Compare commits

..

6 Commits

Author SHA1 Message Date
Darrel Miller
3ea24d4906 docs: Update JSON-RPC binding to include google.rpc.ErrorInfo structure for A2A errors 2026-03-11 09:28:23 -04:00
Mike Smith
e49ff5ce5c
Lint fix 2026-03-06 23:36:15 +00:00
Mike Smith
d9475c457e
Add clarification that additional details are allowed. 2026-03-06 23:31:13 +00:00
Mike Smith
ca9b13effe
Apply suggestions from code review
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-06 23:30:04 +00:00
Mike Smith
c0894bb8cc
Merge branch 'main' into error-updates 2026-03-06 23:27:18 +00:00
Mike Smith
4aaa185597
docs: Update HTTP+JSON error mapping to use google.rpc.Status
For alignment with gRPC transcoding.
2026-03-06 23:22:47 +00:00
43 changed files with 299 additions and 5554 deletions

16
.github/CODEOWNERS vendored
View File

@ -5,14 +5,14 @@
# https://help.github.com/en/github/creating-cloning-and-archiving-repositories/about-code-owners#codeowners-syntax
* @a2aproject/a2a-tsc
docs/ @a2aproject/a2a-tsc
scripts/ @a2aproject/a2a-tsc
docs/ @a2aproject/tech-writing
scripts/ @a2aproject/tech-writing @a2aproject/google-a2a-eng
specification/ @a2aproject/a2a-tsc
docs/specification.md @a2aproject/a2a-tsc
GOVERNANCE.md @a2aproject/a2a-tsc
.mkdocs/ @a2aproject/a2a-tsc
.mkdocs.yml @a2aproject/a2a-tsc
README.md @a2aproject/a2a-tsc
.gemini/ @a2aproject/a2a-tsc
.mkdocs/ @a2aproject/a2a-tsc
.github/ @a2aproject/a2a-tsc
.mkdocs/ @a2aproject/tech-writing
.mkdocs.yml @a2aproject/tech-writing
README.md @a2aproject/tech-writing
.gemini/ @a2aproject/tech-writing @a2aproject/google-a2a-eng
.mkdocs/ @a2aproject/tech-writing
.github/ @a2aproject/tech-writing

View File

@ -19,7 +19,6 @@ AService
ASq
AStarlette
AUTOCOMMIT
Abhimanyu
Agentspace
Agno
Autogen
@ -77,12 +76,10 @@ Jhb
Jra
KGgo
KRW
LFX
LHR
LJcvt
LLM
LLMs
Lindfors
Lix
MSIs
MWpm
@ -91,13 +88,11 @@ Mvosg
Nszl
OIDC
OOa
OTP
Ollama
PLE
PLW
PMEEi
PTH
Petschulat
Polski
Portugu
QFdk
@ -105,11 +100,9 @@ Qvandrcy
RFCs
RPCs
RUF
SFDC
SLAs
SLF
SSLv
Siwach
Solax
TJS
TMDB
@ -143,7 +136,6 @@ aacacac
aboutasha
achat
aconnect
actioncard
adk
adr
adrs
@ -191,7 +183,6 @@ codegen
codeowner
codespace
codewiki
cpb
crewai
datamodel
datapart
@ -248,7 +239,6 @@ gstatic
gweb
hackathon
hackathons
hexpm
hqdefault
hughesthe
iana
@ -270,7 +260,6 @@ konami
kty
langgraph
lerhaupt
lfx
linenums
linkedin
linting
@ -332,7 +321,6 @@ rst
rvelicheti
sandijean
scm
siwachabhi
sllm
sourced
sourcing
@ -354,11 +342,8 @@ taskstate
taskstatus
textpart
threadsafe
tiangolo
toctree
tok
tolgaki
tomtom
toolkits
tracestate
ugc
@ -369,7 +354,6 @@ versioned
vnd
voa
vscode
vvvvvvvv
weavehacks
webform
webpage

View File

@ -1,6 +0,0 @@
Abhimanyu
lfx
Petschulat
SFDC
Siwach
siwachabhi

View File

@ -5,8 +5,7 @@
"**/images/**",
"**/samples/**",
"**/tests/**",
"**/.git/**",
"**/a2a_logo/**"
"**/.git/**"
],
"threshold": 3,
"reporters": ["html", "markdown"]

View File

@ -23,11 +23,6 @@ on:
types:
- published
workflow_dispatch:
inputs:
version:
description: 'Version to deploy to (e.g., v1.0.0)'
required: true
default: 'dev'
jobs:
build_and_deploy:
@ -56,7 +51,7 @@ jobs:
python-version: 3.13
- name: Setup uv
uses: astral-sh/setup-uv@v7
uses: astral-sh/setup-uv@v5
- name: Restore pip cache
uses: actions/cache@v5
@ -133,14 +128,3 @@ jobs:
bash scripts/deploy_root_files.sh ${{ github.repository }} ${{ secrets.GITHUB_TOKEN }}
env:
GITHUB_EVENT_RELEASE_TAG_NAME: ${{ github.event.release.tag_name }}
- name: Manually deploy specific version from main
if: github.event_name == 'workflow_dispatch'
run: |
mike deploy --push --update-aliases ${{ github.event.inputs.version }} latest
echo "Setting 'latest' as the default version for the site..."
mike set-default --push latest
# Re-deploy 404 page
bash scripts/deploy_root_files.sh ${{ github.repository }} ${{ secrets.GITHUB_TOKEN }}

View File

@ -29,7 +29,7 @@ jobs:
echo "last_month=$first_day..$last_day" >> "$GITHUB_ENV"
- name: Run issue-metrics tool
uses: github-community-projects/issue-metrics@v4
uses: github/issue-metrics@v3
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
SEARCH_QUERY: 'repo:a2aproject/A2A is:issue created:${{ env.last_month }} -reason:"not planned"'

View File

@ -27,7 +27,7 @@ jobs:
steps:
- name: check-spelling
id: spelling
uses: check-spelling/check-spelling@v0.0.26
uses: check-spelling/check-spelling@main
with:
suppress_push_for_open_pull_request: ${{ github.actor != 'dependabot[bot]' && 1 }}
checkout: true

