openclaw - ✅(Solved) Fix [Bug]: Asks for OpenAI Whisper/ElevenLabs API key even though initial list says KEY not needed [2 pull requests, 1 comments, 2 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
openclaw/openclaw#74382Fetched 2026-04-30 06:24:34
View on GitHub
Comments
1
Participants
2
Timeline
7
Reactions
2
Timeline (top)
cross-referenced ×3labeled ×2commented ×1renamed ×1
  Install missing skill dependencies
│  🧩 clawhub, 🎮 gog, 📍 goplaces, 📦 mcporter, 📊 model-usage, 🎤 openai-whisper, 📜 session-logs, 🧾 summarize, 📱 wacli

Near this text, in openai-whisper, the text in In parentheses, said that you would not require an API key.

Root Cause

  Install missing skill dependencies
│  🧩 clawhub, 🎮 gog, 📍 goplaces, 📦 mcporter, 📊 model-usage, 🎤 openai-whisper, 📜 session-logs, 🧾 summarize, 📱 wacli

Near this text, in openai-whisper, the text in In parentheses, said that you would not require an API key.

Fix Action

Fixed

PR fix notes

PR #74407: fix(onboard): clarify keyed vs keyless skill setup prompts

Description (problem / solution / changelog)

Made-with: Cursor

Summary

  • Problem: openclaw onboard can show keyless skill dependency install options (for example local openai-whisper) and later ask for API keys for different keyed skills, which is easy to misread as contradictory.
  • Why it matters: Users may think onboarding is requesting unnecessary secrets, reducing trust and increasing setup friction.
  • What changed: Added a dedicated "Skill credentials" note that explicitly separates dependency installation from credential setup, and lists only skills that actually require env secrets.
  • What did NOT change: No skill capability semantics changed; no security ACL logic changed; no install backend behavior changed.

Linked Issue/PR

  • Closes #74382
  • Related #74382
  • This PR fixes a bug or regression

Root Cause

  • Root cause: Onboarding mixed install and credential steps without an explicit transition note, so keyless/keyed skills appeared conflated in the user flow.
  • Missing guardrail: No regression test covered a mixed keyless (openai-whisper) + keyed (openai-whisper-api, sag) scenario.

Regression Test Plan

  • Coverage: Unit test
  • Target: src/commands/onboard-skills.test.ts
  • Scenario: Mixed keyless + keyed skills only prompts for keyed env vars and shows a credentials summary note.

User-visible / Behavior Changes

  • Onboarding now shows a "Skill credentials" note before secret prompts.
  • Secret prompts only target skills with missing required env vars.

Security Impact

  • New permissions/capabilities? No
  • Secrets/tokens handling changed? No (prompt clarity only)
  • New/changed network calls? No
  • Command/tool execution surface changed? No
  • Data access scope changed? No

Changed files

  • src/commands/onboard-skills.test.ts (modified, +103/-0)
  • src/commands/onboard-skills.ts (modified, +17/-4)

PR #74417: fix(onboard): clarify skill credential prompts

Description (problem / solution / changelog)

Summary

Describe the problem and fix in 2–5 bullets:

  • Problem: Skills onboarding can list a keyless local dependency, such as openai-whisper, and then immediately ask for API keys required by separate API-backed skills.
  • Why it matters: The flow makes the later credential prompts look like they contradict the keyless local install hint.
  • What changed: Added a short Skill API credentials note before env-gated skill prompts and covered the mixed openai-whisper / openai-whisper-api / sag scenario.
  • What did NOT change (scope boundary): No installer behavior, credential storage semantics, skill metadata, or dependency detection changed.

AI-assisted: yes.

Change Type (select all)

  • Bug fix
  • Feature
  • Refactor required for the fix
  • Docs
  • Security hardening
  • Chore/infra

Scope (select all touched areas)

  • Gateway / orchestration
  • Skills / tool execution
  • Auth / tokens
  • Memory / storage
  • Integrations
  • API / contracts
  • UI / DX
  • CI/CD / infra

Linked Issue/PR

  • Closes #74382
  • Related #
  • This PR fixes a bug or regression

Root Cause (if applicable)

  • Root cause: Dependency installs and credential prompts were separate code paths, but the credential phase had no framing to distinguish API-backed skills from the earlier keyless local dependency list.
  • Missing detection / guardrail: No test covered mixed keyless local and API-backed missing skills in one onboarding run.
  • Contributing context (if known): The local openai-whisper skill has no primaryEnv, while openai-whisper-api and sag require API key env vars.

Regression Test Plan (if applicable)

  • Coverage level that should have caught this:
    • Unit test
    • Seam / integration test
    • End-to-end test
    • Existing coverage already sufficient
  • Target test or file: src/commands/onboard-skills.test.ts
  • Scenario the test should lock in: a keyless local install option is shown separately from API credential prompts for openai-whisper-api and sag.
  • Why this is the smallest reliable guardrail: setupSkills owns both the install selection prompt and the credential prompt loop.
  • Existing test that already covers this (if any): none for the mixed keyless/keyed prompt sequence.
  • If no new test is added, why not: N/A

User-visible / Behavior Changes

Onboarding now shows a short note before skill API credential prompts, clarifying that those prompts are separate from local dependency installation.

