* Update .NET Copilot SDK cookbook: fix On<T> breaking change, add in-process runtime, tool search, and message provenance recipes
- Fix breaking change: Session.On is now generic (On<T> where T : SessionEvent).
Updated all recipes that used the old non-generic session.On(evt => ...) pattern:
error-handling, pr-visualization, managing-local-files, accessibility-report,
ralph-loop (both .md and .cs where applicable).
- Add new 'In-Process Runtime' recipe (in-process-runtime.md + recipe/in-process-runtime.cs)
demonstrating RuntimeConnection.ForInProcess(), live-tested.
- Document tool search / deferred loading (SessionConfig.ToolSearch / ToolSearchConfig)
in pr-visualization.md, live-tested.
- Document typed message provenance (MessageOptions.Source / MessageSource) in
error-handling.md, live-tested.
- Fix dotnet/README.md recipe index: it was missing Ralph Loop and Accessibility
Report entries; also added the new In-Process Runtime entry.
- Add In-Process Runtime entry to the top-level cookbook/copilot-sdk/README.md
.NET section.
- Update dotnet/recipe/README.md runnable-examples table with the new recipe.
All existing .NET cookbook recipes were rebuilt and rechecked against the current
GitHub Copilot SDK (Copilot CLI 1.0.85); no other breaking changes were found.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Update cookbook model names to current supported models
- Replace stale/nonexistent model IDs (gpt-5, claude-sonnet-4.5,
claude-opus-4.6, gpt-5.1-codex-mini) with current values from the
supported AI models list
- Prefer Model = "auto" wherever a specific model isn't load-bearing
to the recipe's teaching point
- ralph-loop: pin gpt-5.3-codex (current codex-family GA model), since
a dedicated coding model is a deliberate, documented choice for the
autonomous loop
- multiple-sessions: reshape the model narrative so it demonstrates a
real explicit-override use case (A/B testing via claude-sonnet-5)
instead of two sessions sharing the same hardcoded model
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Use SendAndWaitAsync in in-process runtime recipe
Replace the event-based TaskCompletionSource pattern with SendAndWaitAsync so the example waits for the final assistant response, propagates session errors, and uses the SDK timeout behavior.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Update .NET Copilot SDK cookbook for GitHub.Copilot.SDK 1.0
Align the dotnet copilot-sdk cookbook recipes and docs with the 1.0.1 release:
- Namespace GitHub.Copilot.SDK -> GitHub.Copilot
- MCP config uses Dictionary<string, McpServerConfig> + McpStdioServerConfig (drop Type discriminator)
- StopAsync no longer returns an error list; wrap graceful shutdown in try/catch
- GetMessagesAsync -> GetEventsAsync with event pattern matching
- LogLevel string -> CopilotLogLevel.Error enum
* Address PR review: clarify package/namespace, default event case, MCP stdio wording
- Note that the GitHub.Copilot.SDK package exposes the GitHub.Copilot namespace in each recipe
- Add a default case + note to the GetEventsAsync history example so other event kinds are not silently dropped
- Refine accessibility-report docs to describe a local stdio MCP server (McpStdioServerConfig via npx)
* Address re-review: add using for event types, note StopAsync throw behavior
* Apply permission handler requirements across Copilot SDK docs
Co-authored-by: jamesmontemagno <1676321+jamesmontemagno@users.noreply.github.com>
Agent-Logs-Url: https://github.com/jamesmontemagno/awesome-copilot/sessions/adf27a88-92f8-4ca6-b3fe-1204e3bb9963
* Polish permission update formatting in SDK examples
Co-authored-by: jamesmontemagno <1676321+jamesmontemagno@users.noreply.github.com>
Agent-Logs-Url: https://github.com/jamesmontemagno/awesome-copilot/sessions/adf27a88-92f8-4ca6-b3fe-1204e3bb9963
* Fix review comments on SDK permission handling PR
Address 5 review comments from PR #1103:
1. Fix invalid object literal syntax (stray comma) in resumeSession
example in copilot-sdk-nodejs.instructions.md
2. Replace unused PermissionHandler import with actual usage in
cookbook/copilot-sdk/python/recipe/ralph_loop.py (was using
inline lambda instead)
3. Replace unused approveAll import with actual usage in
cookbook/copilot-sdk/nodejs/recipe/ralph-loop.ts (was using
inline handler instead)
4. Add missing PermissionHandler import to 4 Python code snippets
in skills/copilot-sdk/SKILL.md that reference it without importing
5. Add missing approveAll import to 3 TypeScript code snippets
in skills/copilot-sdk/SKILL.md that reference it without importing
* Refactor session creation to improve code formatting and consistency across SDK examples
* Fix formatting: split multi-property lines and put closing braces on own lines
Address review comments on PR #1107:
- Split OnPermissionRequest + Model onto separate lines in Go, C#, TypeScript
- Put closing }); on its own line consistently across all examples
- Fix indentation in SKILL.md Quick Start, CLI URL, Error Handling sections
- Fix cookbook Go multiple-sessions and error-handling formatting
- Fix ralph-loop.md TypeScript indentation
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: jamesmontemagno <1676321+jamesmontemagno@users.noreply.github.com>
Add a new cookbook recipe that generates WCAG accessibility reports using
the Playwright MCP server. Includes streaming output, structured report
formatting, and optional Playwright test generation.
- C#, TypeScript, Python, and Go implementations
- Markdown documentation for each language
- Updated cookbook.yml, copilot-sdk README, and package.json
- Add WorkingDirectory/working_directory to pin sessions to project root
- Add OnPermissionRequest/on_permission_request for unattended operation
- Add tool execution event logging for visibility
- Add See Also cross-links to error-handling and persisting-sessions
- Add best practices for WorkingDirectory and permission auto-approval
- Consistent across all 4 languages (Node.js, Python, .NET, Go)
Git operations (commit, push) belong in the prompt instructions, not
hardcoded in the loop orchestrator. The SDK recipes should focus purely
on the SDK API: create client, create session, send prompt, destroy.
- Move session.On handler outside loop to prevent handler accumulation (C#)
- Use TrySetResult instead of SetResult to avoid duplicate-set exceptions (C#)
- Wrap CreateSessionAsync in broader try/finally so client always stops (C#)
- Fix PersistentRalphLoop to use maxIterations parameter instead of hardcoded 10
- Align model name to gpt-5.1-codex-mini across all doc snippets
- Fix completion promise DONE -> COMPLETE in usage snippet
- Replace Claude references with generic model terminology
Add iterative RALPH-loop (Read, Act, Log, Persist, Halt) pattern
implementations for all four supported languages:
- C#/.NET: ralph-loop.cs with documentation
- Node.js/TypeScript: ralph-loop.ts with documentation
- Python: ralph_loop.py with documentation (async API)
- Go: ralph-loop.go with documentation
Each recipe demonstrates:
- Self-referential iteration where AI reviews its own output
- Completion promise detection to halt the loop
- Max iteration safety limits
- File persistence between iterations
Verified against real Copilot SDK APIs:
- Python: fully verified end-to-end with github-copilot-sdk
- Node.js: fully verified end-to-end with @github/copilot-sdk
- C#: compiles and runs successfully with GitHub.Copilot.SDK
- Go: compiles against github.com/github/copilot-sdk/go v0.1.23
Jon GallowayandCopilot
Aaron Powell
Anthony Shaw