fix(venice): switch default model to kimi-k2-5 by vincentkoc · Pull Request #38423 · openclaw/openclaw

vincentkoc · 2026-03-07T00:30:38Z

Summary

Problem: Venice still defaults to llama-3.3-70b even after the catalog refresh, and the Venice provider docs still describe the old default and stale model inventory.
Why it matters: The current shipped default and docs lag the live Venice catalog, which keeps the #20156 follow-up partially unresolved after #38306.
What changed: Switched the built-in Venice default model to kimi-k2-5, updated the onboard alias, refreshed the Venice provider guide to match the current private/anonymized catalog, and added changelog credit for the original contributor path.
What did NOT change (scope boundary): No new Venice discovery/runtime hardening beyond the already merged #38306 work.

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

User-visible / Behavior Changes

OpenClaw now defaults Venice setups to venice/kimi-k2-5, uses Kimi K2.5 as the default onboard alias, and ships Venice docs/recommendations that match the current catalog.

Security Impact (required)

New permissions/capabilities? No
Secrets/tokens handling changed? No
New/changed network calls? No
Command/tool execution surface changed? No
Data access scope changed? No

Repro + Verification

Environment

OS: macOS
Runtime/container: Node.js 22 + pnpm
Model/provider: Venice
Integration/channel: Provider config and docs
Relevant config: default Venice provider config

Steps

Inspect the Venice default model constant and onboard alias on current main.
Compare the shipped Venice docs to the current checked-in catalog.
Apply the default-model/docs refresh.
Run the targeted Venice tests and a full build.

Expected

Venice defaults to kimi-k2-5
Onboard alias matches the new default
Venice docs reflect the current model catalog and recommendations

Actual

Before this PR, the runtime default and docs still pointed at llama-3.3-70b

Evidence

Failing test/log before + passing after
Trace/log snippets
Screenshot/recording
Perf numbers (if relevant)

Human Verification (required)

Verified scenarios: Venice default constant, onboard alias, provider docs, changelog entry
Edge cases checked: docs now classify Kimi/MiniMax as private and point high-capability guidance at claude-opus-4-6
What you did not verify: live Venice API traffic, since this PR only changes defaults/docs

Compatibility / Migration

Backward compatible? Yes
Config/env changes? No
Migration needed? No

Failure Recovery (if this breaks)

How to disable/revert this change quickly: revert this PR or set an explicit Venice default model in config
Files/config to restore: src/agents/venice-models.ts, src/commands/onboard-auth.config-core.ts, docs/providers/venice.md
Known bad symptoms reviewers should watch for: Venice onboarding showing the wrong default alias or docs pointing at stale models

Risks and Mitigations

Risk: Users who relied on the implicit Venice default changing to kimi-k2-5 will see a different first-run model.
- Mitigation: the new default is already present in the shipped catalog, private, and documented in the refreshed Venice guide.

greptile-apps · 2026-03-07T00:33:49Z

Greptile Summary

This PR switches the built-in Venice default model from llama-3.3-70b to kimi-k2-5 and refreshes the Venice provider documentation to match the current model catalog. The change is minimal and well-scoped: one constant update in venice-models.ts, one alias string update in onboard-auth.config-core.ts, a comprehensive docs refresh, and a changelog entry.

The new default kimi-k2-5 is properly defined in VENICE_MODEL_CATALOG (private, reasoning, vision, 256k context, 65536 maxTokens) — no missing catalog entry. All references to the old default in docs, CLI examples, and the manual config snippet have been consistently updated. The privacy mode reclassification of Kimi and MiniMax models to Private (and the narrowed Anonymized table) is consistent between venice-models.ts and docs/providers/venice.md.

Confidence Score: 5/5

This PR is safe to merge — it only changes a default model constant, an alias string, documentation, and a changelog entry.
All four changed files are low-risk: a string constant swap, a display alias update, a docs refresh, and a changelog line. The new default model is already present in the static catalog with correct properties. No runtime logic, authentication flows, or API contracts were modified. The changes are straightforward and well-verified.
No files require special attention.

_{Last reviewed commit: 24ebeb7}

* Docs: refresh Venice default model guidance * Venice: switch default model to Kimi K2.5 * Changelog: credit Venice default refresh

(cherry picked from commit 3070faf) Partial: only onboard-auth.config-core.ts — gutted venice-models/docs discarded

vincentkoc added 3 commits March 6, 2026 19:28

Docs: refresh Venice default model guidance

2c7b649

Venice: switch default model to Kimi K2.5

39439b0

Changelog: credit Venice default refresh

24ebeb7

vincentkoc self-assigned this Mar 7, 2026

openclaw-barnacle bot added docs Improvements or additions to documentation commands Command implementations agents Agent runtime and tooling size: XS maintainer Maintainer-authored PR labels Mar 7, 2026

vincentkoc marked this pull request as ready for review March 7, 2026 00:30

vincentkoc merged commit 3070faf into main Mar 7, 2026
33 of 34 checks passed

vincentkoc deleted the vincentkoc-code/venice-default-kimi-k25 branch March 7, 2026 00:31

vincentkoc mentioned this pull request Mar 7, 2026

fix(#20156): Venice - add missing models and set a new model default #12964

Closed

github-actions bot mentioned this pull request Mar 7, 2026

📡 Upstream Digest — 2026-03-07 01:15 UTC curtismercier/openclaw-mods#196

Open

alexyyyander mentioned this pull request Mar 7, 2026

fix/gateway token mismatch 38617 #38676

Closed

alexey-pelykh mentioned this pull request Mar 10, 2026

Cherry-pick: compaction config, Venice hardening, skill rate-limit, nodes remoteclaw/remoteclaw#842

Closed

alexey-pelykh pushed a commit to remoteclaw/remoteclaw that referenced this pull request Mar 20, 2026

fix(venice): switch default model to kimi-k2-5 (openclaw#38423)

2204880

(cherry picked from commit 3070faf) Partial: only onboard-auth.config-core.ts — gutted venice-models/docs discarded

alexey-pelykh mentioned this pull request Mar 20, 2026

Cherry-pick issue #842: compaction-config-venice-kilocode-auth-nodes remoteclaw/remoteclaw#1725

Merged

alexey-pelykh pushed a commit to remoteclaw/remoteclaw that referenced this pull request Mar 20, 2026

fix(venice): switch default model to kimi-k2-5 (openclaw#38423)

2c8c9dc

(cherry picked from commit 3070faf) Partial: only onboard-auth.config-core.ts — gutted venice-models/docs discarded

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(venice): switch default model to kimi-k2-5#38423

fix(venice): switch default model to kimi-k2-5#38423
vincentkoc merged 3 commits intomainfrom
vincentkoc-code/venice-default-kimi-k25

vincentkoc commented Mar 7, 2026

Uh oh!

Uh oh!

greptile-apps bot commented Mar 7, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

vincentkoc commented Mar 7, 2026

Summary

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

User-visible / Behavior Changes

Security Impact (required)

Repro + Verification

Environment

Steps

Expected

Actual

Evidence

Human Verification (required)

Compatibility / Migration

Failure Recovery (if this breaks)

Risks and Mitigations

Uh oh!

Uh oh!

greptile-apps bot commented Mar 7, 2026

Greptile Summary

Confidence Score: 5/5

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant