Repository navigation
Add native A2A Echo and Copilot web-search travel samples - #1158
Open
Hameed Kunkanoor (Hameedkunkanoor) wants to merge 14 commits into
Open
Hameed Kunkanoor (Hameedkunkanoor) wants to merge 14 commits into
Hameed Kunkanoor (Hameedkunkanoor) wants to merge 14 commits into
Conversation
Include only deterministic Echo and direct A2A travel research with bounded Toolbox web search and versioned user-isolated saved plans. Use public beta SDKs, sample documentation and shared behavior fixtures; exclude the standalone bug-bash guide and Support Case sample. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Bind specialist evidence to the plan ID and version captured before delegation. Accept partial cited-search success while preserving bounded attempts and all receipts, and allow additional successful delegations in the cloud fixture. Add offline regressions and document the research binding. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Validate native A2A 1.0 contracts and collect checked JSON-RPC Task artifact evidence through the shared runner. Preserve multi-agent deployments with explicit target, specialist endpoint bindings and cell-owned toolbox lifecycle. Add policy, transport, runner and toolbox integration regressions; keep existing Responses and Invocations behavior. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Verify completed Echo artifact and exact saved Task retrieval in a fresh hosted deployment. Separate only recognized azd update notices from raw JSON-RPC evidence; preserve protocol errors and reject unexpected trailing output. Add regressions for the actual CLI output shape. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Return failed Tasks without rethrowing, preserve partial planner and failed-specialist receipts, clear recovered specialist failures and align public Agent Cards. Correct service-key cleanup, GitHub init prerequisites and RBAC cache hints. Include sharing-branch backports of partial-search success and version-bound research, with real SDK failed Task send/list/get regressions. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Reject unsafe Toolbox paths before authentication, allow metadata-only edits of existing pending drafts, preserve stderr retry evidence, manage only CI-owned planner Consumer assignments, and use upstream main sample URLs. Add focused boundary, completion and role lifecycle regressions. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Use a deterministic principal/project/role assignment ID and retain CI runtime access across job cleanup. Stable agent identities are shared by concurrent builds, so ephemeral grant cleanup cannot safely revoke their access. Document explicit administrative retirement and test overlapping acquisitions and cleanup. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Deploy CI specialists first and bind planner discovery/invocations to their captured versions. Preserve retryable JSON-RPC service errors for retry classification, retain web-search artifacts on failed specialist Tasks, and require matching plan/version saves for every researched plan. Add protocol, deployment, receipt and multi-plan regressions. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Validate each hosted-agent project independently. Route explicit transient failed-Task status diagnostics through bounded retries while preserving terminal failures and per-attempt evidence. Add runner and classifier regressions. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Route dependency failures through bounded deployment retries, separate validated A2A diagnostics from answer artifacts, and propagate safe model error codes through specialists and planner receipts. Cover recovery, retry exhaustion, permanent and malformed failures, successful error-like output, and mixed failure causes. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Apply bounded throttling retries to failed-Task and JSON-RPC HTTP 429 messages without scanning successful artifacts. Cover recovery, retry exhaustion, and nonmatching prose/status codes. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Hameed Kunkanoor (Hameedkunkanoor)
requested a review
from a team
as a code owner
November 11, 2026 15:59
Hameed Kunkanoor (Hameedkunkanoor)
deployed
to
L4-validation
November 11, 2026 15:59 — with 
GitHub Actions
Active
GitHub Actions
Active
Contributor
There was a problem hiding this comment.
🟡 Changes recommended
A successful Flight call for one plan can clear another plan’s unresolved research failure, allowing completion without the failed plan’s research recovering.
1 open issue
What changed in this PR
Adds native A2A examples to the Python hosted-agent samples and extends shared CI to deploy and validate them. This repository-branch replacement for #1144 preserves the earlier review history; reported offline validation does not establish a fresh Travel cloud run.
Changes:
- Adds deterministic Echo and a three-agent travel planner with bounded web search and versioned, user-isolated research storage.
- Extends contract validation, discovery, deployment, invocation and bounded retries for native A2A 1.0.
- Adds deployment guides, request examples, behavior fixtures and regression coverage.