View File

@ -1,88 +1,10 @@
# Changelog
## [1.0.0](https://github.com/a2aproject/A2A/compare/v0.3.0...v1.0.0) (2026-03-12)
### ⚠ BREAKING CHANGES
* **spec:** Combine `TaskPushNotificationConfig` and `PushNotificationConfig` ([#1500](https://github.com/a2aproject/A2A/issues/1500))
* **spec:** remove duplicated ID from the create task push config request ([#1487](https://github.com/a2aproject/A2A/issues/1487))
* **spec:** pluralize configs in `ListTaskPushNotificationConfigs` ([#1486](https://github.com/a2aproject/A2A/issues/1486))
* **spec:** Add LF prefix to the package. ([#1474](https://github.com/a2aproject/A2A/issues/1474))
* **spec:** Switch to non-complex IDs in requests ([#1389](https://github.com/a2aproject/A2A/issues/1389))
* **spec:** Standardize spelling of "canceled" to use American Spelling throughout ([#1283](https://github.com/a2aproject/A2A/issues/1283))
* **spec:** Align enum format with ADR-001 ProtoJSON specification ([#1384](https://github.com/a2aproject/A2A/issues/1384))
* **spec:** Remove redundant `final` field from `TaskStatusUpdateEvent` ([#1308](https://github.com/a2aproject/A2A/issues/1308))
* **spec:** Move `extendedAgentCard` field to `AgentCapabilities` ([#1307](https://github.com/a2aproject/A2A/issues/1307))
* **spec:** Fixes for the last_updated_after field ([#1358](https://github.com/a2aproject/A2A/issues/1358))
* **spec:** modernize oauth 2.0 flows - remove implicit/password, add device code / pkce ([#1303](https://github.com/a2aproject/A2A/issues/1303))
* **spec:** Make "message" field name consistent between protocol bindings ([#1302](https://github.com/a2aproject/A2A/issues/1302))
* **spec:** Remove deprecated fields from a2a.proto for v1.0 release ([#1301](https://github.com/a2aproject/A2A/issues/1301))
* **spec:** Rename `supportsAuthenticatedExtendedCard` to `supportsExtendedAgentCard` ([#1222](https://github.com/a2aproject/A2A/issues/1222))
* **spec:** Remove v1s from a2a url http bindings
* **spec:** Large refactor of specification to separate application protocol definition from mapping to transports
## [0.4.0](https://github.com/a2aproject/A2A/compare/v0.3.0...v0.4.0) (2025-09-15)
### Features
* **spec:** Add `tasks/list` method with filtering and pagination to the specification ([0a9f629](https://github.com/a2aproject/A2A/commit/0a9f629e801d4ae89f94991fc28afe9429c91cbc))
* **spec:** modernize oauth 2.0 flows - remove implicit/password, add device code / pkce ([#1303](https://github.com/a2aproject/A2A/issues/1303)) ([525ff38](https://github.com/a2aproject/A2A/commit/525ff38e5fe2a118f5be5d25189708b590616dd4))
* **spec:** Natively Support Multi-tenancy on gRPC through an additional scope field on the request. ([#1195](https://github.com/a2aproject/A2A/issues/1195)) ([cfbce32](https://github.com/a2aproject/A2A/commit/cfbce32cb0ac2a630597eb8b771691cac5b20a4b)), closes [#1148](https://github.com/a2aproject/A2A/issues/1148)
* **spec:** Provide ability for SDKs to be backwards compatible. ([#1401](https://github.com/a2aproject/A2A/issues/1401)) ([227e249](https://github.com/a2aproject/A2A/commit/227e2493c317004b7e6f7ef4a484e220ffd0b77e))
* **spec:** Remove v1s from a2a url http bindings ([1bd263f](https://github.com/a2aproject/A2A/commit/1bd263f5373fdc8fa7c17ec8bdb24088996b6828))
### Bug Fixes
* Add missing metadata field to Part message in gRPC specification ([#1019](https://github.com/a2aproject/A2A/issues/1019)) ([b3b266d](https://github.com/a2aproject/A2A/commit/b3b266d127dde3d1000ec103b252d1de81289e83)), closes [#1005](https://github.com/a2aproject/A2A/issues/1005)
* Add name field to FilePart protobuf message ([#983](https://github.com/a2aproject/A2A/issues/983)) ([2b7cb6f](https://github.com/a2aproject/A2A/commit/2b7cb6f8408e6324c48fb82c71839c67a18f1fab)), closes [#984](https://github.com/a2aproject/A2A/issues/984)
* Clarify blocking calls return on interrupted states ([#1403](https://github.com/a2aproject/A2A/issues/1403)) ([0655ff3](https://github.com/a2aproject/A2A/commit/0655ff324a93b7e0eaebc108666e6703998b4a9c))
* **doc:** Makes JSON-RPC SendMessage response clearer ([#1241](https://github.com/a2aproject/A2A/issues/1241)) ([5792804](https://github.com/a2aproject/A2A/commit/57928043727e5e002a1395dadfb5f699d0626b1c))
* **docs:** Clearer wording around context id. ([#1588](https://github.com/a2aproject/A2A/issues/1588)) ([dec790a](https://github.com/a2aproject/A2A/commit/dec790aa063943e3ac70e972f9da513c25ab420c))
* **grpc:** Fix inconsistent property name between gRPC and JSON-RPC in Message object ([#1100](https://github.com/a2aproject/A2A/issues/1100)) ([2a1f819](https://github.com/a2aproject/A2A/commit/2a1f819aaa2540602ee81498e159ebe0192be818))
* **grpc:** missing field in gRPC spec - state_transition_history ([#1138](https://github.com/a2aproject/A2A/issues/1138)) ([a2de798](https://github.com/a2aproject/A2A/commit/a2de7981cadeaa5197bee56cbd6ab7b2c5da2541)), closes [#1139](https://github.com/a2aproject/A2A/issues/1139)
* **grpc:** Update `CreateTaskPushNotificationConfig` endpoint to `/v1/{parent=tasks/*/pushNotificationConfigs}` ([#979](https://github.com/a2aproject/A2A/issues/979)) ([911f9b0](https://github.com/a2aproject/A2A/commit/911f9b059c52dd65497b76ccf63d196ca84c7f0e))
* **proto:** Add icon_url to a2a.proto ([#986](https://github.com/a2aproject/A2A/issues/986)) ([17e7f62](https://github.com/a2aproject/A2A/commit/17e7f62df9a3e4ca0768ab8d4f0bb7573b3d73e1))
* **proto:** Adds metadata field to A2A DataPart proto ([#1004](https://github.com/a2aproject/A2A/issues/1004)) ([a8b45dc](https://github.com/a2aproject/A2A/commit/a8b45dcc429a5571ef8a24c36336bf84b89bbd7f))
* Remove unimplemented state_transition_history capability field ([#1396](https://github.com/a2aproject/A2A/issues/1396)) ([c768a44](https://github.com/a2aproject/A2A/commit/c768a44da0f719595e375636f3cab9898ff6df75)), closes [#1228](https://github.com/a2aproject/A2A/issues/1228)
* Restore CreateTaskPushNotificationConfig method naming ([#1402](https://github.com/a2aproject/A2A/issues/1402)) ([d14f410](https://github.com/a2aproject/A2A/commit/d14f4107119bf0fe0dff9e2c577eb4ab70b51793))
* Revert "chore(gRPC): Update a2a.proto to include metadata on GetTaskRequest" ([#1000](https://github.com/a2aproject/A2A/issues/1000)) ([e6b8c65](https://github.com/a2aproject/A2A/commit/e6b8c654a86a6ee461bb5c7be5d5b81004b80a92))
* Simplify Part message structure by flattening FilePart and DataPart ([#1411](https://github.com/a2aproject/A2A/issues/1411)) ([bfae8f7](https://github.com/a2aproject/A2A/commit/bfae8f7791e019f21f6662dd73fce0b3ab261cd6))
* **spec:** Add LF prefix to the package. ([#1474](https://github.com/a2aproject/A2A/issues/1474)) ([a54e809](https://github.com/a2aproject/A2A/commit/a54e80904aa32c74a14bc2c3d21bf82936ccbbdd))
* **spec:** add metadata to `CancelTaskRequest` ([#1485](https://github.com/a2aproject/A2A/issues/1485)) ([c441b91](https://github.com/a2aproject/A2A/commit/c441b910b64d45514ae929a42e7367c2a9a2f6c3)), closes [#1484](https://github.com/a2aproject/A2A/issues/1484)
* **spec:** Added clarification on timestamps in HTTP query params ([#1425](https://github.com/a2aproject/A2A/issues/1425)) ([6292104](https://github.com/a2aproject/A2A/commit/6292104e359efca05bd8703174517b6f961ae4e1))
* **spec:** Added clarifying text around messages and artifacts ([#1424](https://github.com/a2aproject/A2A/issues/1424)) ([b03d141](https://github.com/a2aproject/A2A/commit/b03d141aeab6abd71a229e85c81f7e4c00b537ec))
* **spec:** Adjust field number for `ListTasksRequest.tenant` to prevent missing number ([#1470](https://github.com/a2aproject/A2A/issues/1470)) ([cd16c52](https://github.com/a2aproject/A2A/commit/cd16c5276b4c662ca1823678d07487a624cad606))
* **spec:** Clarify contextId behavior when message is sent with taskId but without contextId ([#1309](https://github.com/a2aproject/A2A/issues/1309)) ([a336a5a](https://github.com/a2aproject/A2A/commit/a336a5a4846fdf85079d4e310339ea0128922ee7))
* **spec:** Clarify versioning strategy and client responsibilities in protocol specification ([#1259](https://github.com/a2aproject/A2A/issues/1259)) ([a4afeea](https://github.com/a2aproject/A2A/commit/a4afeea788b3877101f7a63c2e50091709490058))
* **spec:** Fix/1251 clarify authentication scheme ([#1256](https://github.com/a2aproject/A2A/issues/1256)) ([3e6c7db](https://github.com/a2aproject/A2A/commit/3e6c7db90790c2d05dad3ab1a313de26debe5cb7))
* **spec:** Fixes for the last_updated_after field ([#1358](https://github.com/a2aproject/A2A/issues/1358)) ([0e204bf](https://github.com/a2aproject/A2A/commit/0e204bf878eb63619e205d3419ebc48d4cd35849))
* **spec:** Make "message" field name consistent between protocol bindings ([#1302](https://github.com/a2aproject/A2A/issues/1302)) ([1e5f462](https://github.com/a2aproject/A2A/commit/1e5f46206403982cc629a0dad535856b28c269aa)), closes [#1230](https://github.com/a2aproject/A2A/issues/1230)
* **spec:** make `history_length` optional ([#1071](https://github.com/a2aproject/A2A/issues/1071)) ([0572953](https://github.com/a2aproject/A2A/commit/057295311b8ddda63bdda56c82a694c76d307e37))
* **spec:** pluralize configs in `ListTaskPushNotificationConfigs` ([#1486](https://github.com/a2aproject/A2A/issues/1486)) ([cf735cb](https://github.com/a2aproject/A2A/commit/cf735cb87056ff6d62abd21a1a66ccb14a23c38e))
* **spec:** Remove config from binding. ([#1587](https://github.com/a2aproject/A2A/issues/1587)) ([010b9cc](https://github.com/a2aproject/A2A/commit/010b9cc936fbafd66610282ad66070da2cb28855))
* **spec:** Remove deprecated fields from a2a.proto for v1.0 release ([#1301](https://github.com/a2aproject/A2A/issues/1301)) ([60f83c3](https://github.com/a2aproject/A2A/commit/60f83c3faac4770b231f038406c9e02282887a25)), closes [#1227](https://github.com/a2aproject/A2A/issues/1227)
* **spec:** remove duplicated ID from the create task push config request ([#1487](https://github.com/a2aproject/A2A/issues/1487)) ([393898d](https://github.com/a2aproject/A2A/commit/393898dfeefa37186aced5b61733c5d2c0d9c34a))
* **spec:** Remove metadata field from ListTasksRequest ([#1235](https://github.com/a2aproject/A2A/issues/1235)) ([b6ef9ee](https://github.com/a2aproject/A2A/commit/b6ef9eec558c877fb69024df090a8bb63c542a1c))
* **spec:** Remove reserved and fix tags ordering ([#1494](https://github.com/a2aproject/A2A/issues/1494)) ([1997c9d](https://github.com/a2aproject/A2A/commit/1997c9d63058ca0b89361a7d6e508f4641a6f68b))
* **spec:** Rename `supportsAuthenticatedExtendedCard` to `supportsExtendedAgentCard` ([#1222](https://github.com/a2aproject/A2A/issues/1222)) ([c196824](https://github.com/a2aproject/A2A/commit/c196824396bb4af4c595f30e2c503a5ab1dbac4b)), closes [#1215](https://github.com/a2aproject/A2A/issues/1215)
* **spec:** Standardize spelling of "canceled" to use American Spelling throughout ([#1283](https://github.com/a2aproject/A2A/issues/1283)) ([4dd980f](https://github.com/a2aproject/A2A/commit/4dd980f6ff1989177faffa631a695aba811c56ad))
* **spec:** Suggest Unique Identifier fields to be UUID ([#966](https://github.com/a2aproject/A2A/issues/966)) ([00cf76e](https://github.com/a2aproject/A2A/commit/00cf76e7bbc752842ef254f3d4136ed1b5751f6e))
* **spec:** Switch to non-complex IDs in requests ([#1389](https://github.com/a2aproject/A2A/issues/1389)) ([2596c1c](https://github.com/a2aproject/A2A/commit/2596c1c5e0effd941880e8487d38d78b74b9c0bf)), closes [#1390](https://github.com/a2aproject/A2A/issues/1390)
* **spec:** Update security schemes example ([#1364](https://github.com/a2aproject/A2A/issues/1364)) ([f9a8f5b](https://github.com/a2aproject/A2A/commit/f9a8f5b85d5b07824c52d55d63f7d71ccc6303c5))
* Update the Java tutorials and descriptions ([#1181](https://github.com/a2aproject/A2A/issues/1181)) ([202aa06](https://github.com/a2aproject/A2A/commit/202aa069e66f701bacf2156d42d8916fc96a5188))
### Documentation
* **spec:** Align enum format with ADR-001 ProtoJSON specification ([#1384](https://github.com/a2aproject/A2A/issues/1384)) ([810eaa1](https://github.com/a2aproject/A2A/commit/810eaa1c6e6462f845a00774f8622b998272116e)), closes [#1344](https://github.com/a2aproject/A2A/issues/1344)
### Code Refactoring
* **spec:** Combine `TaskPushNotificationConfig` and `PushNotificationConfig` ([#1500](https://github.com/a2aproject/A2A/issues/1500)) ([d1ed0da](https://github.com/a2aproject/A2A/commit/d1ed0da587d2d634ba0b81a40d082cee0850b81b))
* **spec:** Large refactor of specification to separate application protocol definition from mapping to transports ([b078419](https://github.com/a2aproject/A2A/commit/b0784199543eebf2e95dcb02e9336cb213923506))
* **spec:** Move `extendedAgentCard` field to `AgentCapabilities` ([#1307](https://github.com/a2aproject/A2A/issues/1307)) ([40d6286](https://github.com/a2aproject/A2A/commit/40d6286fbe29fb083d416b77e84122df8d70ae9d))
* **spec:** Remove redundant `final` field from `TaskStatusUpdateEvent` ([#1308](https://github.com/a2aproject/A2A/issues/1308)) ([5b101cc](https://github.com/a2aproject/A2A/commit/5b101cce0fff449c1120ad50ce360acf7c90bac3))
* **spec:** Add `tasks/list` method for retrieving and filtering tasks with pagination
## [0.3.0](https://github.com/a2aproject/A2A/compare/v0.2.6...v0.3.0) (2025-07-30)

View File

@ -2,84 +2,7 @@
We'd love to accept your patches and contributions to this project.
## Development Setup
### Prerequisites
To contribute to this project, you will need the following tools installed:
- [Python 3.10+](https://www.python.org/downloads/)
- [uv](https://docs.astral.sh/uv/getting-started/installation/) - Fast Python package installer and resolver.
- [Node.js & npm](https://nodejs.org/en/download/) - For markdown formatting tools.
- [Docker](https://www.docker.com/get-started) - Required for running the local linter.
## Working with Documentation
The A2A documentation is built using [MkDocs](https://www.mkdocs.org/) with the [Material theme](https://squidfunk.github.io/mkdocs-material/).
### Local Setup
1. **Create a virtual environment:**
```bash
uv venv .doc-venv
```
2. **Activate the virtual environment:**
```bash
source .doc-venv/bin/activate # Unix/macOS
# .doc-venv\Scripts\activate # Windows
```
3. **Install dependencies:**
```bash
uv pip install -r requirements-docs.txt
```
### Build and Serve
1. **Build the documentation:**
This script regenerates the JSON schema from the protocol definition, builds the SDK documentation, and then builds the MkDocs site.
```bash
./scripts/build_docs.sh
```
2. **Serve the documentation locally:**
Run the following command to start a local server with live reloading:
```bash
mkdocs serve
```
3. **View the documentation:**
Open [http://localhost:8000](http://localhost:8000) in your browser.
## Code Standards
### Linting
We use [Super Linter](https://github.com/super-linter/super-linter) to ensure code quality across the repository. You can run the linter locally using Docker:
```bash
./scripts/lint.sh
```
### Formatting
We use [markdownlint](https://github.com/igorshubovych/markdownlint-cli) for formatting markdown files. You can fix most formatting issues automatically by running:
```bash
./scripts/format.sh
```
### Conventional Commits
We follow the [Conventional Commits](https://www.conventionalcommits.org/) specification for our commit messages. This helps us automate our release process and maintain a clear changelog.
## Contribution Process
## Contribution process
### Code reviews
@ -88,17 +11,18 @@ use GitHub pull requests for this purpose. Consult
[GitHub Help](https://help.github.com/articles/about-pull-requests/) for more
information on using pull requests.
### Workflow
### Contributor Guide
You may follow these steps to contribute:
1. **Fork the official repository.** This will create a copy of the official repository in your own account.
2. **Sync the branches.** This will ensure that your copy of the repository is up-to-date with the latest changes from the official repository.
3. **Work on your forked repository's feature branch.** This is where you will make your changes to the code.
4. **Test your changes.** Build and preview the documentation locally to ensure everything looks correct.
5. Format and lint your code. Run ./scripts/format.sh and ./scripts/lint.sh to ensure your changes meet our standards.
6. **Commit your updates.** Use conventional commit messages on your feature branch.
7. **Submit a pull request.** Submit a PR from your fork's feature branch to the official repository's `main` branch.
8. **Resolve any feedback.** Work with reviewers to address any comments or requested changes.
4. **Commit your updates on your forked repository's feature branch.** This will save your changes to your copy of the repository.
5. **Submit a pull request to the official repository's main branch.** This will request that your changes be merged into the official repository.
6. **Resolve any linting errors.** This will ensure that your changes are formatted correctly.
Be patient! It may take some time for your pull request to be reviewed and merged.
Here are some additional things to keep in mind during the process:
- **Test your changes.** Before you submit a pull request, make sure that your changes work as expected.
- **Be patient.** It may take some time for your pull request to be reviewed and merged.

