Repository navigation
docs: add OpenAI Agents SDK documentation-first example - #47
Merged
Merged
Conversation
gjwang
marked this pull request as ready for review
November 11, 2026 08:00
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Owner: growth-Web/01a133d7
OpenAI Agents SDK users can now search and read BlockVectra documentation through its native
MCPServerStreamableHttpclient. The example needs Python 3.12+, uses the documentation-only two-tool route, and prints complete Markdown in JSON without running a model or requiring a wallet, account or API key. English/Chinese instructions and the agent routing table point to the same entry.Validation: 8 focused offline tests plus 6 existing helper tests passed; compileall and diff checks passed. Independent source review: APPROVE_SCOPED, no blockers, exact head
184b1116330edcf2fc00f50a2f8ac1f5c39fccc3/ treea4fa86fd53bc0750c65e0319a2e5c9fec1f50e48.After merge
707680bd5c0acbc64962bb996255e0a02c4c56d1, native SDK QA on Python 3.12.12 / openai-agents 0.24.0 / mcp 2.3.0 completed server discovery → tools/list → search_docs → read_doc: 4 HTTP 200, no retries, full quickstart Markdown matched the saved response (44,959 characters). Requests carried the QA marker; no model API, chain RPC, account or key was used. This proves this explicit SDK tool flow, not a model-driven agent workflow or external adoption. QA used the task environment with the pinned direct dependencies; a separate cleanuv runinstallation was not tested.Local evidence:
merged-sdk-qa/terminal.actual.json, four saved HTTP bodies,merged-sdk-output.native.json, anddelivery-and-qa-consumption.actual.jsonunder this task's evidence directory. Earlier diagnostic failures remain recorded separately; their 3-request prefix was not counted as a completed first read. Existing push CI also completed; no manual CI or new workflow was added.