| File | Description |
|---|---|
| samples/python/hosted-agents/README.md | Links both native A2A samples. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/trip-request.json | Provides a public travel-research request. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/toolbox.json | Defines the web-search-only toolbox. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/tests/test_research.py | Covers research evidence and version safeguards. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/tests/test_failures.py | Covers failure reporting and retry recovery. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/travel-agent/tools.py | Implements request-scoped specialist delegation. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/travel-agent/pyproject.toml | Pins planner runtime dependencies. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/travel-agent/plan_store.py | Implements versioned trip-storage tools. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/travel-agent/main.py | Hosts the planner and emits Task receipts. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/travel-agent/client.py | Coordinates the model, specialists and storage. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/travel-agent/agents.py | Validates and authenticates specialist discovery. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/travel-agent/.azdignore | Excludes local files from packaging. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/travel-agent/.agentignore | Excludes local files from agent uploads. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/hotel-agent/pyproject.toml | Pins hotel runtime dependencies. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/hotel-agent/main.py | Hosts hotel research with failure receipts. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/hotel-agent/client.py | Runs bounded hotel web searches. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/hotel-agent/.azdignore | Excludes local files from packaging. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/hotel-agent/.agentignore | Excludes local files from agent uploads. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/flight-agent/pyproject.toml | Pins flight runtime dependencies. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/flight-agent/main.py | Hosts flight research with failure receipts. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/flight-agent/client.py | Runs bounded flight web searches. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/flight-agent/.azdignore | Excludes local files from packaging. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/src/flight-agent/.agentignore | Excludes local files from agent uploads. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/README.md | Documents deployment, storage and research limitations. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/azure.yaml | Configures all three hosted agents. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/AGENTS.md | Documents sample maintenance and safety constraints. |
| samples/python/hosted-agents/bring-your-own/a2a/travel-planner-web-search/.gitignore | Excludes generated development files. |
| samples/python/hosted-agents/bring-your-own/a2a/echo/src/echo-a2a/pyproject.toml | Pins Echo runtime dependencies. |
| samples/python/hosted-agents/bring-your-own/a2a/echo/src/echo-a2a/main.py | Returns deterministic completed Echo Tasks. |
| samples/python/hosted-agents/bring-your-own/a2a/echo/src/echo-a2a/.azdignore | Excludes local files from packaging. |
| samples/python/hosted-agents/bring-your-own/a2a/echo/src/echo-a2a/.agentignore | Excludes local files from agent uploads. |
| samples/python/hosted-agents/bring-your-own/a2a/echo/README.md | Documents hosted and local Echo usage. |
| samples/python/hosted-agents/bring-your-own/a2a/echo/get-task.json | Provides a native Task-retrieval request. |
| samples/python/hosted-agents/bring-your-own/a2a/echo/echo-request.json | Provides a blocking Echo request. |
| samples/python/hosted-agents/bring-your-own/a2a/echo/azure.yaml | Configures native A2A Echo deployment. |
| samples/python/hosted-agents/bring-your-own/a2a/echo/AGENTS.md | Documents Echo maintenance constraints. |
| samples/python/hosted-agents/bring-your-own/a2a/echo/.gitignore | Excludes generated files and local state. |
| .github/scripts/test/test_check_hosted_agent_contracts.py | Tests A2A contract and version validation. |
| .github/scripts/test/test_ado_pipeline_fixtures.py | Recognizes A2A in published-fixture checks. |
| .github/scripts/hosted_agent_test_spec.py | Adds A2A planning and deployment settings. |
| .github/scripts/check_hosted_agent_contracts.py | Accepts native A2A 1.0 contracts. |
| .azure-pipelines/scripts/hosted-agents/tests/test-hosted-agent-session-quota.sh | Tests A2A retry diagnostic classification. |
| .azure-pipelines/scripts/hosted-agents/tests/test_hosted_agent_a2a.py | Covers A2A preparation, transport and retries. |
| .azure-pipelines/scripts/hosted-agents/tests/test_a2a_access.py | Tests persistent runtime-access grants. |
| .azure-pipelines/scripts/hosted-agents/scripts/prepare_hosted_agent_a2a.py | Preserves services and pins specialist deployments. |
| .azure-pipelines/scripts/hosted-agents/scripts/invoke_hosted_agent_a2a.py | Validates native Tasks and collects evidence. |
| .azure-pipelines/scripts/hosted-agents/scripts/hosted-agent-retry.sh | Classifies transient and throttling diagnostics. |
| .azure-pipelines/scripts/hosted-agents/scripts/hosted_agent_a2a_access.py | Ensures persistent planner runtime access. |
| .azure-pipelines/scripts/hosted-agents/run-hosted-agent.sh | Integrates A2A deployment and invocation. |
| .azure-pipelines/scripts/hosted-agents/discover-samples.sh | Discovers native A2A matrix entries. |
| .azure-pipelines/hosted-agents-samples-ci.yml | Selects A2A for fixture validation. |
| .azure-pipelines/hosted-agent-tests/README.md | Documents A2A contracts and CI lifecycle. |
| .azure-pipelines/hosted-agent-tests/python/bring-your-own/a2a/travel-planner-web-search/test-spec.yml | Defines travel research behavior assertions. |
| .azure-pipelines/hosted-agent-tests/python/bring-your-own/a2a/echo/test-spec.yml | Defines the Echo behavior assertion. |
Review effort: Balanced
| ) | ||
| result = {"agent": card.name, "task_id": task.id, "answer": answer} | ||
| calls.append({"tool": name, **result, **binding}) | ||
| failures[:] = [failure for failure in failures if failure != name] |
This branch was successfully deployed
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.