View File

@ -6,7 +6,7 @@ The Agent2Agent project is governed by the Technical Steering Committee. The Com
| :--- | :--- | :--- | :--- |
| **Google** | Todd Segal | Principal Engineer | [@ToddSegal](https://github.com/ToddSegal) |
| **Microsoft** | Darrel Miller | Partner API Architect | [@darrelmiller](https://github.com/darrelmiller) |
| **Cisco** | Luca Muscariello | Distinguished Engineer | [@muscariello](https://github.com/muscariello) |
| **Cisco** | Luca Muscariello | Principal Engineer | [@muscariello](https://github.com/muscariello) |
| **Amazon Web Services** | Abhimanyu Siwach | Senior Software Engineer | [@siwachabhi](https://github.com/siwachabhi) |
| **Salesforce** | Stephen Petschulat | Principal Architect | [@spetschulatSFDC](https://github.com/spetschulatSFDC) |
| **ServiceNow** | Sean Hughes | Director of Open Science | [@hughesthe1st](https://github.com/hughesthe1st) |
@ -32,8 +32,6 @@ The Agent2Agent project is governed by the Technical Steering Committee. The Com
a. **"Startup Phase."** At the inception of the Project, each organization listed in the [`GOVERNANCE`](GOVERNANCE.md) file in the governance repository of the Project will have the right to appoint (and remove and replace) one employee to serve as a voting member of the TSC.
Adding new organizations to the GOVERNANCE file will be determined through a proposal to the TSC GOVERNANCE.md file. Any new organization will be added through a majority vote of the TSC, and an employee of that organization will serve as a voting member of the TSC.
b. **"Steady State."** The TSC will decide upon a "steady state" composition of the TSC (whether by election, subproject technical leads, or other method as determined by the TSC), to take effect from the date that is 18 months following the inception of the Project, or at such other point as determined by the TSC.
c. The TSC may choose an alternative approach for determining the voting members of the TSC, and any such alternative approach will be documented in the GOVERNANCE file. Any meetings of the Technical Steering Committee are intended to be open to the public, and can be conducted electronically, via teleconference, or in person.
@ -69,8 +67,6 @@ While the Project aims to operate as a consensus-based community, if any TSC dec
Quorum for TSC meetings requires at least fifty percent of all voting members of the TSC to be present. The TSC may continue to meet if quorum is not met but will be prevented from making any decisions at the meeting. Except as provided in Section 7.c. and 8.a, decisions by vote at a meeting require a majority vote of those in attendance, provided quorum is met. Decisions made by electronic vote without a meeting require a majority vote of all voting members of the TSC.
A voting member who has not attended a meeting of the TSC within the last six weeks (as measured by the LFX attendance tracking) shall be determined to be an inactive voting member. They will not be included in active votes, which means that they will not be counted for quorum, and the sponsoring organization may choose to replace the named TSC member within a reasonable timeframe.
### TSC Meetings
TSC Meetings are held on the Linux Foundation's meeting platform. [https://zoom-lfx.platform.linuxfoundation.org/meetings/agent2agent](https://zoom-lfx.platform.linuxfoundation.org/meetings/agent2agent) has meeting details and recordings of past meetings.
Our [working doc for TSC Meeting Agendas](https://docs.google.com/document/d/1Dx6qYfCjSChHKRMwLJcvtDjq6igYTAKFW9Vg1IMPCUk/view) is in Google Docs.

View File

@ -1,55 +0,0 @@
# A2A Protocol Ships v1.0: Production-Ready Standard for Agent-to-Agent Communication
The A2A Protocol community today are announcing the release of A2A Protocol v1.0, marking the first stable, production-ready version of the open standard for communication between AI agents. The protocol is guided by a technical steering committee with representatives from eight major technology companies.
As organizations build increasingly sophisticated multi-agent systems, interoperability has become the defining challenge. Teams can coordinate agents effectively within a single platform, but connecting those systems across technology stacks and organizational boundaries remains difficult. A2A addresses that challenge by combining support for multiple protocol bindings, seamless version negotiation, and a common semantic model so agents can interoperate across systems with predictable behavior.
The v1.0 release emphasizes maturity rather than reinvention: the core ideas remain intact, while rough edges have been removed, ambiguous areas clarified, and enterprise deployment requirements addressed more directly. The official SDKs ensure v1.0 A2A agents work seamlessly with older versions.
## Delivering on enterprise requirements
The v1.0 release introduces several capabilities aimed at production environments where trust, scale, and operational control are non-negotiable.
- **Heterogeneous environment support** enables interoperability across diverse technology stacks through multi-protocol bindings and version negotiation, so enterprises are not tied to a single vendor or platform.
- **Multi-tenancy support** allows a single endpoint to securely host many agents.
- **Signed Agent Cards** provide cryptographic verification of agent identity and metadata, establishing trust before interaction across organizational boundaries.
- **Improved security posture** modernizes security flows and removes legacy patterns that are no longer aligned with current best practices.
Together, these changes move A2A from early adopter implementations toward broader enterprise confidence, especially in regulated or multi-party scenarios.
## Web-aligned architecture for scale
A2A v1.0 aligns with core architectural principles of the web: stateless, layered architecture, standard protocol bindings, and infrastructure-friendly communication patterns. That alignment matters operationally because organizations can scale agent interactions with the same proven load balancing, gateway, security and observability patterns they already use for web systems.
The standard builds on industry-proven protocols, including JSON+HTTP, gRPC, and JSON-RPC. It also keeps the barrier to entry low: in its simplest form, an A2A interaction can begin with a single HTTP request.
A2A also gives consumers flexibility in how they receive results. Depending on workload and operational needs, clients can use polling, streaming, or webhooks to consume task updates and responses.
## Complementary to MCP, not a replacement
The release also reinforces A2A's relationship with the Model Context Protocol (MCP), a point that has generated confusion in early ecosystem discussions.
MCP and A2A solve different layers of the problem. MCP is commonly used for tool and context integration at the individual agent level. A2A focuses on communication and coordination between agents. In practice, many systems will use both: MCP inside agents, A2A between agents.
## Smooth migration from earlier versions
The v1.0 release tightens specification behavior, which includes breaking changes in the interaction protocol. AgentCard, however, has evolved in a backward-compatible way and now allows agents to advertise support for both existing v0.3 protocol behavior and v1.0 simultaneously. This enables clients to migrate progressively rather than through a single cutover.
That approach is intended to protect current investments while still delivering the benefits of a cleaner, more durable standard.
## Why this release matters now
AI agents are increasingly deployed across departments, products, and partner ecosystems. At that scale, the key question is no longer whether agents can coordinate within one stack, but whether they can collaborate reliably across organizational and platform boundaries. Open protocols determine whether organizations can compose best-of-breed systems or become locked into isolated stacks.
A2A v1.0 gives the market a stronger foundation for open multi-agent collaboration. The community is now focused on delivering multi-language v1.0 SDK support to help developers build conformant solutions with ease.
The complete v1.0 materials, including specification and migration documentation, are available at [a2a-protocol.org](https://a2a-protocol.org) and on [GitHub](https://github.com/a2aproject/A2A).
---
**About A2A Protocol**
The Agent-to-Agent (A2A) Protocol is an open standard that enables AI agents to discover capabilities, communicate, and delegate tasks across teams, products, and organizations. The A2A Technical Steering Committee includes representatives from AWS, Cisco, Google, IBM Research, Microsoft, Salesforce, SAP, and ServiceNow.
**Media Contact**
A2A Protocol Community
[https://a2a-protocol.org](https://a2a-protocol.org)

Binary file not shown.

Before

Width:  |  Height:  |  Size: 30 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 51 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 31 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 51 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 15 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 43 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 15 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 43 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 14 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 43 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 226 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 125 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 28 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 51 KiB

View File

@ -67,39 +67,6 @@ These agentic frameworks have built-in A2A integration, making it easy to get st
- [Slide (Tyler)](https://slide.mintlify.app/guides/a2a-integration)
- [Strands Agents](https://strandsagents.com/latest/documentation/docs/user-guide/concepts/multi-agent/agent-to-agent/)
## Community SDKs
Building an A2A agent in a language not covered by the [official SDKs](./sdk/index.md)? These community-maintained implementations have you covered.
### 🦀 Rust — a2a-rust
![Stars](https://img.shields.io/github/stars/tomtom215/a2a-rust?style=flat-square) [![Crate](https://img.shields.io/crates/v/a2a-protocol-sdk?style=flat-square)](https://crates.io/crates/a2a-protocol-sdk)
[tomtom215/a2a-rust](https://github.com/tomtom215/a2a-rust) · A2A spec v1.0.0 · Full SDK with JSON-RPC, REST, WebSocket, and gRPC transports.
### 🦀 Rust — a2a-rs
![Stars](https://img.shields.io/github/stars/EmilLindfors/a2a-rs?style=flat-square) [![Crate](https://img.shields.io/crates/v/a2a-rs?style=flat-square)](https://crates.io/crates/a2a-rs)
[EmilLindfors/a2a-rs](https://github.com/EmilLindfors/a2a-rs) · A2A spec v0.3.0 · Modular workspace with core protocol, AP2 extension, and agent framework.
### 🍎 Swift — A2AClient
![Stars](https://img.shields.io/github/stars/tolgaki/a2a-client-swift?style=flat-square)
[tolgaki/a2a-client-swift](https://github.com/tolgaki/a2a-client-swift) · A2A spec v1.0.0 · Swift Package Manager. iOS 15+, macOS 12+, watchOS 8+, tvOS 15+.
### 💧 Elixir — a2a
![Stars](https://img.shields.io/github/stars/actioncard/a2a-elixir?style=flat-square) [![Hex](https://img.shields.io/hexpm/v/a2a?style=flat-square)](https://hex.pm/packages/a2a)
[actioncard/a2a-elixir](https://github.com/actioncard/a2a-elixir) · A2A spec v0.2.0 · OTP-native with Agent behaviour, TaskStore, and supervision tree.
!!! tip "Want to add your SDK?"
Open an issue on [a2aproject/A2A](https://github.com/a2aproject/A2A/issues/new?title=Community%20SDK%20Submission) with a link to your repository and published package.
**Requirements:** Spec compliance, published package on standard registry, documentation, tests with CI, Apache 2.0 license, and active maintenance.
## The Future is Interoperable
The excitement surrounding Google's A2A protocol clearly indicates a strong belief in its potential to revolutionize multi-agent AI systems. By providing a standardized way for AI agents to communicate and collaborate, A2A is poised to unlock new levels of automation and innovation. As enterprises increasingly adopt AI agents, A2A represents a crucial step towards realizing the full power of interconnected AI ecosystems.

View File

@ -82,7 +82,6 @@ collaborate effectively with each other and with users.
- [InfoSys](https://www.infosys.com)
- [Intuit](https://www.intuit.com)
- [Iron Mountain](https://www.ironmountain.com/)
- [JamJet](https://github.com/jamjet-labs/jamjet)
- [JetBrains](https://www.jetbrains.com)
- [JFrog](https://jfrog.com)
- [Kakao](https://www.kakaocorp.com)
@ -109,7 +108,6 @@ collaborate effectively with each other and with users.
- [Nisum](http://www.nisum.com)
- [Noorle Inc](http://www.noorle.com)
- [NTT DATA](https://www.nttdata.com)
- [OIXA Protocol](https://oixa.io)
- [Optimizely Inc](https://www.optimizely.com/)
- [Oracle / NetSuite](https://www.oracle.com/netsuite)
- [Palo Alto Networks](https://www.paloaltonetworks.com/)
@ -140,7 +138,6 @@ collaborate effectively with each other and with users.
- [Solace](https://solace.com/products/agent-mesh/)
- [Solo.io](https://www.solo.io/)
- [Stacklok, Inc](https://stacklok.com)
- [Strale](https://strale.dev)
- [Supertab](https://www.supertab.co/post/supertab-connect-partners-with-google-cloud-to-enable-ai-agents)
- [Suzega](https://suzega.com/)
- [TCS](https://www.tcs.com)
@ -164,7 +161,6 @@ collaborate effectively with each other and with users.
- [Weights & Biases](https://wandb.ai/wandb_fc/product-announcements-fc/reports/Powering-Agent-Collaboration-Weights-Biases-Partners-with-Google-Cloud-on-Agent2Agent-Interoperability-Protocol---VmlldzoxMjE3NDg3OA)
- [Wipro](https://www.wipro.com)
- [Workday](https://www.workday.com)
- [WritBase](https://github.com/Writbase/writbase)
- [Writer](https://writer.com)
- [Zenity](https://zenity.io)
- [Zeotap](https://www.zeotap.com)

