agentleFS
MicrosoftKnown publishermicrosoft-foundry/foundry-samples/samples/csharp/hosted-agents/bring-your-own/conversation_engine/adapter_mode/AGENTS.md

foundry-samples / adapter_mode

AGENTS.md485 starsChanged 3 months agoMITView on GitHub

This standalone sample exposes only the Hosted voice_conversation_engine:1.0.0 protocol. Bridge message version remains 1.0. Do not modify sibling samples. - Keep Python and .NET adapter-mode behavior, tests and docs aligned. - Customers edit the plain streaming Echo handler and its small mapping, not the sample-maintained Adapter protocol runtime. - Call the HTTP-shaped handler in process. Do not register HTTP invocations, add another service/Agent, or use a loopback/network HTTP client. - Preserve interruption, cancellation, deadlines, ID correlation, bounded capacity, heard-text bookkeeping…

The file

We split this AGENTS.md into the rules it gives an agent

6 rules. About 1 is common, 5 are distinctive, and 0 are very specific to this project.

  • ≈1

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep Python and .NET adapter-mode behavior, tests and docs aligned.

    line 6
  2. Distinctive:

    Call the HTTP-shaped handler in process.

    line 9
  3. Distinctive:

    Keep Echo stateless/model-free and preserve whitespace/Unicode exactly.

    line 15
  4. Distinctive:

    No sibling-path imports, local packages, private feeds or generated VS Code files.

    line 16
  5. Common:

    Use structured logging without prompts, responses or credentials.

    line 17
  6. Distinctive:

    Keep explicit package pins and nuget.org-only sources.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Coding instructions — CE Adapter Mode

This standalone sample exposes only the Hosted voice_conversation_engine:1.0.0 protocol. Bridge message version remains 1.0. Do not modify sibling samples.

  • Keep Python and .NET adapter-mode behavior, tests and docs aligned.
  • Customers edit the plain streaming Echo handler and its small mapping, not the sample-maintained Adapter protocol runtime.
  • Call the HTTP-shaped handler in process. Do not register HTTP invocations, add another service/Agent, or use a loopback/network HTTP client.
  • Preserve interruption, cancellation, deadlines, ID correlation, bounded capacity, heard-text bookkeeping and lifecycle cleanup. Never block the receive loop.
  • Drain the handler and finalization before sending success; errors after its SSE done event must remain failures. Do not buffer the complete response.
  • Keep Echo stateless/model-free and preserve whitespace/Unicode exactly.
  • No sibling-path imports, local packages, private feeds or generated VS Code files.
  • Use structured logging without prompts, responses or credentials.
  • Keep explicit package pins and nuget.org-only sources. Invocations beta.8 and Core beta.30 are published; use normal restore, not source-built SDK packages or private feeds.
  • The shared cloud runner lacks CE support. Retain its central deployment skiplist entry, public owner/behavior spec, local schema/plan validation and dedicated socket tests; never describe these as cloud E2E.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.