file form
2777</h3>
2778
2779You passed [`--append-subagent-system-prompt`](/docs/en/cli-reference#cli-flags) together with `--append-subagent-system-prompt-file` in one `claude` invocation, so `claude` exits with code 1 instead of starting the session:
2780
2781```text theme={null}
2782Error: Cannot use both --append-subagent-system-prompt and --append-subagent-system-prompt-file. Please use only one.
2783```
2784
2785Before v2.1.283, `claude` exited the same way when you passed `--system-prompt` with `--system-prompt-file`, or `--append-system-prompt` with `--append-system-prompt-file`, because those pairs conflicted instead of [combining](/docs/en/cli-reference#system-prompt-flags). On those versions the message names the pair you combined.
2786
2787**What to do:**
2788
2789* Keep one form of the flag and drop the other. To combine a fixed prompt file with per-run text, merge the text into the file before launching instead of passing both flags
2790
2791<h3 id="invalid-agents-configuration">
2792 Invalid `--agents` configuration
2793</h3>
2794
2795The value you passed to `--agents` is invalid, so `claude` exits with code 1 instead of starting the session. When you pass `--safe-mode` or set [`CLAUDE_CODE_SAFE_MODE`](/docs/en/env-vars#variables), Claude Code ignores `--agents` entirely. With `--resume` or `--continue`, an inline JSON value isn't checked and the session starts; a value read from a file is checked on every launch. Before v2.1.242, Claude Code started the session anyway.
2796
2797```text theme={null}
2798Error: Invalid --agents configuration:
2799<what failed>
2800```
2801
2802What follows the first line depends on how the value failed. Claude Code runs these checks in order and stops at the first one that fails. If your value has two ki
2793--bg and --print co
No line in this hunk matches that.