View File

@ -1,13 +1,15 @@
# A2A protocol roadmap
**Last updated:** March 10, 2026
**Last updated:** Jul 16, 2025
## Near-term initiatives
- Release `1.0` version of the protocol which represents significant maturation of the protocol with enhanced clarity, stronger specifications, and important structural improvements.
- [What's New in A2A Protocol v1.0](https://a2a-protocol.org/latest/whats-new-v1/) has further updates.
- Continue to support additional [A2A extensions](topics/extensions.md) with SDK support.
- Prioritize community-led development with standardized processes for contributing to the specification, SDKs and tooling.
- Release `0.3` version of the protocol which we intend to keep supported and without breaking changes for a significant amount of time with backward compatibility of the SDKs starting at version `0.3`. As part of this release there are a few known breaking changes including:
- Update the `/.well-known/agent.json` path for hosting Agent Cards to `/.well-known/agent-card.json` based on feedback from IANA.
- Refactor class fields to be more Pythonic and adopt `snake_case`. [PR 199](https://github.com/a2aproject/a2a-python/pull/199)
- Solidify the support for [A2A extensions](topics/extensions.md) with SDK support (starting with the Python SDK) and publishing sample extensions.
- Introduce support for signed Agent Cards [Discussion 199](https://github.com/a2aproject/A2A/discussions/199#discussioncomment-13770576) to allow verifying the integrity of Agent Card content.
- Enhance the client side support in SDK (starting with Python) to expose ready-to-use A2A clients, streamlined auth handling and improved handling of tasks.
To review recent protocol changes see [Release Notes](https://github.com/a2aproject/A2A/releases).
@ -15,12 +17,15 @@ To review recent protocol changes see [Release Notes](https://github.com/a2aproj
### Governance
The TSC looks to streamline opportunities for contribution through [A2A extensions](topics/extensions.md), [Samples](https://github.com/a2aproject/a2a-samples) and participation.
The protocol has been [donated](https://www.linuxfoundation.org/press/linux-foundation-launches-the-agent2agent-protocol-project-to-enable-secure-intelligent-communication-between-ai-agents) to the Linux Foundation. The TSC is working on implementing a governance structure that prioritizes community-led development with standardized processes for contributing to the specification, SDKs and tooling. As part of the effort there will be dedicated working groups created for specific areas of the protocol.
### Agent Registry
Agent Registry enables the discovery of agents and is a critical component of a multi-agent system. There is an active and ongoing discussion in the community around the latest [Discussion 741](https://github.com/a2aproject/A2A/discussions/741).
### Validation
As the A2A ecosystem matures, it becomes critical for the A2A community to have tools to validate their agents. The community has launched two efforts to help with validation. Learn more about [A2A Inspector](https://github.com/a2aproject/a2a-inspector) and the [A2A Protocol Technology Compatibility Kit](https://github.com/a2aproject/a2a-tck) (TCK).
As the A2A ecosystem matures, it becomes critical for the A2A community to have tools to validate their agents. The community has launched two efforts to help with validation which the group will continue to enhance in the coming months. Learn more about [A2A Inspector](https://github.com/a2aproject/a2a-inspector) and the [A2A Protocol Technology Compatibility Kit](https://github.com/a2aproject/a2a-tck) (TCK).
### SDKs

View File

@ -1,14 +1,15 @@
# A2A SDK
The following table lists the supported languages for official A2A SDKs and their repositories.
A2A currently hosts SDKs in five languages (Python, Go, JS, Java, .NET).
| Language | Repository |
|------------|----------------------------------------------------------|
| Python | [`a2a-python`](https://github.com/a2aproject/a2a-python) |
| Go | [`a2a-go`](https://github.com/a2aproject/a2a-go) |
| Java | [`a2a-java`](https://github.com/a2aproject/a2a-java) |
| JavaScript | [`a2a-js`](https://github.com/a2aproject/a2a-js) |
| C#/.NET | [`a2a-dotnet`](https://github.com/a2aproject/a2a-dotnet) |
| Rust | [`a2a-rs`](https://github.com/a2aproject/a2a-rs) |
The following table lists the supported languages and their stability.
| Language | Support |
| :--------- | :------- |
| Python | [Stable](https://github.com/a2aproject/a2a-python) |
| Go | [Stable](https://github.com/a2aproject/a2a-go) |
| Java | [Stable](https://github.com/a2aproject/a2a-java) |
| JavaScript | [Stable](https://github.com/a2aproject/a2a-js) |
| C#/.NET | [Stable](https://github.com/a2aproject/a2a-dotnet) |
The A2A project provides numerous samples across supported languages in the [a2a-samples repository](https://github.com/a2aproject/a2a-samples).

