Error reference changederrors
Nearest release: v2.1.282, published 6 hours before 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 24 Sep 2026 22:56 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 24 Sep 2026 23:07 UTC.
Upstream edited
Recorded here
Lines+33added
Lines−0removed
From line
30
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits193to this page, all time
### The server returned no safety verdict
The whole hunk
from line 30, 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 30
3030| `Auto mode could not evaluate this action and is blocking it for safety` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
3131| `Auto mode classifier transcript exceeded context window` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
3232| `Agent aborted: auto mode classifier request refused by the safety safeguard` | [Server errors](#auto-mode-cannot-determine-the-safety-of-an-action) |
33| `The server-side auto mode classifier gave no verdict` | [Server errors](#the-server-returned-no-safety-verdict) |
34| `Auto mode is unavailable — the server returned no safety verdict for the last 10 responses` | [Server errors](#the-server-returned-no-safety-verdict) |
3335| `Agent terminated early due to an API error` | [Server errors](#agent-terminated-early-due-to-an-api-error) |
3436| `You've hit your session limit` / `You've hit your weekly limit` / `You've hit your Opus limit` / `You've hit your Sonnet limit` | [Usage limits](#youve-hit-your-session-limit) |
3537| `Usage credits required for 1M context` | [Usage limits](#usage-credits-required-for-1m-context) |
from line 545
543545* In an interactive session, approve or deny the action in the prompt that appears
544546* In an interactive session, run `/compact` to reduce the conversation size so subsequent actions fit within the classifier window again
545547
548### The server returned no safety verdict
549
550Under [server-side classifier review](/docs/en/permission-modes#server-side-classifier-review), auto mode denies an action when the server gives no verdict for it. The denial names a category in parentheses when Claude Code can determine one, such as `(timed out)`:
551
552```text theme={null}
553The server-side auto mode classifier gave no verdict (timed out), so auto mode cannot determine the safety of <tool>.
554```
555
556The rest of the message tells Claude whether one retry can help. Before some of these denials, Claude Code waits so that Claude's next attempt doesn't follow at once. During the wait in an interactive session, the spinner shows `Auto mode check unavailable` with a countdown, and pressing `Esc` interrupts the turn.
557
558After ten responses in a row with no verdict, auto mode stops the turn:
559
560```text theme={null}
561Auto mode is unavailable — the server returned no safety verdict for the last 10 responses, so Claude stopped. Send a message to try again, or switch out of auto mode.
562```
563
564The stop message appears in a different place in each kind of session:
565
566* In an interactive session, the message appears as a warning in the transcript and the turn ends
567* In a [non-interactive](/docs/en/headless) `-p` run, the run ends and reports an execution error. With the default text output, the message prints on stderr.
568* When a [subagent](/docs/en/sub-agents) hit the limit, the subagent stops before finishing, and Claude receives whatever it produced with a note that auto mode stopped it
569
570**What to do:**
571
572* Send another message to have Claude try again. The count of responses starts over.
573* If the stop repeats and your requests go through an [LLM gateway or proxy](/docs/en/llm-gateway), check whether it cuts streaming responses short or rewrites them. [Server-side classifier review](/docs/en/permission-modes#server-side-classifier-review) says which gateway behavior causes denials, and the [gateway compatibility guide](/docs/en/llm-gateway-protocol#feature-pass-through) lists what to pass through unchanged.
574* Set `CLAUDE_CODE_AUTO_MODE_SERVER=0` before you start Claude Code to use its own classifier requests instead. Before v2.1.281, Claude Code didn't read the variable on a direct connection to the Anthropic API.
575* To approve the actions yourself instead, [switch out of auto mode](/docs/en/permission-modes#switch-permission-modes)
576
577Before v2.1.280, Claude Code denied each action from a response without a verdict immediately and never stopped the turn.
578
546579### Agent terminated early due to an API error
547580
548581A [subagent](/docs/en/sub-agents)'s API request failed terminally, for example because a usage limit was reached or retries for a server error ran out, so the subagent stopped before finishing its task. This message requires Claude Code v2.1.199 or later; before then the API error text was returned to Claude as if it were the subagent's result.
from line 1915
18821915Error during compaction: Conversation too long. Press esc twice to go up a few messages and try again.
18831916```
18841917
1885This can happen when the window is already full at the moment auto-compact triggers, or when you run `/compact` after seeing [`Prompt is too long`](#prompt-is-too-long). In an interactive session, that error is the `Context limit reached` line.
1886
1887**What to do:**
1888
1889* Press Esc twice to open the message list and step back several turns. This drops the most recent messages from context. Then run `/compact` again.
1890* If stepping back doesn't free enough space, run `/clear` to start a fresh session. Your previous conversation is preserved and can be reopened with `/resume`.
1891
1892This message and other `/compact` failures display in error styling. Before v2.1.216, they rendered in the same dim style as successful command output, so you could read a failed compaction as a success.
1893
1894### Request too large
1895
1896The raw request body exceeded the API's 32MB limit before tokenization, usually because of large pasted content, tool results, or attachments. This limit is separate from the [context window](#prompt-is-too-long).
1897
1898```text theme={null}
1899Request too large (max 32MB). Accumulated images and attachments in the conversation pushed the request over the limit. Run /compact, or double press esc to go back and remove attachments.
1900```
1901
1902When the request went straight to the Claude API and the API itself rejected it, Claude Code measures the conversation and words the message by whether recovery can work. Through a proxy, gateway, or cloud provider you get the general message. The measured forms:
1903
1904* `Request too large (max 32MB; 20.1MB of about 33.4MB is images or documents).`: images or documents pushed the request over the limit. Claude Code retries with them stripped.
1905* `Request too large for the API's 32MB request limit`: the messages alone are over the limit, so the message says `compacting cannot make it fit` and Claude Code doesn't retry. In [non-interactive mode](/docs/en/headless), the message tells you to reduce the input or start a new session instead.
1906
1907Before v2.1.212, conversations with enough accumulated images failed on every turn with `Request too large (max 32MB). Double press esc to go back and try with a smaller file.` Before v2.1.229, Claude Code showed the attachment advice for every rejection, even when compacting couldn't help.
1908
1909**What to do:**
1910
1911* If the message says `compacting cannot make it fit`, press Esc twice to step back past the turn that added the large content, or run `/clear` to start fresh
1912* Otherwise, run `/compact`, which drops accumulated images and attachments
1913* Reference large files by path instead of pasting their contents, so Claude can read them in chunks
1914* For images, see [Image was too large](#image-was-too-large) below
1915
1916### Image was too large
1917
1918A pasted or attached image exceeds the API's size or dimension limits.
1919
1920```text theme={null}
1921Image was too large. Double press esc to go back and try again with a smaller image.
1922API Error: 400 ... image dimensions exceed max allowed size
1923```
1924
1925Claude Code replaces the unprocessable image with a text placeholder and retries, so subsequent messages succeed. On versions before 2.1.142, a pasted image could remain in the conversation and repeat the same error on every subsequent message. To recover on those versions, press Esc twice and step back past the turn where the image was added.
1926
1927**What to do:**
1928
1929* Resize the image before pasting. The API accepts images up to 8000 pixel
1918This can happen when the window is already full at the moment auto-compact trigg
No line in this hunk matches that.