Diagram (if applicable)

Before:
[missing local dependency list] -> [API key prompt with no framing]

After:
[missing local dependency list] -> [Skill API credentials note] -> [API key prompt for env-gated skill]

Security Impact (required)

  • New permissions/capabilities? (Yes/No) No
  • Secrets/tokens handling changed? (Yes/No) No
  • New/changed network calls? (Yes/No) No
  • Command/tool execution surface changed? (Yes/No) No
  • Data access scope changed? (Yes/No) No
  • If any Yes, explain risk + mitigation: N/A

Repro + Verification

Environment

  • OS: macOS
  • Runtime/container: Node 24.14.0, pnpm 10.33.0
  • Model/provider: N/A
  • Integration/channel (if any): N/A
  • Relevant config (redacted): N/A

Steps

  1. Run skill onboarding with missing openai-whisper, openai-whisper-api, and sag requirements.
  2. Observe the missing dependency prompt for the keyless local skill.
  3. Continue to the credential prompt phase.

Expected

  • API key prompts are framed as credential setup for API-backed skills only.

Actual

  • Previously, API key prompts followed the keyless dependency list without a separating explanation.

Evidence

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

Human Verification (required)

What you personally verified (not just CI), and how:

  • Verified scenarios: mixed keyless local and API-backed skills through setupSkills unit coverage.
  • Edge cases checked: credential prompts remain limited to skills with primaryEnv and missing env requirements; install prompt still shows the keyless local skill hint.
  • What you did not verify: manual interactive onboarding in a terminal.

Review Conversations

  • I replied to or resolved every bot review conversation I addressed in this PR.
  • I left unresolved only the conversations that still need reviewer or maintainer judgment.

If a bot review conversation is addressed by this PR, resolve that conversation yourself. Do not leave bot review conversation cleanup for maintainers.

Compatibility / Migration

  • Backward compatible? (Yes/No) Yes
  • Config/env changes? (Yes/No) No
  • Migration needed? (Yes/No) No
  • If yes, exact upgrade steps: N/A

Risks and Mitigations

  • Risk: The extra note adds one more onboarding text block for users with missing skill credentials.
    • Mitigation: It appears only when credential prompts are actually needed and lists only the affected skills.

Validation

pnpm test src/commands/onboard-skills.test.ts
pnpm test src/agents/skills.buildworkspaceskillstatus.test.ts
pnpm exec oxfmt --check --threads=1 src/commands/onboard-skills.ts src/commands/onboard-skills.test.ts CHANGELOG.md
pnpm check:changed
git diff --check
codex review --base origin/main

Changed files

Code Example

Install missing skill dependencies
│  🧩 clawhub, 🎮 gog, 📍 goplaces, 📦 mcporter, 📊 model-usage, 🎤 openai-whisper, 📜 session-logs, 🧾 summarize, 📱 wacli

---
RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

  Install missing skill dependencies
│  🧩 clawhub, 🎮 gog, 📍 goplaces, 📦 mcporter, 📊 model-usage, 🎤 openai-whisper, 📜 session-logs, 🧾 summarize, 📱 wacli

Near this text, in openai-whisper, the text in In parentheses, said that you would not require an API key.

Steps to reproduce

openclaw onboard

Expected behavior

Should not ask for API key since the text said that it's not needed.

Actual behavior

Asks for an API key.

OpenClaw version

2026.4.26 (be8c246)

Operating system

Tahoe 26.4

Install method

npm global

Model

google/gemini-3-flash-preview

Provider / routing chain

openclaw

Additional provider/model setup details

No response

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response

extent analysis

TL;DR

The issue can likely be resolved by re-examining the documentation or configuration for the openai-whisper skill to ensure that an API key is indeed not required or to find the correct setup to bypass the API key prompt.

Guidance

  • Verify the openai-whisper skill documentation to confirm if an API key is required for its functionality, as the text suggesting it's not needed might be outdated or incorrect.
  • Check the openclaw configuration files or setup process to see if there's an option to bypass the API key prompt for openai-whisper or if there's a specific setup required to use it without an API key.
  • If the documentation or configuration does indeed indicate that an API key should not be required, consider filing a bug report or seeking further assistance from the openclaw or openai-whisper support channels.
  • Review the output of openclaw onboard to see if there are any specific error messages or hints that could indicate why an API key is being requested despite the documentation suggesting it's not needed.

Example

No specific code example can be provided without more details on the openclaw or openai-whisper APIs and configurations.

Notes

The solution might depend on the specific versions of openclaw and openai-whisper being used, as well as any custom configurations applied during setup.

Recommendation

Apply workaround: Given the discrepancy between the documentation and the actual behavior, it's likely that either the documentation needs updating or there's a specific workaround required to use openai-whisper without an API key. Until this is clarified, using a workaround such as providing a dummy API key (if possible) or seeking an alternative skill that does not require an API key might be necessary.

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…

FAQ

Expected behavior

Should not ask for API key since the text said that it's not needed.

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

openclaw - ✅(Solved) Fix [Bug]: Asks for OpenAI Whisper/ElevenLabs API key even though initial list says KEY not needed [2 pull requests, 1 comments, 2 participants]