View File

@ -1,11 +1,13 @@
# Agent2Agent (A2A) Protocol Specification
# Agent2Agent (A2A) Protocol Specification (Release Candidate v1.0)
??? note "**Latest Released Version** [`1.0.0`](https://a2a-protocol.org/v1.0.0/specification)"
??? note "**Latest Released Version** [`0.3.0`](https://a2a-protocol.org/v0.3.0/specification)"
**Previous Versions**
- [`0.3.0`](https://a2a-protocol.org/v0.3.0/specification)
- [`0.2.6`](https://a2a-protocol.org/v0.2.6/specification)
- [`0.2.5`](https://a2a-protocol.org/v0.2.5/specification)
- [`0.2.4`](https://a2a-protocol.org/v0.2.4/specification)
- [`0.2.0`](https://a2a-protocol.org/v0.2.0/specification)
- [`0.1.0`](https://a2a-protocol.org/v0.1.0/specification)
See [Release Notes](https://github.com/a2aproject/A2A/releases) for changes made between versions.
@ -53,7 +55,7 @@ graph TB
subgraph L2 ["A2A Operations"]
direction LR
G[Send Message] ~~~ H[Send Streaming Message] ~~~ I[Get Task] ~~~ J[List Tasks] ~~~ K[Cancel Task] ~~~ L[Get Agent Card]
G[Send Message] ~~~ H[Stream Message] ~~~ I[Get Task] ~~~ J[List Tasks] ~~~ K[Cancel Task] ~~~ L[Get Agent Card]
end
subgraph L3 ["Protocol Bindings"]
@ -213,7 +215,7 @@ The agent MAY return a `Task` for complex processing with status/artifact update
#### 3.1.3. Get Task
Retrieves the current state (including status, artifacts, and optionally history) of a previously initiated task. This is typically used for polling the status of a task initiated with Send Message, or for fetching the final state of a task after being notified via a push notification or after a stream has ended.
Retrieves the current state (including status, artifacts, and optionally history) of a previously initiated task. This is typically used for polling the status of a task initiated with message/send, or for fetching the final state of a task after being notified via a push notification or after a stream has ended.
**Inputs:**
@ -439,19 +441,19 @@ This section defines common parameter objects used across multiple operations.
{{ proto_to_table("SendMessageConfiguration") }}
**Execution Mode:**
**Blocking vs Non-Blocking Execution:**
The `return_immediately` field in [`SendMessageConfiguration`](#322-sendmessageconfiguration) controls whether the operation returns immediately or waits for task completion. Operations are blocking by default:
The `blocking` field in [`SendMessageConfiguration`](#322-sendmessageconfiguration) controls whether the operation waits for task completion:
- **Blocking (`return_immediately: false` or unset)**: The operation MUST wait until the task reaches a terminal state (`COMPLETED`, `FAILED`, `CANCELED`, `REJECTED`) or an interrupted state (`INPUT_REQUIRED`, `AUTH_REQUIRED`) before returning. The response MUST include the latest task state with all artifacts and status information. This is the default behavior.
- **Blocking (`blocking: true`)**: The operation MUST wait until the task reaches a terminal state (`COMPLETED`, `FAILED`, `CANCELED`, `REJECTED`) or an interrupted state (`INPUT_REQUIRED`, `AUTH_REQUIRED`) before returning. The response MUST include the latest task state with all artifacts and status information.
- **Non-Blocking (`return_immediately: true`)**: The operation MUST return immediately after creating the task, even if processing is still in progress. The returned task will have an in-progress state (e.g., `working`, `input_required`). It is the caller's responsibility to poll for updates using [Get Task](#313-get-task), subscribe via [Subscribe to Task](#316-subscribe-to-task), or receive updates via push notifications.
- **Non-Blocking (`blocking: false`)**: The operation MUST return immediately after creating the task, even if processing is still in progress. The returned task will have an in-progress state (e.g., `working`, `input_required`). It is the caller's responsibility to poll for updates using [Get Task](#313-get-task), subscribe via [Subscribe to Task](#316-subscribe-to-task), or receive updates via push notifications.
The `return_immediately` field has no effect:
The `blocking` field has no effect:
- when the operation returns a direct [`Message`](#414-message) response instead of a task.
- for streaming operations, which always return updates in real-time.
- on configured push notification configurations, which operates independently of execution mode.
- on configured push notification configurations, which operates independently of blocking mode.
#### 3.2.3. Stream Response
@ -541,7 +543,7 @@ All error responses in the A2A protocol, regardless of binding, **MUST** convey
1. **Error Code**: A machine-readable identifier for the error type (e.g., string code, numeric code, or protocol-specific status)
2. **Error Message**: A human-readable description of the error
3. **Error Details** (optional): An array of objects providing additional structured information about the error. Each object in the array **MUST** include a `@type` key that identifies the object's type (using [ProtoJSON `Any` representation](https://protobuf.dev/programming-guides/json)). Well-known types from the [`google.rpc` error model](https://cloud.google.com/apis/design/errors#error_model) (e.g., `ErrorInfo`, `BadRequest`) **SHOULD** be used where applicable. Error details may be used for:
3. **Error Details** (optional): Additional structured information about the error, such as:
- Affected fields or parameters
- Contextual information (e.g., task ID, timestamp)
- Suggestions for resolution
@ -659,7 +661,7 @@ The A2A protocol provides three complementary mechanisms for clients to receive
**Streaming:**
- Real-time delivery of events as they occur
- Operations: Send Streaming Message ([Section 3.1.2](#312-send-streaming-message)) and Subscribe to Task ([Section 3.1.6](#316-subscribe-to-task))
- Operations: Stream Message ([Section 3.1.2](#312-send-streaming-message)) and Subscribe to Task ([Section 3.1.6](#316-subscribe-to-task))
- Low latency, efficient for frequent updates
- Requires persistent connection support
- Best for: Interactive applications, real-time dashboards, live progress monitoring
@ -848,7 +850,7 @@ When a task update occurs, the agent sends an HTTP POST request to the configure
```http
POST {webhook_url}
Authorization: {authentication_scheme} {credentials}
Content-Type: application/a2a+json
Content-Type: application/json
{
/* StreamResponse object - one of: */
@ -1055,7 +1057,7 @@ Clients indicate their desire to opt into the use of specific extensions through
```http
POST /message:send HTTP/1.1
Host: agent.example.com
Content-Type: application/a2a+json
Content-Type: application/json
Authorization: Bearer token
A2A-Extensions: https://example.com/extensions/geolocation/v1,https://standards.org/extensions/citations/v1
@ -1162,7 +1164,7 @@ When an agent supports multiple protocols, all supported protocols **MUST**:
| Functionality | JSON-RPC Method | gRPC Method | REST Endpoint |
| :------------------------------ | :--------------------------------- | :--------------------------------- | :------------------------------------------------------ |
| Send message | `SendMessage` | `SendMessage` | `POST /message:send` |
| Send streaming message | `SendStreamingMessage` | `SendStreamingMessage` | `POST /message:stream` |
| Stream message | `SendStreamingMessage` | `SendStreamingMessage` | `POST /message:stream` |
| Get task | `GetTask` | `GetTask` | `GET /tasks/{id}` |
| List tasks | `ListTasks` | `ListTasks` | `GET /tasks` |
| Cancel task | `CancelTask` | `CancelTask` | `POST /tasks/{id}:cancel` |
@ -1177,17 +1179,17 @@ When an agent supports multiple protocols, all supported protocols **MUST**:
All A2A-specific errors defined in [Section 3.3.2](#332-error-handling) **MUST** be mapped to binding-specific error representations. The following table provides the canonical mappings for each standard protocol binding:
| A2A Error Type | JSON-RPC Code | gRPC Status | HTTP Status |
| :------------------------------------ | :------------ | :-------------------- | :-------------------------- |
| `TaskNotFoundError` | `-32001` | `NOT_FOUND` | `404 Not Found` |
| `TaskNotCancelableError` | `-32002` | `FAILED_PRECONDITION` | `400 Bad Request` |
| `PushNotificationNotSupportedError` | `-32003` | `FAILED_PRECONDITION` | `400 Bad Request` |
| `UnsupportedOperationError` | `-32004` | `FAILED_PRECONDITION` | `400 Bad Request` |
| `ContentTypeNotSupportedError` | `-32005` | `INVALID_ARGUMENT` | `400 Bad Request` |
| `InvalidAgentResponseError` | `-32006` | `INTERNAL` | `500 Internal Server Error` |
| `ExtendedAgentCardNotConfiguredError` | `-32007` | `FAILED_PRECONDITION` | `400 Bad Request` |
| `ExtensionSupportRequiredError` | `-32008` | `FAILED_PRECONDITION` | `400 Bad Request` |
| `VersionNotSupportedError` | `-32009` | `FAILED_PRECONDITION` | `400 Bad Request` |
| A2A Error Type | JSON-RPC Code | gRPC Status | HTTP Status |
| :------------------------------------ | :------------ | :-------------------- | :--------------------------- |
| `TaskNotFoundError` | `-32001` | `NOT_FOUND` | `404 Not Found` |
| `TaskNotCancelableError` | `-32002` | `FAILED_PRECONDITION` | `409 Conflict` |
| `PushNotificationNotSupportedError` | `-32003` | `UNIMPLEMENTED` | `400 Bad Request` |
| `UnsupportedOperationError` | `-32004` | `UNIMPLEMENTED` | `400 Bad Request` |
| `ContentTypeNotSupportedError` | `-32005` | `INVALID_ARGUMENT` | `415 Unsupported Media Type` |
| `InvalidAgentResponseError` | `-32006` | `INTERNAL` | `502 Bad Gateway` |
| `ExtendedAgentCardNotConfiguredError` | `-32007` | `FAILED_PRECONDITION` | `400 Bad Request` |
| `ExtensionSupportRequiredError` | `-32008` | `FAILED_PRECONDITION` | `400 Bad Request` |
| `VersionNotSupportedError` | `-32009` | `UNIMPLEMENTED` | `400 Bad Request` |
**Custom Binding Requirements:**
@ -1274,33 +1276,6 @@ The Protocol Buffer `optional` keyword is used to distinguish between a field be
Implementations **SHOULD** ignore unrecognized fields in messages, allowing for forward compatibility as the protocol evolves.
### 5.8. Custom Binding Identification
Custom protocol bindings **SHOULD** be identified by a URI. Using a URI as the
identifier provides globally unique identification across all implementers.
The `protocolBinding` field in the Agent Card's `supportedInterfaces` entry
**SHOULD** be a URI:
```json
{
"supportedInterfaces": [
{
"url": "wss://agent.example.com/a2a/websocket",
"protocolBinding": "https://example.com/bindings/websocket/v1",
"protocolVersion": "1.0"
}
]
}
```
When a breaking change is introduced to a binding, a new URI **MUST** be used
so that clients can distinguish between incompatible versions:
```text
https://example.com/bindings/websocket/v1 → https://example.com/bindings/websocket/v2
```
## 6. Common Workflows & Examples
This section provides illustrative examples of common A2A interactions across different bindings.
@ -1485,9 +1460,16 @@ Content-Type: application/problem+json
**Request:**
```http
GET /tasks?contextId=c295ea44-7543-4f78-b524-7a38915ad6e4&pageSize=10&historyLength=3 HTTP/1.1
POST /tasks/list HTTP/1.1
Host: agent.example.com
Content-Type: application/a2a+json
Authorization: Bearer token
{
"contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
"pageSize": 10,
"historyLength": 3
}
```
**Response:**
@ -1518,9 +1500,15 @@ Content-Type: application/a2a+json
**Request:**
```http
GET /tasks?status=TASK_STATE_WORKING&pageSize=20 HTTP/1.1
POST /tasks/list HTTP/1.1
Host: agent.example.com
Content-Type: application/a2a+json
Authorization: Bearer token
{
"status": "TASK_STATE_WORKING",
"pageSize": 20
}
```
**Response:**
@ -1560,9 +1548,16 @@ Content-Type: application/a2a+json
**Request:**
```http
GET /tasks?contextId=c295ea44-7543-4f78-b524-7a38915ad6e4&pageSize=10&pageToken=base64-encoded-cursor-token HTTP/1.1
POST /tasks/list HTTP/1.1
Host: agent.example.com
Content-Type: application/a2a+json
Authorization: Bearer token
{
"contextId": "c295ea44-7543-4f78-b524-7a38915ad6e4",
"pageSize": 10,
"pageToken": "base64-encoded-cursor-token"
}
```
**Response:**
@ -1586,9 +1581,16 @@ Content-Type: application/a2a+json
**Request:**
```http
GET /tasks?pageSize=150&historyLength=-5&status=TASK_STATE_RUNNING HTTP/1.1
POST /tasks/list HTTP/1.1
Host: agent.example.com
Content-Type: application/a2a+json
Authorization: Bearer token
{
"pageSize": 150,
"historyLength": -5,
"status": "running"
}
```
**Response:**
@ -1897,7 +1899,15 @@ The A2A Server:
- **SHOULD** use appropriate binding-specific error codes for authentication challenges or rejections.
- **SHOULD** provide relevant authentication challenge information with error responses.
### 7.5. Server Authorization Responsibilities
### 7.5. In-Task Authentication (Secondary Credentials)
If an agent requires additional credentials during task execution:
1. It **SHOULD** transition the A2A task to the `TASK_STATE_AUTH_REQUIRED` state.
2. The accompanying `TaskStatus.update` **SHOULD** provide details about the required secondary authentication.
3. The A2A Client obtains these credentials out-of-band and provides them in a subsequent message request.
### 7.6. Authorization
Once authenticated, the A2A Server authorizes requests based on the authenticated identity and its own policies. Authorization logic is implementation-specific and **MAY** consider:
@ -1906,62 +1916,6 @@ Once authenticated, the A2A Server authorizes requests based on the authenticate
- Data access policies
- OAuth scopes (if applicable)
### 7.6. In-Task Authorization
In the course of performing a task, an agent may require authorization to perform some action. Examples include:
- An agent requiring an OAuth access token to call an API or another agent
- An agent requiring human approval before a destructive action is taken
In the sections below, we refer to the object that represents the approved authorization as a credential.
Agents may have multiple means for retrieving this authorization, such as via directly sending messages to a human.
A2A provides the capability for agents to delegate the fulfillment of this authorization to the client via the `TASK_STATE_AUTH_REQUIRED` Task state. This provides agents a fallback path for requesting authorization by passing the responsibility to the client.
#### 7.6.1 In-Task Authorization Agent Responsibilities
To request that a client fulfills an authorization request, the agent:
1. MUST use a Task to track the operation it is performing
2. MUST transition the TaskState to `TASK_STATE_AUTH_REQUIRED`
3. MUST include a TaskStatus message explaining the required authorization, unless the details of the authorization have been negotiated out-of-band or via an extension
Agents MUST arrange to receive credentials via an out-of-band means, unless an in-band mechanism has been negotiated out-of-band or via an extension.
If the credential is received out-of-band, the agent SHOULD maintain any active response streams with the client after setting the TaskState to `TASK_STATE_AUTH_REQUIRED`. The agent MAY immediately continue Task processing after receiving the credential, without a requirement that clients send a follow-up message.
Agents SHOULD support receiving messages directed to the Task while the Task remains in `TASK_STATE_AUTH_REQUIRED`. This enables clients to negotiate, correct, or reject an authorization request.
#### 7.6.2 In-Task Authorization Client Responsibilities
Upon receiving a Task in `TASK_STATE_AUTH_REQUIRED`, a client is expected to take action in some way to resolve the agent's request for authorization.
A client may:
- Send a response message to the Task to negotiate, correct, or reject the authorization request.
- Contact another human, agent, or service to fulfill the authorization request
- Directly fulfill the authorization request via an out-of-band or extension negotiated means
If the client is itself an A2A agent actively processing a Task, the client may further delegate the authorization request to its client by transitioning its own Task to `TASK_STATE_AUTH_REQUIRED`. The client SHOULD follow all [In-Task Authorization Agent Responsibilities](#761-in-task-authorization-agent-responsibilities). This enables forming a chain of Tasks in `TASK_STATE_AUTH_REQUIRED`.
Clients may not be aware of when the agent receives credentials out-of-band and subsequently continues Task processing. If a client does not have an active response stream open with the agent, the client risks missing Task updates. To avoid this, a client SHOULD perform one of the following:
- Subscribe to a stream of events for the Task using the [Subscribe to Task](#316-subscribe-to-task) operation
- Register a webhook to receive events, if supported by the agent, using the [Create Push Notification Config](#317-create-push-notification-config) operation
- Begin polling the Task using the [Get Task](#313-get-task) operation
#### 7.6.3 In-Task Authorization Security Considerations
Agents SHOULD receive credentials for in-task authorization requests out of band via a secure channel, such as HTTPS. This ensures that credentials are provided directly to the agent.
In-band credential exchange may be negotiated via out-of-band means or by using extensions. In-band credential exchange can allow credentials to be passed across chains of multiple A2A agents, exposing those credentials to each agent participating in the chain.
If using in-band credential exchange, we recommend adhering to the following security practices:
- Credentials SHOULD be bound to the agent which originated the request, such that only this agent is able to use the credentials. This ensures that credentials propagating through a chain of A2A requests are only usable by the requesting agent.
- Credentials containing sensitive information SHOULD be only readable by the agent which originated the request, such as by encrypting the credential.
## 8. Agent Discovery: The Agent Card
<span id="5-agent-discovery-the-agent-card"></span>
@ -1976,7 +1930,7 @@ For more on discovery strategies, see the [Agent Discovery guide](./topics/agent
Clients can find Agent Cards through:
- **Well-Known URI:** Accessing `https://{server_domain}/.well-known/agent-card.json` (see [Section 8.6](#86-caching) for caching guidance)
- **Well-Known URI:** Accessing `https://{server_domain}/.well-known/agent-card.json`
- **Registries/Catalogs:** Querying curated catalogs of agents
- **Direct Configuration:** Pre-configured Agent Card URLs or content
@ -2211,22 +2165,6 @@ Clients verifying Agent Card signatures **MUST**:
}
```
### 8.6. Caching
Agent Card content changes infrequently relative to the frequency at which clients may fetch it. Servers and clients **SHOULD** use standard HTTP caching mechanisms to reduce unnecessary network overhead.
#### 8.6.1. Server Requirements
- Agent Card HTTP endpoints **SHOULD** include a `Cache-Control` response header with a `max-age` directive appropriate for the agent's expected update frequency
- Agent Card HTTP endpoints **SHOULD** include an `ETag` response header derived from the Agent Card's `version` field or a hash of the card content
- Agent Card HTTP endpoints **MAY** include a `Last-Modified` response header
#### 8.6.2. Client Requirements
- Clients **SHOULD** honor HTTP caching semantics as defined in [RFC 9111](https://www.rfc-editor.org/rfc/rfc9111) when fetching Agent Cards
- When a cached Agent Card has expired, clients **SHOULD** use conditional requests (`If-None-Match` with the stored `ETag`, or `If-Modified-Since`) to avoid re-downloading unchanged cards
- When the server does not include caching headers, clients **MAY** apply an implementation-specific default cache duration
## 9. JSON-RPC Protocol Binding
The JSON-RPC protocol binding provides a simple, HTTP-based interface using JSON-RPC 2.0 for method calls and Server-Sent Events for streaming.
@ -2435,7 +2373,7 @@ JSON-RPC error responses use the standard [JSON-RPC 2.0 error object](https://ww
- **Error Code**: Mapped to `error.code` (numeric JSON-RPC error code)
- **Error Message**: Mapped to `error.message` (human-readable string)
- **Error Details**: Mapped to `error.data` (array of objects, each containing a `@type` key, using ProtoJSON `Any` representation)
- **Error Details**: Mapped to `error.data` (array containing `google.protobuf.Any` messages, using ProtoJSON representation)
**Standard JSON-RPC Error Codes:**
@ -2451,9 +2389,16 @@ JSON-RPC error responses use the standard [JSON-RPC 2.0 error object](https://ww
A2A-specific errors use codes in the range `-32001` to `-32099`. For the complete mapping of A2A error types to JSON-RPC error codes, see [Section 5.4 (Error Code Mappings)](#54-error-code-mappings).
**Error Detail Objects:**
**A2A Error Representation:**
Each object in the `data` array **MUST** include a `@type` key that identifies the object's type. Implementations **SHOULD** use well-known types such as `google.rpc.ErrorInfo` to refine error reporting, or `google.rpc.BadRequest` to attach structured data to validation errors. Additional error context **MAY** be included as further objects in the `data` array.
For A2A-specific errors, implementations **MUST** include a `google.rpc.ErrorInfo` message in the `data` array with:
- `@type`: Set to `"type.googleapis.com/google.rpc.ErrorInfo"`
- `reason`: The A2A error type in UPPER_SNAKE_CASE without the "Error" suffix (e.g., `TASK_NOT_FOUND`)
- `domain`: Set to `"a2a-protocol.org"`
- `metadata`: Optional map of additional error context
Additional error context **MAY** be included in the `data` array.
**Error Response Structure:**
@ -2462,19 +2407,11 @@ Each object in the `data` array **MUST** include a `@type` key that identifies t
"jsonrpc": "2.0",
"id": 1,
"error": {
"code": -32602,
"message": "Invalid parameters",
"data": [
{
"@type": "type.googleapis.com/google.rpc.BadRequest",
"fieldViolations": [
{
"field": "message.parts",
"description": "At least one part is required"
}
]
}
]
"code": -32601,
"message": "Method not found",
"data": {
"method": "invalid/method"
}
}
}
```
@ -2675,6 +2612,10 @@ Resource wrapper for push notification configurations. This is a gRPC-specific t
{{ proto_to_table("TaskPushNotificationConfig") }}
**Fields:**
{{ proto_to_table("TaskPushNotificationConfig") }}
### 10.6. Error Handling
gRPC error responses use the standard [gRPC status](https://grpc.io/docs/guides/error/) structure with [google.rpc.Status](https://github.com/googleapis/googleapis/blob/master/google/rpc/status.proto), which maps to the generic A2A error model defined in [Section 3.3.2](#332-error-handling) as follows:
@ -2748,7 +2689,7 @@ The HTTP+JSON protocol binding provides a RESTful interface using standard HTTP
### 11.1. Protocol Requirements
- **Protocol:** HTTP(S) with JSON payloads
- **Content-Type:** application/a2a+json **SHOULD** be used for requests and responses
- **Content-Type:** `application/json` for requests and responses
- **Methods:** Standard HTTP verbs (GET, POST, PUT, DELETE)
- **URL Patterns:** RESTful resource-based URLs
- **Streaming:** Server-Sent Events for real-time updates
@ -2768,7 +2709,7 @@ A2A service parameters defined in [Section 3.2.6](#326-service-parameters) **MUS
```http
POST /message:send HTTP/1.1
Host: agent.example.com
Content-Type: application/a2a+json
Content-Type: application/json
Authorization: Bearer token
A2A-Version: 0.3
A2A-Extensions: https://example.com/extensions/geolocation/v1,https://standards.org/extensions/citations/v1
@ -2814,7 +2755,7 @@ All requests and responses use JSON objects structurally equivalent to the Proto
```http
POST /message:send
Content-Type: application/a2a+json
Content-Type: application/json
{
"message": {
@ -2834,7 +2775,7 @@ Content-Type: application/a2a+json
```http
HTTP/1.1 200 OK
Content-Type: application/a2a+json
Content-Type: application/json
{
"task": {
@ -2896,49 +2837,43 @@ All query parameter values **MUST** be properly URL-encoded per [RFC 3986](https
### 11.6. Error Handling
HTTP error responses use the [google.rpc.Status](https://github.com/googleapis/googleapis/blob/master/google/rpc/status.proto) JSON representation, which maps to the generic A2A error model defined in [Section 3.3.2](#332-error-handling) as follows:
HTTP error responses use the ProtoJSON representation of the [`google.rpc.Status`](https://github.com/googleapis/googleapis/blob/master/google/rpc/status.proto) structure, which maps to the generic A2A error model defined in [Section 3.3.2](#332-error-handling) as follows:
- **Error Code**: Mapped to the HTTP status code and the `error.code` field
- **Error Message**: Mapped to the `error.message` field (human-readable string)
- **Error Details**: Mapped to the `error.details` array (array of objects, each containing a `@type` key, using ProtoJSON `Any` representation)
**Error Detail Objects:**
Each object in the `details` array **MUST** include a `@type` key that identifies the object's type. Implementations **SHOULD** use well-known types such as `google.rpc.BadRequest` to attach structured data to validation errors. Additional error context **MAY** be included as further objects in the `details` array.
- **Error Code**: Mapped to the HTTP status code and the `code` field (gRPC status code integer)
- **Error Message**: Mapped to the `message` field (human-readable string)
- **Error Details**: Mapped to the `details` array (containing `google.protobuf.Any` messages)
**A2A Error Representation:**
Since multiple A2A error types may map to the same HTTP status code (e.g., `TaskNotCancelableError` and `PushNotificationNotSupportedError` both map to `400 Bad Request`), implementations **MUST** include a `google.rpc.ErrorInfo` object in the `details` array for A2A-specific errors with:
For A2A-specific errors, implementations **MUST** include a `google.rpc.ErrorInfo` message in the `details` array with:
- `@type`: Set to `"type.googleapis.com/google.rpc.ErrorInfo"`
- `reason`: The A2A error type in UPPER_SNAKE_CASE without the "Error" suffix (e.g., `TASK_NOT_FOUND`, `TASK_NOT_CANCELABLE`)
- `reason`: The A2A error type in UPPER_SNAKE_CASE without the "Error" suffix (e.g., `TASK_NOT_FOUND`)
- `domain`: Set to `"a2a-protocol.org"`
- `metadata`: Optional map of additional error context
For the complete mapping of A2A error types to HTTP status codes, see [Section 5.4 (Error Code Mappings)](#54-error-code-mappings).
For the complete mapping of A2A error types to HTTP and gRPC status codes, see [Section 5.4 (Error Code Mappings)](#54-error-code-mappings). Additional error context **MAY** be included in the `details` array of the Status object.
**Error Response Example:**
```http
HTTP/1.1 404 Not Found
Content-Type: application/a2a+json
Content-Type: application/json
{
"error": {
"code": 404,
"status": "NOT_FOUND",
"message": "The specified task ID does not exist or is not accessible",
"details": [
{
"@type": "type.googleapis.com/google.rpc.ErrorInfo",
"reason": "TASK_NOT_FOUND",
"domain": "a2a-protocol.org",
"metadata": {
"taskId": "task-123",
"timestamp": "2025-11-09T10:30:00.000Z"
}
"code": 5,
"message": "The specified task ID does not exist or is not accessible",
"details": [
{
"@type": "type.googleapis.com/google.rpc.ErrorInfo",
"reason": "TASK_NOT_FOUND",
"domain": "a2a-protocol.org",
"metadata": {
"taskId": "task-123",
"timestamp": "2025-11-09T10:30:00.000Z"
}
]
}
}
]
}
```
@ -2952,7 +2887,7 @@ REST streaming uses Server-Sent Events with the `data` field containing JSON ser
```http
POST /message:stream
Content-Type: application/a2a+json
Content-Type: application/json
{ /* SendMessageRequest object */ }
```
@ -3042,8 +2977,9 @@ Custom bindings **MUST**:
Custom bindings **MUST** be declared in the Agent Card:
1. **Transport Identifier**: Use a URI to identify the binding (see [Section 5.8](#58-custom-binding-identification))
1. **Transport Identifier**: Use a clear, descriptive transport name
2. **Endpoint URL**: Provide the full URL where the binding is available
3. **Documentation Link**: Include a URL to the complete binding specification
**Example:**
@ -3052,7 +2988,7 @@ Custom bindings **MUST** be declared in the Agent Card:
"supportedInterfaces": [
{
"url": "wss://agent.example.com/a2a/websocket",
"protocolBinding": "https://example.com/bindings/websocket/v1"
"protocolBinding": "WEBSOCKET"
}
]
}

View File

@ -91,22 +91,6 @@ To mitigate risks, the following protection mechanisms should be considered:
Any Agent Card containing sensitive data must be protected with authentication and authorization mechanisms. The A2A specification strongly recommends the use of out-of-band dynamic credentials rather than embedding static secrets within the Agent Card.
## Caching Considerations
Agent Cards describe an agent's capabilities and typically change infrequently — for example, when skills are added or authentication requirements are updated. Applying standard HTTP caching practices to Agent Card endpoints reduces unnecessary network requests while ensuring clients eventually receive updated information.
### Server Guidance
Servers hosting Agent Card endpoints should include HTTP caching headers in their responses. The `Cache-Control` header with an appropriate `max-age` directive allows clients and intermediaries to cache the card for a specified duration. Including an `ETag` header — derived from the card's `version` field or a content hash — enables clients to make conditional requests and avoid re-downloading unchanged cards.
### Client Guidance
Clients fetching Agent Cards should honor standard HTTP caching semantics. When a cached card expires, clients should use conditional requests (for example, `If-None-Match` with the stored `ETag` or `If-Modified-Since`) rather than unconditionally re-fetching the full card. When the server does not provide caching headers, clients may apply a reasonable default cache duration.
For Extended Agent Cards, clients should also follow the session-scoped caching guidance described in the [specification](../specification.md#133-extended-agent-card-access-control).
For normative requirements, see [Section 8.6](../specification.md#86-caching) of the specification.
## Future Considerations
The A2A community explores standardizing registry interactions or advanced discovery protocols.

View File

@ -1,135 +0,0 @@
# Custom Protocol Bindings
The A2A protocol ships with three standard bindings (JSON-RPC, gRPC, and
HTTP+JSON/REST) that cover the majority of deployment scenarios. Custom protocol
bindings let implementers expose A2A operations over additional transport
mechanisms not covered by the standard set.
Custom protocol bindings are a complementary but distinct concept to
[Extensions](extensions.md). Extensions modify the *behavior* of protocol
interactions by adding new data, methods, or state transitions on top of an
existing transport. Custom protocol bindings change the *transport layer*
itself—for example, exposing A2A over WebSockets for low-latency bidirectional
communication, or over MQTT for IoT environments with constrained connectivity.
## Declaration in the Agent Card
Custom protocol bindings are declared in the Agent Card's `supportedInterfaces`
list. Each entry identifies the transport by URI, the endpoint URL, and the A2A
protocol version it implements. The `protocolBinding` field should be a URI that uniquely identifies the
binding (see [Section 5.8 of the specification](../specification.md#58-custom-binding-identification)
for the normative requirement and versioning guidance).
```json
{
"supportedInterfaces": [
{
"url": "wss://agent.example.com/a2a/websocket",
"protocolBinding": "https://a2a-protocol.org/bindings/websocket",
"protocolVersion": "1.0"
}
]
}
```
Agents that support multiple bindings list all of them. Clients parse
`supportedInterfaces` in order and select the first transport they support, so
entries should be listed in preference order.
## Requirements
Custom protocol bindings must comply with all requirements in the
[Protocol Binding Requirements and Interoperability](../specification.md#5-protocol-binding-requirements-and-interoperability)
section of the specification. In particular:
- **All core operations must be supported.** The binding must expose every
operation defined in the abstract operations layer (send message, get task,
cancel task, streaming, push notifications, etc.).
- **The data model must be preserved.** All data structures must be
functionally equivalent to the canonical Protocol Buffer definitions. JSON
serializations must use camelCase field names, and timestamps must be
ISO 8601 strings in UTC.
- **Behavior must be consistent.** Semantically equivalent requests must
produce semantically equivalent results regardless of which binding is used.
## Key Areas to Specify
A custom binding specification must address each of the following areas.
### Data Type Mappings
Document how each Protocol Buffer type is represented in the custom transport,
including:
- Binary data encoding (e.g., base64 for text-based transports)
- Enum representation (strings, integers, or named constants)
- Timestamp format (ISO 8601 strings in UTC per the core convention)
### Service Parameters
Service parameters are key-value pairs used to carry horizontally applicable
context such as tracing identifiers or authentication hints. The binding
specification must state:
- The mechanism used to carry service parameters (e.g., custom message headers,
a top-level metadata field)
- Any character encoding or size constraints on keys and values
- Any names reserved by the binding itself
For transports that lack native header support, a common pattern is to embed
service parameters as a JSON object in a dedicated metadata field, for example
`a2a-service-parameters`.
### Error Mapping
The binding must map all A2A error types to transport-native error
representations while preserving their semantic meaning. Provide a mapping
table equivalent to the one in the specification's
[Error Code Mappings](../specification.md#54-error-code-mappings) section, showing
how each A2A error type (e.g., `TaskNotFoundError`, `UnsupportedOperationError`) is expressed in the custom binding's native error format.
### Streaming
If the transport supports streaming, document:
- The stream mechanism (e.g., WebSocket frames, chunked encoding, long polling)
- Ordering guarantees (events must be delivered in the order they were
generated)
- Reconnection behavior when a connection is interrupted
- How stream completion or termination is signaled to the client
If the transport does not support streaming, state this limitation clearly in
the Agent Card so clients can fall back to polling.
### Authentication and Authorization
Document how authentication credentials declared in the Agent Card are
transmitted using the custom transport. Define how authentication challenges are
communicated to clients and ensure the custom binding does not inadvertently
bypass the agent's primary security controls.
## Interoperability Testing
Before publishing a custom binding, verify that:
- All operations behave identically to the standard bindings for the same
logical requests
- Error conditions, large payloads, and long-running tasks are handled correctly
- Any intentional deviations from standard binding behavior are clearly
documented
- Sample requests and responses are included in the specification to help
implementers
## Governance
The A2A organization uses a formal governance framework for how custom protocol
bindings are proposed, developed, promoted, and maintained. Official bindings
use the `https://a2a-protocol.org/bindings/` URI prefix and are hosted under
the `a2aproject` organization with the `cpb-` repository prefix (experimental
bindings use `experimental-cpb-`). A2A SDKs SHOULD implement official custom
protocol bindings.
For the full governance process—including tiers, lifecycle, SDK support, and
legal requirements—see the
[Extension and Protocol Binding Governance](extension-and-binding-governance.md)
page.

View File

@ -1,189 +0,0 @@
# Extension and Protocol Binding Governance
The A2A organization uses a unified governance framework for both
[Extensions](extensions.md) and [Custom Protocol Bindings](custom-protocol-bindings.md).
This document defines the formal process for proposing, developing, promoting,
and maintaining these artifacts within the A2A organization.
Anyone may develop and publish extensions or custom protocol bindings
independently. The tiers and lifecycle described here apply specifically to
those hosted under the `a2aproject` GitHub organization.
## Tiers
Both extensions and custom protocol bindings use a two-tier system within the
`a2aproject` organization. Repository naming and URI prefixes differ by type:
| | Extensions | Custom Protocol Bindings |
| :----------------------- | :---------------------------------------------- | :--------------------------------------------- |
| Official repo prefix | `ext-{name}` | `cpb-{name}` |
| Experimental repo prefix | `experimental-ext-{name}` | `experimental-cpb-{name}` |
| Official URI prefix | `https://a2a-protocol.org/extensions/` | `https://a2a-protocol.org/bindings/` |
### Official
Official artifacts are developed and maintained under the `a2aproject` GitHub
organization, officially recommended by the TSC. Each repository has designated
maintainers identified in `MAINTAINERS.md`.
**Requirements:**
- Specifications MUST use the same language as the core specification
([RFC 2119](https://tools.ietf.org/html/rfc2119))
- MUST be licensed under Apache 2.0
- MUST have at least one reference implementation
- SHOULD have associated documentation on the A2A website
### Experimental
Experimental artifacts provide an incubation pathway for community contributors
to prototype and collaborate on ideas before graduation to official status.
**Creation Requirements:**
- An experimental repository can ONLY be created with sponsorship from an A2A
Maintainer
- The sponsoring Maintainer is responsible for initial oversight of the
experimental artifact
- Experimental repositories MUST clearly indicate their experimental/non-official
status in the README
- Any published packages MUST use naming that clearly indicates experimental
status
- The TSC retains oversight, including the ability to archive or remove
experimental repositories
## Lifecycle
Extensions and custom protocol bindings progress through the following phases.
### Proposal Phase
Any community member may propose an extension or custom protocol binding:
1. **Open an Issue**: Create an issue in the main `a2aproject/A2A` repository
describing:
- An abstract describing the extension's purpose or the binding's transport
and use case
- Motivation explaining why this cannot be achieved with the core protocol
or existing standard bindings
- An initial technical approach or specification draft
2. **Community Discussion**: The proposal is open for community feedback and
refinement
### Maintainer Sponsorship
For a proposal to proceed to experimental status:
1. **Secure a Sponsor**: An A2A Maintainer must agree to sponsor the proposal
2. **Repository Creation**: The sponsoring Maintainer creates the
`experimental-ext-*` or `experimental-cpb-*` repository under `a2aproject`
3. **Oversight**: The sponsoring Maintainer provides initial oversight and
ensures alignment with A2A design principles
### Experimental Development
While in experimental status:
- Contributors iterate on the specification and reference implementations
- The experimental artifact MAY be used by early adopters with the
understanding that breaking changes are expected
- Community feedback is gathered and incorporated
- The experimental repository MUST clearly indicate its non-official status
### Graduation to Official Status
To graduate an experimental extension or binding to official status:
1. **Maturity Requirements**:
- At least one production-quality reference implementation
- Documentation meeting A2A standards
- Evidence of community adoption or interest
- Clear maintainer commitment for ongoing maintenance
2. **Graduation Proposal**: Open an issue in `a2aproject/A2A` with:
- Reference to the experimental repository and its implementations
- Summary of community feedback and adoption
- Proposed maintainers for the official artifact
3. **TSC Vote**:
- The proposal is added to the TSC meeting agenda
- **Quorum Requirement**: At least 50% of TSC voting members must be
present
- **Approval**: Requires majority vote of those in attendance (per A2A
governance)
- The TSC may request revisions before a final vote
4. **Acceptance**:
- (Extensions) The repository is renamed from `experimental-ext-*` to
`ext-*`; documentation is added to the A2A website's extensions page
- (Custom Protocol Bindings) The repository is renamed from
`experimental-cpb-*` to `cpb-*`; documentation is added to the A2A
website's custom protocol bindings page
### Official Iteration
Once official, extensions and bindings may be iterated on:
- Repository maintainers are responsible for day-to-day governance
- Changes SHOULD be coordinated via the relevant working group if one exists
- Breaking changes require a new identifier
- Breaking changes require TSC review
- Maintainers SHOULD coordinate with SDK maintainers for implementation updates
### Promotion to Core Protocol
Some extensions may eventually transition to core protocol features, and some
custom protocol bindings may transition to core bindings. This is governed
through the existing A2A specification enhancement process:
- A proposal is submitted following the standard specification change process
- The proposal references the official extension or binding and its adoption
- TSC vote with standard quorum and majority requirements applies
- Not all extensions or bindings are suitable for core inclusion; many will
remain as extensions or custom bindings indefinitely
## SDK Support
SDK support requirements differ between extensions and official custom protocol
bindings, reflecting their different roles in the protocol ecosystem.
**Extensions**: A2A SDKs MAY implement extensions. Where implemented:
- Extensions MUST be disabled by default and require explicit opt-in
- SDK documentation SHOULD list supported extensions
- SDK maintainers have full autonomy over extension support decisions
- Extension support is not required for protocol conformance
**Official Custom Protocol Bindings**: A2A SDKs SHOULD implement official
custom protocol bindings. Where implemented:
- Custom protocol bindings MUST be disabled by default and require explicit
opt-in
- SDK documentation SHOULD list supported custom protocol bindings
- SDK maintainers have full autonomy over binding support decisions
- Custom protocol binding support is not required for protocol conformance
## Legal Requirements
### Licensing
Official extensions and custom protocol bindings MUST be available under the
Apache 2.0 license, consistent with the core A2A project.
### Contributor License Grant
By submitting a contribution to an official A2A extension or custom protocol
binding repository, contributors represent that:
1. They have the legal authority to grant the rights
2. The contribution is original work or they have sufficient rights to submit it
3. They grant to the Linux Foundation and recipients a perpetual, worldwide,
non-exclusive, royalty-free license to use, reproduce, modify, and
distribute the contribution
### Antitrust
Extension and custom protocol binding developers acknowledge that:
- They may compete with other participants
- They have no obligation to implement any extension or binding
- They are free to develop competing extensions or bindings
- Status as an official extension or binding does not create an exclusive
relationship

View File

@ -51,19 +51,6 @@ However, some foreseeable applications include:
| [Traceability Extension](https://github.com/a2aproject/a2a-samples/tree/main/samples/python/extensions/traceability) | Explore the Python implementation and basic usage of the Traceability Extension (v1). |
| [Agent Gateway Protocol (AGP) Extension](https://github.com/a2aproject/a2a-samples/tree/main/extensions/agp) | A Core Protocol Layer or Routing Extension that introduces Autonomous Squads (ASq) and routes Intent payloads based on declared Capabilities, enhancing scalability (v1). |
## Extension Governance
The A2A organization uses a formal governance framework for how extensions are
proposed, developed, promoted, and maintained. Official extensions use the
`https://a2a-protocol.org/extensions/` URI prefix and are hosted under the
`a2aproject` organization with the `ext-` repository prefix (experimental
extensions use `experimental-ext-`).
For the full governance process—including tiers, lifecycle, SDK support, and
legal requirements—see the
[Extension and Protocol Binding Governance](extension-and-binding-governance.md)
page.
## Limitations
There are some changes to the protocol that extensions don't allow, primarily
@ -239,10 +226,9 @@ versioning, and distributing extension implementations.
- **Permanent Identifiers**: Authors are encouraged to use a permanent
identifier service, such as `w3id.org`, for their extension URIs to
prevent broken links.
- **Community Registry**: The A2A [Extension Governance](#extension-governance)
framework defines a tiered system for official and experimental
extensions hosted under the `a2aproject` organization, including a
lifecycle for proposing and promoting extensions.
- **Community Registry (Future)**: The A2A community might establish a
central registry for discovering and browsing available extensions in
the future.
- **Packaging and Reusability (A2A SDKs and Libraries)**:
To promote adoption, extension logic should be packaged into reusable
libraries that can be integrated into existing A2A client and

View File

@ -1,4 +1,4 @@
# 2. Set Up Your Environment
# 2. Setup Your Environment
## Prerequisites
@ -38,7 +38,7 @@ We recommend using a virtual environment for Python projects. The A2A Python SDK
.venv\Scripts\activate
```
2. **Install the A2A SDK and its required Python dependencies:**
2. **Install needed Python dependencies along with the A2A SDK and its dependencies:**
```bash
pip install -r samples/python/requirements.txt

View File

@ -8,15 +8,14 @@ We'll use the `helloworld` example located in [`a2a-samples/samples/python/agent
An **Agent Skill** describes a specific capability or function the agent can perform. It's a building block that tells clients what kinds of tasks the agent is good for.
Attributes of an `AgentSkill` (defined in `a2a.types`):
Key attributes of an `AgentSkill` (defined in `a2a.types`):
- `id`: A unique identifier for the skill.
- `name`: A human-readable name.
- `description`: A more detailed explanation of what the skill does.
- `tags`: Keywords for categorization and discovery.
- `examples`: Sample prompts or use cases.
- `input_modes` / `output_modes`: Supported Media Types for input and output (e.g., "text/plain", "application/json").
- `security_requirements`: Security schemes necessary for this skill.
- `inputModes` / `outputModes`: Supported Media Types for input and output (e.g., "text/plain", "application/json").
In `__main__.py`, you can see how a skill for the Helloworld agent is defined:
@ -33,9 +32,9 @@ The **Agent Card** is a JSON document that an A2A Server makes available, typica
Key attributes of an `AgentCard` (defined in `a2a.types`):
- `name`, `description`, `version`: Basic identity information.
- `supported_interfaces`: Ordered list of endpoints and protocols where the A2A service can be reached.
- `capabilities`: Supported A2A features like `streaming` or `extended_agent_card`.
- `default_input_modes` / `default_output_modes`: Default Media Types for the agent.
- `url`: The endpoint where the A2A service can be reached.
- `capabilities`: Specifies supported A2A features like `streaming` or `pushNotifications`.
- `defaultInputModes` / `defaultOutputModes`: Default Media Types for the agent.
- `skills`: A list of `AgentSkill` objects that the agent offers.
The `helloworld` example defines its Agent Card like this:
@ -44,4 +43,6 @@ The `helloworld` example defines its Agent Card like this:
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/__main__.py:AgentCard"
```
This card tells us the agent is named "Hello World Agent", can be run at `http://127.0.0.1:9999/`, supports text interactions, and has the `hello_world` skill.
This card tells us the agent is named "Hello World Agent", runs at `http://localhost:9999/`, supports text interactions, and has the `hello_world` skill. It also indicates public authentication, meaning no specific credentials are required.
Understanding the Agent Card is crucial because it's how a client discovers an agent and learns how to interact with it.

