Claude Code v2.1.323 · 12 Nov 2026
Unknown-model warning now suggests /autocompact instead of adding [1m]
The warning for an unrecognised model no longer says to add [1m] and now suggests /autocompact for 1M-token windows
Use it now Tier: how much it should matter to you
2 Useful: my rating, 1 to 5
1 Signal: worth watching, 1 to 5
Models Area: what it touches
Improvements Kind: in v2.1.323, 12 Nov 26
What probably matters to you Section of the release
What
When Claude Code does not recognise your model name, such as an alias from a gateway, it shows a notice about the context window (how much text the model can hold at once) it assumes. That notice changed:
It no longer suggests adding [1m] to the model name to get a 1 million token window
When the assumed window is 1 million tokens or more, it suggests setting a smaller auto-compact window with /autocompact
The notice still suggests setting CLAUDE_CODE_MAX_CONTEXT_TOKENS CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT =1
Why
If you use a model Claude Code does not recognise, the advice in the warning is different. With a large assumed window, it now points you to /autocompact
How sure we are
One source agrees One thing we can check says the same as this entry.
Anthropic's release notes agree Changed the context window assumed for a model ID that Claude Code doesn't recognize from 200K to 1M; use /autocompact to compact earlier…
See this entry in the whole of v2.1.323 →
12 Nov 2026 · 888 entries, this one is #106.
77 533 64 214
Open the release →
Names in this entry
slash /autocompact Set the auto-compact window: how full the context window gets before Claude Code compacts automatically. Pass a size such as 500k, or auto to return to the window tuned for your model. Claude Code saves the value to user settings and applies it to the current session. See Set the auto-compact window for accepted values and what overrides it. Without an argument, opens a dialog that shows the current window. Requires Claude Code v2.1.221 or later
env CLAUDE_CODE_MAX_CONTEXT_TOKENS Override the context window size Claude Code assumes for the active model. As of v2.1.193, how it applies depends on how Claude Code resolves the model ID; see Correct the window for a gateway or custom model ID . Use this when routing to a model through ANTHROPIC_BASE_URL whose context window does not match the built-in size for its name
env CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT Set to 1 to skip proactive auto-compaction when Claude Code doesn't recognize the model ID, such as an LLM gateway alias. Without this variable, Claude Code compacts at the context window it assumes for the ID. CLAUDE_CODE_MAX_CONTEXT_TOKENS can correct the assumed window instead; see Correct the window for a gateway or custom model ID for when each variable applies. Requires Claude Code v2.1.223 or later
Anthropic's note
Upstream's own release notes for v2.1.323 name something this entry names, so the two are probably about the same change. Probably: the pairing is made on a shared name rather than on the words around it.
Is this right?
0 0 Feedback
What's wrong with this entry?
Hard to understand Too vague Looks wrong Not relevant to me Too long Missing the detail I wanted Duplicate of another card
Clear Learned something new I can act on this Good catch
Related
Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.
← Previous · 105 of 888
The PowerShell parse timeout setting is now capped at a maximum
Use it now Elsewhere
In v2.1.323 What probably matters to you release-page order
Next → · 107 of 888
Slow-worktree tip now includes .claude in its sparsePaths example
Use it now Worktrees
