azure-dev / azure.ai.routines
AGENTS.md573 starsChanged 8 months agoMITView on GitHub
Use this file together with cli/azd/AGENTS.md. This guide supplements the root azd instructions with the conventions that are specific to this extension. azure.ai.routines is a first-party azd extension under cli/azd/extensions/azure.ai.routines/. It runs as a separate Go binary and talks to the azd host over gRPC. The user-facing surface is azd ai routine <verb> — CRUD over Microsoft Foundry Routines attached to a Foundry project endpoint. Useful places to start: - internal/cmd/: Cobra commands and verb implementations - Project-endpoint resolution comes…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository25 other files it gives its agents.
- cli/azd/AGENTS.mdAGENTS.md
- cli/azd/extensions/azure.ai.agents/AGENTS.mdAGENTS.md
- cli/azd/extensions/azure.ai.connections/AGENTS.mdAGENTS.md
- cli/azd/extensions/azure.ai.inspector/AGENTS.mdAGENTS.md
- cli/azd/extensions/azure.ai.projects/AGENTS.mdAGENTS.md
- cli/azd/extensions/azure.ai.skills/AGENTS.mdAGENTS.md
- cli/azd/extensions/azure.ai.toolboxes/AGENTS.mdAGENTS.md
- ext/vscode/AGENTS.mdAGENTS.md
- .github/skills/extension-user-contract-review/evals/fixtures/cli/azd/AGENTS.mdAGENTS.md
- ext/vscode/.github/copilot-instructions.mdCopilot instructions
- .github/copilot-instructions.mdCopilot instructions
- azdSkill
- agentic-workflowsSkill
- azd-code-reviewerSkill
- azd-grpc-contractsSkill
- azd-preflightSkill
- changelog-generationSkill
- extension-user-contract-reviewSkill
- foundry-extension-scenario-authoringSkill
- foundry-extension-scenario-pr-regressionSkill
- foundry-extension-scenario-suite-runSkill
- senseiSkill
- tool-version-upgradeSkill
- weekly-demo-videoSkill
- weekly-reportSkill
The file
We split this AGENTS.md into the rules it gives an agent
9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
Use this file together with cli/azd/AGENTS.md.
- Distinctive: line 36
If extension work depends on a new azd core change, plan for two PRs:
- Distinctive: line 62
Create a structured error once, as close as possible to the place where you know the final category, code, and suggestion.
- Very specific: line 64
If err is already a structured error, return it unchanged.
- Distinctive: line 68
Prefer the dedicated helpers at the Azure/gRPC boundary:
- Very specific: line 91
After the GitHub release is live, a follow-up PR updates cli/azd/extensions/registry.json so azd users can install the new version.
- Very specific: line 107
Do not use log.Fatal or log.Panic for expected failures — return an error instead.
- Distinctive: line 126
Use modern Go 1.26 patterns where they help readability.
- Very specific: line 131
When using PromptSubscription(), create credentials with Subscription.UserTenantId, not Subscription.TenantId.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 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.
Files
Azure AI Routines Extension - Agent Instructions
Use this file together with cli/azd/AGENTS.md. This guide supplements the root azd
instructions with the conventions that are specific to this extension.
Overview
azure.ai.routines is a first-party azd extension under
cli/azd/extensions/azure.ai.routines/. It runs as a separate Go binary and talks
to the azd host over gRPC.
The user-facing surface is azd ai routine <verb> — CRUD over Microsoft Foundry
Routines attached to a Foundry project endpoint.
Useful places to start:
internal/cmd/: Cobra commands and verb implementations- Project-endpoint resolution comes from the sibling
azure.ai.projectsextension (and the shared cascade); do not re-implement it here.
Build and test
From cli/azd/extensions/azure.ai.routines:
# Build using developer extension (for local development)
azd x build
# Or build using Go directly
go build
# Run unit tests
go test ./... -count=1If extension work depends on a new azd core change, plan for two PRs:
- Land the core change in
cli/azdfirst. - Land the extension change after that, updating this module to the newer azd
dependency with
go get github.com/azure/azure-dev/cli/azd && go mod tidy.
For local development, draft work, or validating both sides together before the core PR is merged, you may temporarily add:
replace github.com/azure/azure-dev/cli/azd => ../../That replace points this extension at your local cli/azd checkout instead of
the version in go.mod. Do not merge the extension with that replace still
present.
Error handling
Return plain Go errors by default, and wrap lower-level failures with
fmt.Errorf("context: %w", err) where useful.
This extension uses an internal/exterrors package (modeled on azure.ai.agents /
azure.ai.toolboxes) for stable telemetry categories, error codes, and
user-facing suggestions:
- Create a structured error once, as close as possible to the place where you know the final category, code, and suggestion.
- If
erris already a structured error, return it unchanged. Do not wrap it withfmt.Errorf("context: %w", err)— during gRPC serialization, azd preserves the structured error's own message/code/category, not the outer wrapper text. - Prefer the dedicated helpers at the Azure/gRPC boundary:
exterrors.ServiceFromAzure(err, operation)forazcore.ResponseError(data-plane and ARM calls).exterrors.FromPrompt(err, contextMessage)forazdClient.Prompt().*failures.
Release preparation
A new extension release ships in two PRs:
PR 1 — Version bump
Bumps the extension to the new version. Touches only:
version.txt— new semver stringextension.yaml—version:fieldCHANGELOG.md— new release section at the top
Once merged, the team triggers the CI release pipeline, which builds, signs, and publishes the extension binaries as a GitHub release.
PR 2 — Registry update
After the GitHub release is live, a follow-up PR updates
cli/azd/extensions/registry.json so azd users can install the new version.
The contents of that file are produced by running azd x publish against the
published release artifacts (which computes the artifact URLs and checksums).
The resulting PR should contain only the regenerated registry.json entry for
the extension, and in some cases updated test snapshots as well.
Output: log vs fmt
Extensions write directly to stdout/stderr — there is no Console abstraction
from azd core.
fmt.Print*— user-facing output (stdout). Pair withoutput.With*Formathelpers for styled text.log.Print*— developer diagnostics (stderr). Hidden unless--debugis set. Never uselogfor anything the user needs to see.- Do not use
log.Fatalorlog.Panicfor expected failures — return an error instead.
// ✅ log — internal detail the user doesn't need to see
log.Printf("routine show: pending-routine read failed for %q: %v", name, err)
// ✅ fmt — user-facing status and results
fmt.Printf("Created routine %s at version %s.\n", name, version)
// ❌ fmt used for debug noise — user sees internal details they can't act on
fmt.Printf("Parsed endpoint: host=%s, path=%s\n", host, path) // use log.Printf
// ❌ log used for user-facing info — user never sees it without --debug
log.Printf("No routines found on project") // use fmt.Print*Other extension conventions
- Use modern Go 1.26 patterns where they help readability.
- Reserved azd globals (
--output,--no-prompt) are inherited fromextCtx, not registered as flags on each verb. - Lowercase-normalize
--outputwhen reading it fromextCtxso downstream branches can compare with== "json". - When using
PromptSubscription(), create credentials withSubscription.UserTenantId, notSubscription.TenantId.
API spec alignment
The authoritative TypeSpec is in
azure-rest-api-specs PR #43498
(specification/ai-foundry/data-plane/Foundry/src/routines/). The client in
internal/pkg/routines/ matches that spec; routines list responses use
value + continuationToken, run-history list responses use value +
nextPageToken, and both list operations send pagination via limit and
after query parameters.
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
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.