View File

@ -22,7 +22,7 @@ Let's look at `agent_executor.py`. It defines `HelloWorldAgentExecutor`.
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/agent_executor.py:HelloWorldAgent"
```
It has a simple `invoke` method that returns the string "Hello, World!".
It has a simple `invoke` method that returns the string "Hello World".
2. **The Executor (`HelloWorldAgentExecutor`)**:
This class implements the `AgentExecutor` interface.
@ -41,16 +41,17 @@ Let's look at `agent_executor.py`. It defines `HelloWorldAgentExecutor`.
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/agent_executor.py:HelloWorldAgentExecutor_execute"
```
When a `Send Message` or `Send Streaming Message` request comes in (both are handled by `execute` in this simplified executor), the following steps occur:
When a `message/send` or `message/stream` request comes in (both are handled by `execute` in this simplified executor):
**Step 1.** The `A2A instance` (server) retrieves the current task from the context. If there is no task in context, then it creates a new task and adds it to the `EventQueue`.
1. It calls `self.agent.invoke()` to get the "Hello World" string.
2. It creates an A2A `Message` object using the `new_agent_text_message` utility function.
3. It enqueues this message onto the `event_queue`. The underlying `DefaultRequestHandler` will then process this queue to send the response(s) to the client. For a single message like this, it will result in a single response for `message/send` or a single event for `message/stream` before the stream closes.
**Step 2.** It enqueues a `TaskStatusUpdateEvent` with a state of `TASK_STATE_WORKING` to indicate the agent has begun processing.
- **`cancel`**:
The Hello World example's `cancel` method simply raises an exception, indicating that cancellation is not supported for this basic agent.
**Step 3.** It calls `self.agent.invoke()` to execute the actual business logic (which simply returns "Hello, World!").
**Step 4.** It enqueues a `TaskArtifactUpdateEvent` containing the result text from the agent.
**Step 5.** Finally, it enqueues a `TaskStatusUpdateEvent` with a state of `TASK_STATE_COMPLETED` to conclude the task.
```python { .no-copy }
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/agent_executor.py:HelloWorldAgentExecutor_cancel"
```
The `AgentExecutor` acts as the bridge between the A2A protocol (managed by the request handler and server application) and your agent's specific logic. It receives context about the request and uses an event queue to communicate results or updates back.

