Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix [DOCS] Model configuration docs still describe Opus 4.6 as the current 1M-context Opus model [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#51786•Fetched 2026-04-22 07:52:53
View on GitHub
Comments
0
Participants
1
Timeline
3
Reactions
0
Author
coygeekcoygeek
Participants
coygeekcoygeek
Timeline (top)
labeled ×3

Root Cause

Changelog v2.1.117 says Claude Code fixed Opus 4.7 sessions that were showing inflated /context percentages and autocompacting too early because the app was still computing against a 200K window instead of Opus 4.7's native 1M context window.

RAW_BUFFERClick to expand / collapse

Documentation Type

Incorrect/outdated documentation

Documentation Location

https://code.claude.com/docs/en/model-config

Section/Topic

opus model alias table entry and the "Extended context" section

Current Documentation

The docs currently say:

| opus | Uses the latest Opus model (currently Opus 4.6) for complex reasoning tasks |

Opus 4.6 and Sonnet 4.6 support a 1 million token context window for long sessions with large codebases.

Availability varies by model and plan. On Max, Team, and Enterprise plans, Opus is automatically upgraded to 1M context with no additional configuration.

What's Wrong or Missing?

Changelog v2.1.117 says Claude Code fixed Opus 4.7 sessions that were showing inflated /context percentages and autocompacting too early because the app was still computing against a 200K window instead of Opus 4.7's native 1M context window.

That makes the current model documentation outdated: it still tells users that the latest/current Opus model is 4.6 and that the relevant 1M-context Opus model is Opus 4.6. Users reading the model docs do not get an accurate explanation of why Opus 4.7 sessions should use a 1M context window for /context percentages and auto-compaction thresholds.

Suggested Improvement

Update https://code.claude.com/docs/en/model-config to reflect the current Opus model and context behavior:

  1. Change the opus alias entry so it no longer says the latest Opus model is "currently Opus 4.6" if Opus 4.7 is now the default/current Opus model.
  2. Update the "Extended context" section to state that Opus 4.7 sessions use a native 1M context window where applicable.
  3. Add a short clarification that /context, status-line context percentages, and auto-compaction thresholds are based on the active model's actual context window.
  4. If provider-specific behavior differs, explicitly call out when 1M is automatic versus when users still need a pinned [1m] model variant.

Impact

Medium - Makes feature difficult to understand

Additional Context

Affected Pages:

PageContext
https://code.claude.com/docs/en/model-configAlias table still says opus currently means Opus 4.6, and the extended-context section still describes Opus 4.6 as the 1M-context Opus model
https://code.claude.com/docs/en/azure-ai-foundryPinning guidance already tells Foundry users to set an Opus 4.7 model ID to use the latest model, which conflicts with model-config's current/latest Opus text

Total scope: 2 pages affected

Source: Changelog v2.1.117

Exact changelog entry: Fixed Opus 4.7 sessions showing inflated /context percentages and autocompacting too early — Claude Code was computing against a 200K context window instead of Opus 4.7's native 1M

extent analysis

TL;DR

Update the opus model alias table entry and the "Extended context" section in the documentation to reflect the current Opus model and context behavior, specifically Opus 4.7's native 1M context window.

Guidance

  • Review the current documentation at https://code.claude.com/docs/en/model-config and identify areas that reference Opus 4.6 as the latest model.
  • Update the opus alias entry to reflect that Opus 4.7 is now the default/current Opus model.
  • Clarify in the "Extended context" section that Opus 4.7 sessions use a native 1M context window where applicable.
  • Verify that the changes are consistent across all affected pages, including https://code.claude.com/docs/en/azure-ai-foundry.

Example

No code snippet is necessary for this issue, as it is a documentation update.

Notes

The update should ensure that users have accurate information about the current Opus model and its context behavior, which will help resolve the medium-impact issue of making the feature difficult to understand.

Recommendation

Apply workaround: Update the documentation to reflect the current Opus model and context behavior, as this will provide users with accurate information and resolve the issue.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#API routing#API middleware#SSR setup#ISR setup#authentication setup

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

claude-code - 💡(How to fix) Fix [DOCS] Model configuration docs still describe Opus 4.6 as the current 1M-context Opus model [1 participants]