SOU-69: offline LangChain/CrewAI/AgentKit examples

[tsouth89]

Summary

• First-party offline examples for LangChain callback, CrewAI LLM+tool, and AgentKit payment mirroring
• Use llm_cost(), correct rail/currency (USD for LLM, x402/USDC for AgentKit), no framework deps
• README pointer to the new demos

Leaves community PR #8 open with review notes — that PR needs live API keys and still has pricing/rail issues in the CrewAI file.

Closes Linear SOU-69
Related: #3

Test plan

• python examples/langchain_callback.py / crewai_tools.py / agentkit_payment.py run offline
• pytest -q — 26 passed
• CI green
• CodeRabbit addressed before merge

[tsouth89]

@coderabbitai review

[coderabbitai]

✅ Action performed

Review finished.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

[coderabbitai]

Warning

Review limit reached

@tsouth89, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 1 minute

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: ec889f4d-669f-400f-a625-4958323c1daa

📥 Commits

Reviewing files that changed from the base of the PR and between 4958ec6 and 633f0b5.

📒 Files selected for processing (2)

• examples/crewai_tools.py
• examples/langchain_callback.py

📝 Walkthrough

Walkthrough

Added three standalone, offline examples for Burnwatch observability. The LangChain-style callback estimates and records LLM spend. The CrewAI-like example records LLM costs and paid-search fees. The AgentKit-style example records successful x402 payment metadata, including transaction hashes. Each example includes a disabled demo entrypoint with simulated inputs.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Title check	✅ Passed	The title clearly summarizes the main change: offline examples for LangChain, CrewAI, and AgentKit.
Description check	✅ Passed	The description is directly related and matches the added offline examples, test plan, and README pointer.

---

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

[coderabbitai]

Actionable comments posted: 2

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 9924141a-fb98-4c53-9f48-5743f1625da3

📥 Commits

Reviewing files that changed from the base of the PR and between 42f26b4 and 4958ec6.

⛔ Files ignored due to path filters (1)

• README.md is excluded by !**/*.md

📒 Files selected for processing (3)

• examples/agentkit_payment.py
• examples/crewai_tools.py
• examples/langchain_callback.py

[tsouth89]

@coderabbitai review

[coderabbitai]

✅ Action performed

Review finished.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.