Document OpenRouter setup for OpenAI-compatible models

[aantn]

Summary

• add dedicated OpenRouter page with two Holmes CLI methods and required environment variables
• link the new OpenRouter page from the AI providers index
• clarify wording for the LiteLLM OpenRouter provider method; keep OpenAI-compatible page generic

Testing

• not run (docs-only change)

---

Codex Task

Summary by CodeRabbit

• Documentation
  • Added OpenRouter as a new supported AI provider with complete configuration documentation.
  • New guide covers provider setup, required environment variables, and practical usage examples for multiple model options.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

Walkthrough

Added OpenRouter as a new AI provider with documentation. The change includes adding an OpenRouter entry to the providers grid in the index and creating a new setup guide documenting two configuration methods using OpenAI-compatible endpoint and LiteLLM approaches.

Changes

Cohort / File(s)	Summary
OpenRouter documentation docs/ai-providers/index.md, docs/ai-providers/openrouter.md	Added OpenRouter provider entry to the index grid and created new documentation file with configuration instructions for two setup methods (OpenAI-compatible endpoint and LiteLLM provider), including required environment variables and example commands.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

• Verify the OpenRouter entry is correctly added to the provider grid layout
• Check documentation accuracy for both configuration methods and environment variable requirements
• Confirm example commands and model ID formats are correct

Possibly related PRs

• #813: Modifies AI providers documentation (docs/ai-providers/*) with provider entries and setup guidance, sharing similar scope as this PR's documentation updates.

Suggested reviewers

• arikalon1
• Sheeproid

Pre-merge checks

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The PR title accurately describes the main change: adding documentation for OpenRouter setup with OpenAI-compatible models, which matches the addition of the new openrouter.md documentation file and index entry.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (2)

docs/ai-providers/openrouter.md (2)

17-23: Add explanatory text before Method 2's code block for consistency.

Method 1 includes a brief explanation of what it does before the code block (line 9), but Method 2 lacks this context. Even if Method 2 is intentionally minimal, readers benefit from understanding what distinguishes it from Method 1.

Consider adding a description like: "Use the LiteLLM OpenRouter provider for more granular OpenRouter-specific model handling and routing features."

🔎 Suggested revision

 ### Method 2: LiteLLM OpenRouter provider
 
+Use the LiteLLM OpenRouter provider for direct OpenRouter model identification and routing.
+
 ```bash
 export OPENAI_API_BASE="https://openrouter.ai/api/v1"
 export OPENAI_API_KEY="sk-or-..."  # your OpenRouter key
 holmes ask "hello" --model="openrouter/openai/gpt-4o-mini" --no-interactive

</details>

---

`25-25`: **Clarify which method the closing note applies to.**

The note about swapping model IDs specifically shows the `openrouter/...` prefix format, which applies to Method 2. However, Method 1 users can also swap models (using the `openai/...` format without the prefix). Consider clarifying the scope or providing examples for both methods.

</blockquote></details>

</blockquote></details>

<details>
<summary>📜 Review details</summary>

**Configuration used**: Organization UI

**Review profile**: CHILL

**Plan**: Pro

<details>
<summary>📥 Commits</summary>

Reviewing files that changed from the base of the PR and between af8b2a58d9832cf146cac7d8580d21ed996ea3a6 and 696d35daf924be99fd734d6094b6d500bcce4b09.

</details>

<details>
<summary>📒 Files selected for processing (2)</summary>

* `docs/ai-providers/index.md` (1 hunks)
* `docs/ai-providers/openrouter.md` (1 hunks)

</details>

<details>
<summary>🧰 Additional context used</summary>

<details>
<summary>📓 Path-based instructions (1)</summary>

<details>
<summary>docs/**/*.md</summary>


**📄 CodeRabbit inference engine (CLAUDE.md)**

> When writing documentation in the docs/ directory, always add a blank line between headers/bold text and lists for proper MkDocs rendering

Files:
- `docs/ai-providers/index.md`
- `docs/ai-providers/openrouter.md`

</details>

</details>

</details>

<details>
<summary>⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (5)</summary>

* GitHub Check: build (3.10)
* GitHub Check: build (3.12)
* GitHub Check: build (3.11)
* GitHub Check: llm_evals
* GitHub Check: build

</details>

<details>
<summary>🔇 Additional comments (1)</summary><blockquote>

<details>
<summary>docs/ai-providers/index.md (1)</summary><blockquote>

`14-16`: **✅ OpenRouter entry properly added to providers grid.**

The new OpenRouter entry is correctly formatted, alphabetically ordered between OpenAI-Compatible and Robusta AI, uses an appropriate icon (`:material-earth:`), and links to the new documentation page. Blank line spacing around the grid items complies with the MkDocs rendering requirements.

</blockquote></details>

</blockquote></details>

</details>

<!-- This is an auto-generated comment by CodeRabbit for review status -->

[github-actions]

Results of HolmesGPT evals

• ask_holmes: 31/37 test cases were successful, 2 regressions, 1 setup failures, 3 mock failures

Test suite	Test case	Status
ask	01_how_many_pods	✅
ask	02_what_is_wrong_with_pod	✅
ask	04_related_k8s_events	✅
ask	05_image_version	✅
ask	09_crashpod	✅
ask	10_image_pull_backoff	✅
ask	110_k8s_events_image_pull	✅
ask	11_init_containers	✅
ask	13a_pending_node_selector_basic	✅
ask	14_pending_resources	✅
ask	15_failed_readiness_probe	✅
ask	163_compaction_follow_up	✅
ask	17_oom_kill	✅
ask	18_oom_kill_from_issues_history	✅
ask	19_detect_missing_app_details	✅
ask	20_long_log_file_search	❌
ask	24_misconfigured_pvc	✅
ask	24a_misconfigured_pvc_basic	✅
ask	28_permissions_error	🚧
ask	39_failed_toolset	❌
ask	41_setup_argo	✅
ask	42_dns_issues_steps_new_tools	✅
ask	43_current_datetime_from_prompt	✅
ask	45_fetch_deployment_logs_simple	✅
ask	51_logs_summarize_errors	✅
ask	53_logs_find_term	✅
ask	54_not_truncated_when_getting_pods	✅
ask	59_label_based_counting	✅
ask	60_count_less_than	✅
ask	61_exact_match_counting	✅
ask	63_fetch_error_logs_no_errors	✅
ask	79_configmap_mount_issue	✅
ask	83_secret_not_found	✅
ask	86_configmap_like_but_secret	✅
ask	93_calling_datadog[0]	🔧
ask	93_calling_datadog[1]	🔧
ask	93_calling_datadog[2]	🔧

Legend

• ✅ the test was successful
• :minus: the test was skipped
• ⚠️ the test failed but is known to be flaky or known to fail
• 🚧 the test had a setup failure (not a code regression)
• 🔧 the test failed due to mock data issues (not a code regression)
• 🚫 the test was throttled by API rate limits/overload
• ❌ the test failed and should be fixed before merging the PR