Repository navigation
New model metadata gaps: grok-4.7 falls back to 128K and unconstrained effort in 2.61.0 #5576
Description
Client or integration
Codex App
Area
Catalog / models
Summary
On OpenCodex 2.61.0 (macOS, Codex runtime 0.155.1), newly discovered xAI grok-4.7 is published with a 128,000-token context and a generic reasoning ladder/default when no per-model override exists. The official contract is 500,000 tokens, low/medium/high/xhigh, default high.
This is separate from synthetic max/ultra picker compatibility discussed in #2420: before adding the missing ladder, ocx effort model xai/grok-4.7 reports unconstrained and translates max to max, rather than xhigh.
Logs or error output
| Field | Before | After explicit provider maps + ocx sync |
|---|---|---|
| catalog context_window / max_context_window | 128000 / 128000 | 500000 / 500000 |
| default_reasoning_level | medium | high |
| configured ladder | unspecified | low,medium,high,xhigh |
| inspect-model translation of max/ultra | max | xhigh |
opencodex_capability_provenance initially identified xai/grok-4.7 without a context assertion. The parser supplied 128000. ocx sync-cache alone did not rebuild these rows; ocx sync did.
A second discovered ID, xai/grok-4.7-build-fast, still has 128000 and the generic ladder. I have NOT assumed the public API model's limits apply to that OAuth/gateway-specific ID; it needs authoritative gateway metadata or a verified contract.
Reproduction
- Use xAI OAuth discovery with grok-4.7 available and no grok-4.7 entries in modelContextWindows/modelReasoningEfforts/modelDefaultReasoningEfforts.
- Run
ocx sync. - Inspect the grok-4.7 row in the generated Codex catalog.
- Run
ocx effort model xai/grok-4.7. - Compare against https://docs.x.ai/developers/models/grok-4.7.
Redacted configuration
Merge these entries into the existing xai provider maps (do not replace unrelated model entries):
{
"modelContextWindows": {"grok-4.7": 500000},
"modelReasoningEfforts": {"grok-4.7": ["low", "medium", "high", "xhigh"]},
"modelDefaultReasoningEfforts": {"grok-4.7": "high"}
}The regenerated catalog and effort inspection were read back. This was metadata/translation verification, not a 500K input load test or captured generation request.
Related audit findings
- Newly discovered anthropic/claude-opus-5-5 had a correct 1M family-derived window and medium default, but no explicit modelReasoningEfforts entry. Its official five-level ladder can now be seeded explicitly: https://platform.claude.com/docs/en/build-with-claude/effort and https://platform.claude.com/docs/en/models/opus-5-5/overview.
- Fable 5.1 and Sonnet 5 catalog defaults were medium, whereas Anthropic documents high. Local per-model defaults corrected this.
- Command Code incomplete ladders are already tracked in command-code: shipped effort ladders are narrower than the live API accepts (and config cannot widen a pinned row) #5096; not asking to duplicate that issue.
- Native OpenAI API limits and Codex runtime caps were deliberately distinguished, not treated as equivalent.
Suggested fix and validation
Add exact new-model metadata to registry seeds and ensure discovery enrichment uses it. Keep unknown gateway variants explicitly unresolved instead of presenting parser fallback values as verified limits. Add a regression for discovered grok-4.7 context/default and max-to-xhigh wire mapping. Preserve synthetic client compatibility only with clear provenance.
No credentials, account identifiers, user prompts, or private configuration are included.
Version
2.61.0 (Codex runtime 0.155.1)
Operating system
macOS 26.6.2
Provider and model
xai / grok-4.7; related anthropic / claude-opus-5-5 metadata
Checks
- I searched existing issues and documentation.
- I removed secrets, tokens, account details, request credentials, and personal data.
Activity
github-actions commentedon Sep 22, 2026
Issue reopened
The report now contains the information required by the automated check. Thanks for updating it.
HeiTuz commentedon Sep 22, 2026
Restart follow-up on 2.61.0: after saving per-model modelContextWindows and modelReasoningEfforts through
ocx config set,ocx service restartremoved the new grok-4.7 / claude-opus-5-5 map entries in this installation (modelDefaultReasoningEfforts remained). The next sync returned Grok to 128000. Root cause within startup/rebase is not yet isolated.A durable local workaround was verified:
ocx models add xai grok-4.7 --context-window 500000 --modalities text,image --reasoning-efforts low,medium,high,xhigh --default-reasoning-effort high. After service restart plus sync the catalog retained 500000/high. An analogous custom registration preserved Opus 5.5's explicit 1M/five-level/medium metadata. This is preferable to treating a pre-restart read-back of provider maps as persistence proof.lidge-jun commentedon Sep 22, 2026
Ill add in days you can manually change it!
lidge-jun commentedon Sep 23, 2026
Status from the 260923 bundle round (lane B, #5676): the grok-4.7 context window and effort metadata this issue reports landed on
devwith #5599 and is pinned byprovider-registry-parity.test.ts. Two parts are not verified yet:grok-4.7-build-fastmetadata, and per-model map entries that are lost on restart. Leaving this open for those.fix(xai): give grok-4.7-build-fast grok-4.7's documented metadata (#5576
fix(xai): give grok-4.7-build-fast grok-4.7's documented metadata (#5576
fix(providers): bundle L3 — MiMo, DeepSeek, Google, Command Code and …
devin-ai-integration commentedon Sep 24, 2026
Triage:
priority: P2— grok-4.7 metadata gaps (context/effort fallback).Criteria (P2): Medium: provider/client-specific bug with a workaround, bounded enhancement tied to a tracked issue, perf, or CI reliability.
Matched pull requests:
priority: P2]lidge-jun commentedon Sep 25, 2026
Fixed in v2.65.0, so closing.
grok-4.7: feat(providers): grok-4.7 parity with grok-4.6 across xAI, Devin, OpenCode Go, Command Code and Cursor #5599 publishes the documented contract (500K context,low..xhigh, defaulthigh) without per-model overrides.tests/providers/provider-registry-parity.test.tspins it.grok-4.7-build-fast: fix(providers): bundle L3 — MiMo, DeepSeek, Google, Command Code and xAI adapter fixes #5739 gives the discovered ID the same 500K window and effort ladder, following xAI's description of Grok 4.7 Fast as the same model served on faster infrastructure.After updating, run
ocx syncto regenerate the catalog rows. You can then remove the manualmodelContextWindows/modelReasoningEfforts/modelDefaultReasoningEffortsentries for these models.#5739 left one related finding out of scope: per-model maps being lost on restart. If you still see that on v2.65.0, please open a separate issue so it can be tracked on its own.