Repository-branch replacement for #1144
This PR carries the exact reviewed head of #1144
(
4e60cda7322823f49c3412dd08b57ee2db17e6e3) on a branch inmicrosoft-foundry/foundry-samples, rather than the contributor fork.See #1144 for the earlier review discussions and fixes. That PR remains open
for review history until this replacement is confirmed.
The original PR's required
Foundry Samples Hosted Agents CIcheck had notreported a result for this commit. This repository-branch PR uses the normal
upstream CI authorization and trigger process; successful cloud execution is
not assumed or claimed.
Latest focused validation: 28 A2A tests and the shared session quota/throttling
shell suite passed, including HTTP 429 service-error retry recovery and bounded
exhaustion. The preceding complete retry fixes passed 109 shared CI Python
tests, 28 locked-SDK runtime tests and both existing shell suites. Formatting,
Bash syntax and whitespace checks passed, with no new Ruff findings versus the
existing baseline. These are local/offline results, not a fresh live Azure E2E run.
The original implementation and historical validation details follow.
Purpose
Add two native A2A Python hosted-agent samples for inclusion in the public sample
repository. This branch starts from upstream main, not from the larger sharing PR.
bring-your-own/a2a/echobring-your-own/a2a/travel-planner-web-searchIncludes these two samples, their shared behavior fixtures, sample-index links,
and shared CI support needed to validate and run native A2A.
No Support Case sample, synthetic non-web-search travel sample, standalone
bug-bash guide, deployment-specific environment, logs or saved plans.
Architecture
endpoints before attaching credentials.
No Toolbox A2A delegation or direct model HTTP implementation.
cited search is required. Failed/source-less attempts remain in receipts.
across the planner's custom-tool callback boundary.
history; user isolation, 30-day default TTL, ETag/version conflict protection.
Specialist evidence is bound to the plan ID/version captured before delegation,
so late results cannot clear a newer revision's pending refresh.
unverified: no claim of exact-date fares, availability,cancellation eligibility, booking or payment.
operation receipts remain compact.
1.0.0b1and Core2.3.1b1,with genuine per-runtime locks.
Web Search is billed and uses Bing grounding services; the README includes the
data-handling and geographic/compliance-boundary disclosures.
Native A2A CI support
fake Responses declaration.
using the cell's explicit session and A2A 1.0 wire version. It validates
JSON-RPC IDs/errors, completed Task state and artifact text, including
HTTP-200/CLI-exit-zero failures; request, headers and raw evidence are retained.
three service/source projects, wires the specialists' own endpoints, and
uses the existing temporary-toolbox isolation/verification/cleanup lifecycle.
Validation
harness tests, 17 contract-policy tests and 2 published-fixture tests.
each with container and code deploy modes.
Both native-A2A fixture plans build successfully. Ruff, new-file Black
formatting, Bash syntax and whitespace checks passed.
public beta SDK runtime, including in-flight stale research rejection.
Echo: hello, completed Task and explicitunsupported cancellation in the public-beta runtime. Runtime dependency policy
previously passed with
--resolvefor both samples; no dependency changesare introduced by this CI fix.
betas to the existing test project (Flight/Hotel v2, Planner v3). Six
execution/storage checks completed while reusing one CLI session. This is
historical evidence, not a cloud deployment of the new review or CI changes.
project enablement, model availability, runtime permissions or a fresh cloud
end-to-end pass. Live cloud execution remains subject to the normal trusted
pipeline and configured project prerequisites.
Known limitations
Research-quality findings remain: some model prose reduced arrival deadlines to
clock-only comparisons, and clarification offered options unsupported by the
current trip schema. Repeating an unchanged update can also leave a tool failure
recorded even if later research saves succeed. Exact-price booking behavior,
forced restarts and cross-user cloud isolation are not claimed as verified.
Sharing PR is preserved
PR #1126 and
feature/a2a-llm-release-plannerremain unchanged by these fixes forusers to share and run the bug-bash guide. This PR remains the separate merge proposal.
Hosted Echo public-beta verification
Echo now uses AgentServer A2A 1.0.0b1 and Core 2.3.1b1 from public PyPI in both PRs. A fresh direct-code hosted deployment passed native SendMessage with exactly Echo: hello in a completed Task. GetTask with the same caller/session returned the identical stored Task, including artifacts, history and status; X-Platform-Server confirmed both beta SDK versions. The runtime and lock were verified identical across both branches and the deployment before pushing. Only Echo was redeployed for this check, not Travel. Dependency-policy validation with --resolve passed; 94 shared runner regressions passed. This does not establish the cause of the separately reported deployment's downstream 400 without its session logs, nor claim cross-user isolation or restart recovery.