Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix [DOCS] Effort level docs omit `xhigh` for Opus 4.7 and fallback-to-`high` behavior [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#49283•Fetched 2026-04-17 08:45:38
View on GitHub
Comments
0
Participants
1
Timeline
5
Reactions
0
Author
coygeekcoygeek
Participants
coygeekcoygeek
Timeline (top)
labeled ×3cross-referenced ×2
RAW_BUFFERClick to expand / collapse

Documentation Type

Incorrect/outdated documentation

Documentation Location

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

Section/Topic

Adjust effort level and the linked /effort / --effort usage guidance

Current Documentation

The model configuration page currently says:

"Three levels persist across sessions: low, medium, and high. A fourth level, max, provides the deepest reasoning with no constraint on token spending, so responses are slower and cost more than at high. max is available on Opus 4.6 only..."

"/effort: run /effort low, /effort medium, /effort high, or /effort max to change the level..."

"--effort flag: pass low, medium, high, or max to set the level for a single session..."

"Effort is supported on Opus 4.6 and Sonnet 4.6. The effort slider appears in /model when a supported model is selected..."

The command reference currently says:

"/effort [low|medium|high|max|auto] ... max applies to the current session only and requires Opus 4.6."

The CLI reference currently says:

"--effort ... Options: low, medium, high, max (Opus 4.6 only)."

What's Wrong or Missing?

These pages are outdated for changelog v2.1.111.

The changelog added an xhigh effort level for Opus 4.7, positioned between high and max, and says it is available through /effort, --effort, and the model picker. The current docs still describe the effort range as only low / medium / high / max, and they still scope the higher-end behavior to Opus 4.6.

The docs also do not explain the new compatibility behavior that other models fall back to high when xhigh is requested.

Suggested Improvement

Update the effort documentation so all user-facing entry points match v2.1.111:

  1. In model-config, document xhigh between high and max and update model support text from Opus 4.6-era wording to Opus 4.7 wording.
  2. In the /effort command docs, add xhigh to the documented values.
  3. In the --effort CLI flag docs, add xhigh to the documented values.
  4. In the model picker guidance, note that xhigh is available for Opus 4.7 and falls back to high on other models.

Impact

Medium - Makes feature difficult to understand

Additional Context

Affected Pages:

PageContext
https://code.claude.com/docs/en/model-configCentral effort-level description, supported-model wording, and model-picker guidance
https://code.claude.com/docs/en/commands/effort syntax still omits xhigh
https://code.claude.com/docs/en/cli-reference--effort options still omit xhigh
https://code.claude.com/docs/en/common-workflowsExtended-thinking guidance still describes effort support using Opus 4.6 / Sonnet 4.6 wording

Total scope: 4 pages affected

Source: Changelog v2.1.111

Entry under review: Added xhigh effort level for Opus 4.7, sitting between high and max. Available via /effort, --effort, and the model picker; other models fall back to high

extent analysis

TL;DR

Update the effort documentation to include the new xhigh level and reflect Opus 4.7 support.

Guidance

  • Review the documentation for model-config, /effort command, --effort CLI flag, and model picker guidance to ensure they are updated to include xhigh as a valid effort level.
  • Verify that the documentation accurately describes the compatibility behavior of other models falling back to high when xhigh is requested.
  • Check the affected pages (model-config, commands, CLI reference, and common-workflows) to ensure consistency in effort level documentation.
  • Consider updating the documentation to clearly indicate the version support for each effort level, including Opus 4.7.

Example

No code snippet is provided as this issue is related to documentation updates.

Notes

The updates should be based on the changelog v2.1.111, which introduced the xhigh effort level for Opus 4.7. The documentation updates should reflect the new effort level and its compatibility behavior.

Recommendation

Apply workaround: Update the documentation to reflect the changes introduced in changelog v2.1.111, including the addition of the xhigh effort level and its support on Opus 4.7. This will ensure that the documentation is accurate and consistent, making it easier for users to understand the feature.

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#ssr#installation#tensor shape#autograd error

Still need to ship something?

×6

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

Back to top recommendations

TRENDING