docs(vlm): document timeout config field (#1580)

[r266-tech]

Summary

PR #1580 (0xble, merged 2026-04-20) added a new timeout field to VLMConfig (default 60.0, gt=0.0 validation) and wired it through both OpenAI and LiteLLM backends. Users can now set vlm.timeout in ov.conf to increase per-request HTTP timeout for slow endpoints (DashScope, local inference, large overview prompts).

docs/en/guides/01-configuration.md and docs/zh/guides/01-configuration.md list the other VLM fields (api_key, model, max_retries, extra_headers, stream, …) in the parameter tables but are missing timeout. Users who want to raise the timeout have no signal from the docs that the field exists — they have to read vlm_config.py source or the #1580 PR description.

Changes

• docs/en/guides/01-configuration.md: +1 row in the vlm Parameters table describing timeout (type float, default 60.0, must be > 0, slow-endpoint use case mirrored from the Field description in vlm_config.py)
• docs/zh/guides/01-configuration.md: +1 row in the 参数 table (中文描述, 与 EN 镜像)

Docs-only change; no code touched.

Related

• Follows up on feat(vlm): expose timeout as a config field and thread it through #1580 (documents the field it added)
• Related to Directory overview generation can build oversized prompts and destabilize VLM calls #529 (oversized overview prompts triggering VLM timeouts — one of the user scenarios mentioned in feat(vlm): expose timeout as a config field and thread it through #1580 motivation)

[github-actions]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

🎫 Ticket compliance analysis 🔶 1580 - Partially compliant Compliant requirements: Document the new timeout field in English and Chinese configuration guides Non-compliant requirements: (No code changes needed here as this is a docs-only follow-up) Requires further human verification: Verify Japanese documentation update (if applicable)

⏱️ Estimated effort to review: 1 🔵⚪⚪⚪⚪

🏅 Score: 100

🧪 No relevant tests

🔒 No security concerns identified

✅ No TODO sections

🔀 No multiple PR themes

⚡ No major issues detected

[github-actions]

PR Code Suggestions ✨

No code suggestions found for the PR.