View File

@ -2,9 +2,7 @@
Now that we have an Agent Card and an Agent Executor, we can set up and start the A2A server.
To set up an A2A server, the Python SDK provides a route factory and helper functions (`create_agent_card_routes`, `create_jsonrpc_routes`, `create_rest_routes`). Use the route factory to create routes for the A2A server's services. These routes can be attached natively to popular frameworks like [Starlette](https://www.starlette.io/) and [FastAPI](https://fastapi.tiangolo.com/), which give you better control over authentication, logging, and other features.
In this tutorial, we will use Starlette with [Uvicorn](https://www.uvicorn.org/).
The A2A Python SDK provides an `A2AStarletteApplication` class that simplifies running an A2A-compliant HTTP server. It uses [Starlette](https://www.starlette.io/) for the web framework and is typically run with an ASGI server like [Uvicorn](https://www.uvicorn.org/).
## Server Setup in Helloworld
@ -18,22 +16,21 @@ Let's break this down:
1. **`DefaultRequestHandler`**:
- The SDK provides `DefaultRequestHandler`. This handler takes your `AgentExecutor` implementation (`HelloWorldAgentExecutor`), a `TaskStore` (`InMemoryTaskStore`), and the public and extended `AgentCard` objects.
- The SDK provides `DefaultRequestHandler`. This handler takes your `AgentExecutor` implementation (here, `HelloWorldAgentExecutor`) and a `TaskStore` (here, `InMemoryTaskStore`).
- It routes incoming A2A RPC calls to the appropriate methods on your executor (like `execute` or `cancel`).
- The `TaskStore` is used by the `DefaultRequestHandler` to manage the lifecycle of tasks, especially for stateful interactions, streaming, and resubscription. Even if your agent executor is simple, the handler needs a task store.
- `agent_card` is passed to the handler so it can verify the agent's declared capabilities when processing incoming requests. For example, it checks whether streaming or push notifications are supported before handling those request types.
- `extended_agent_card` is passed so the handler can serve it via the `GetExtendedAgentCard` RPC method to authenticated clients.
2. **`create_agent_card_routes` and `create_jsonrpc_routes`**:
2. **`A2AStarletteApplication`**:
- `create_agent_card_routes(public_agent_card)` returns Starlette routes that expose the Agent Card at the `/.well-known/agent-card.json` endpoint for public discovery.
- `create_jsonrpc_routes(request_handler, '/')` returns Starlette routes that handle all incoming A2A JSON-RPC method calls by delegating to the `request_handler`.
- These route lists are combined and passed to a standard `Starlette` application.
- The `A2AStarletteApplication` class is instantiated with the `agent_card` and the `request_handler` (referred to as `http_handler` in its constructor).
- The `agent_card` is crucial because the server will expose it at the `/.well-known/agent-card.json` endpoint (by default).
- The `request_handler` is responsible for processing all incoming A2A method calls by interacting with your `AgentExecutor`.
3. **`uvicorn.run(app, ...)`**:
- The constructed `Starlette` app is run using `uvicorn.run()`, making your agent accessible over HTTP.
- `host='127.0.0.1'` makes the server accessible only from your local machine.
- `port=9999` specifies the port to listen on. This matches the endpoints defined in the `AgentCard`'s `supported_interfaces`.
3. **`uvicorn.run(server_app_builder.build(), ...)`**:
- The `A2AStarletteApplication` has a `build()` method that constructs the actual Starlette application.
- This application is then run using `uvicorn.run()`, making your agent accessible over HTTP.
- `host='0.0.0.0'` makes the server accessible on all network interfaces on your machine.
- `port=9999` specifies the port to listen on. This matches the `url` in the `AgentCard`.
## Running the Helloworld Server
@ -52,7 +49,7 @@ You should see output similar to this, indicating the server is running:
INFO: Started server process [xxxxx]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:9999 (Press CTRL+C to quit)
INFO: Uvicorn running on http://0.0.0.0:9999 (Press CTRL+C to quit)
```
Your A2A Helloworld agent is now live and listening for requests! In the next step, we'll interact with it.

View File

@ -1,18 +1,18 @@
# 6. Interacting with the Server
With the Helloworld A2A server running, let's send some requests to it.
With the Helloworld A2A server running, let's send some requests to it. The SDK includes a client (`A2AClient`) that simplifies these interactions.
## The Helloworld Test Client
The `test_client.py` script demonstrates how to:
1. Fetch the Agent Card from the server.
2. Create a client using `create_client`.
3. Send both `Send Message` and `Send Streaming Message` requests.
2. Create an `A2AClient` instance.
3. Send both non-streaming (`message/send`) and streaming (`message/stream`) requests.
Open a **new terminal window**, activate your virtual environment, and navigate to the `a2a-samples` directory.
Activate the virtual environment (be sure to do this in the same directory where you created it):
Activate virtual environment (Be sure to do this in the same directory where you created the virtual environment):
=== "Mac/Linux"
@ -37,201 +37,59 @@ python samples/python/agents/helloworld/test_client.py
Let's look at key parts of `test_client.py`:
1. **Fetching the Agent Card**:
1. **Fetching the Agent Card & Initializing the Client**:
```python { .no-copy }
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/test_client.py:A2ACardResolver"
```
The `A2ACardResolver` class is a convenience. When `get_agent_card()` is called, it fetches the `AgentCard` from the server's `/.well-known/agent-card.json` endpoint (based on the provided base URL), which is then used to initialize the client.
The `A2ACardResolver` class is a convenience. It first fetches the `AgentCard` from the server's `/.well-known/agent-card.json` endpoint (based on the provided base URL) and then initializes the client with it.
2. **Initializing the Client & Sending a Non-Streaming Message**:
2. **Sending a Non-Streaming Message (`send_message`)**:
```python { .no-copy }
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/test_client.py:message_send"
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/test_client.py:send_message"
```
- The `create_client` function creates a `Client` based on the information provided by the `AgentCard` and a `ClientConfig`.
- We construct a `Message` using the `new_text_message` helper (passing `role=Role.ROLE_USER`), then wrap it in a `SendMessageRequest`.
- The client's `send_message` method returns an async iterator that yields a single final `Task` or `Message` response from the agent. In this example, it is a `Task`.
- The `send_message_payload` constructs the data for `MessageSendParams`.
- This is wrapped in a `SendMessageRequest`.
- It includes a `message` object with the `role` set to "user" and the content in `parts`.
- The Helloworld agent's `execute` method will enqueue a single "Hello World" message. The `DefaultRequestHandler` will retrieve this and send it as the response.
- The `response` will be a `SendMessageResponse` object, which contains either a `SendMessageSuccessResponse` (with the agent's `Message` as the result) or a `JSONRPCErrorResponse`.
3. **Initializing the Client & Sending a Streaming Message**:
3. **Handling Task IDs (Illustrative Note for Helloworld)**:
The Helloworld client (`test_client.py`) doesn't attempt `get_task` or `cancel_task` directly because the simple Helloworld agent's `execute` method, when called via `message/send`, results in the `DefaultRequestHandler` returning a direct `Message` response rather than a `Task` object. More complex agents that explicitly manage tasks (like the LangGraph example) would return a `Task` object from `message/send`, and its `id` could then be used for `get_task` or `cancel_task`.
4. **Sending a Streaming Message (`send_message_streaming`)**:
```python { .no-copy }
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/test_client.py:message_stream"
--8<-- "https://raw.githubusercontent.com/a2aproject/a2a-samples/refs/heads/main/samples/python/agents/helloworld/test_client.py:send_message_streaming"
```
- A separate streaming client is created via `create_client` with `streaming=True` in its `ClientConfig`.
- We again call `send_message`, which now streams events: each iteration of the loop prints a discrete chunk as it arrives over the network.
- Call `await streaming_client.close()` after the loop to release the underlying HTTP connection.
- This method calls the agent's `message/stream` endpoint. The `DefaultRequestHandler` will invoke the `HelloWorldAgentExecutor.execute` method.
- The `execute` method enqueues one "Hello World" message, and then the event queue is closed.
- The client will receive this single message as one `SendStreamingMessageResponse` event, and then the stream will terminate.
- The `stream_response` is an `AsyncGenerator`.
## Expected Output
When you run `test_client.py`, you'll see output for:
When you run `test_client.py`, you'll see JSON outputs for:
- The public agent card, displayed in a formatted summary.
- The non-streaming response: a single `task` in protobuf text format containing the completed status, the generated artifact with "Hello, World!", and the agent's intermediate status message in history.
- The streaming response: four chunks — the initial `task`, a `status_update` for WORKING, an `artifact_update` with the result, and a final `status_update` for COMPLETED.
- The extended agent card, displayed in a formatted summary (with an additional `super_hello_world` skill).
- The non-streaming response (a single "Hello World" message).
- The streaming response (a single "Hello World" message as one chunk, after which the stream ends).
The `id` fields in the output will vary with each run.
```console { .no-copy }
AgentCard
--- General ---
Name : Hello World Agent
Description : Just a hello world agent
Version : 0.0.1
--- Interfaces ---
[0] http://127.0.0.1:9999 (JSONRPC)
--- Capabilities ---
Streaming : True
Push notifications : False
Extended agent card : True
--- I/O Modes ---
Input : text/plain
Output : text/plain
--- Skills ---
----------------------------------------------------
ID : hello_world
Name : Returns hello world
Description : just returns hello world
Tags : hello world
Example : hi
Example : hello world
--- Non-Streaming Call ---
Non-streaming Client initialized.
Response:
// Non-streaming response
task {
id: "xxxxxxxx"
context_id: "yyyyyyyy"
status {
state: TASK_STATE_COMPLETED
}
artifacts {
artifact_id: "zzzzzzzz"
name: "result"
parts {
text: "Hello, World!"
}
}
history {
message_id: "vvvvvvvv"
context_id: "yyyyyyyy"
task_id: "xxxxxxxx"
role: ROLE_USER
parts {
text: "Say hello."
}
}
history {
message_id: "wwwwwwww"
role: ROLE_AGENT
parts {
text: "Processing request..."
}
}
}
// Streaming response
task {
id: "xxxxxxxx-s"
context_id: "yyyyyyyy-s"
status {
state: TASK_STATE_SUBMITTED
}
history {
message_id: "vvvvvvvv"
context_id: "yyyyyyyy-s"
task_id: "xxxxxxxx-s"
role: ROLE_USER
parts {
text: "Say hello."
}
}
}
Response chunk:
status_update {
task_id: "xxxxxxxx-s"
context_id: "yyyyyyyy-s"
status {
state: TASK_STATE_WORKING
message {
message_id: "zzzzzzzz-s"
role: ROLE_AGENT
parts {
text: "Processing request..."
}
}
}
}
Response chunk:
artifact_update {
task_id: "xxxxxxxx-s"
context_id: "yyyyyyyy-s"
artifact {
artifact_id: "wwwwwwww-s"
name: "result"
parts {
text: "Hello, World!"
}
}
}
Response chunk:
status_update {
task_id: "xxxxxxxx-s"
context_id: "yyyyyyyy-s"
status {
state: TASK_STATE_COMPLETED
}
}
AgentCard
--- General ---
Name : Hello World Agent - Extended Edition
Description : The full-featured hello world agent for authenticated users.
Version : 0.0.2
--- Interfaces ---
[0] http://127.0.0.1:9999 (JSONRPC)
--- Capabilities ---
Streaming : True
Push notifications : False
Extended agent card : True
--- I/O Modes ---
Input : text/plain
Output : text/plain
--- Skills ---
----------------------------------------------------
ID : hello_world
Name : Returns hello world
Description : just returns hello world
Tags : hello world
Example : hi
Example : hello world
----------------------------------------------------
ID : super_hello_world
Name : Returns a SUPER Hello World
Description : A more enthusiastic greeting, only for authenticated users.
Tags : hello world, super, extended
Example : super hi
Example : give me a super hello
{"jsonrpc":"2.0","id":"xxxxxxxx","result":{"message":{"role":"ROLE_AGENT","parts":[{"text":"Hello World"}],"messageId":"yyyyyyyy"}}}
// Streaming response (one chunk)
{"jsonrpc":"2.0","id":"zzzzzzzz","result":{"message":{"role":"ROLE_AGENT","parts":[{"text":"Hello World"}],"messageId":"wwwwwwww"}}}
```
_(Actual IDs like `xxxxxxxx`, `yyyyyyyy`, `zzzzzzzz`, `wwwwwwww`, and `vvvvvvvv` will be different UUIDs in each run.)_
_(Actual IDs like `xxxxxxxx`, `yyyyyyyy`, `zzzzzzzz`, `wwwwwwww` will be different UUIDs/request IDs)_
This confirms your server is correctly handling basic A2A interactions with the updated SDK structure.
This confirms your server is correctly handling basic A2A interactions with the updated SDK structure!
You can now shut down the server by pressing Ctrl+C in the terminal window where `__main__.py` is running.
Now you can shut down the server by typing Ctrl+C in the terminal window where `__main__.py` is running.

View File

@ -6,7 +6,7 @@ This example features a "Currency Agent" that uses the Gemini model via LangChai
## Setting up the LangGraph Example
1. Create a [Gemini API Key](https://ai.google.dev/gemini-api/docs/api-key) if you don't already have one.
1. Create a [Gemini API Key](https://ai.google.dev/gemini-api/docs/api-key), if you don't already have one.
2. **Environment Variable:**
@ -64,14 +64,14 @@ The `langgraph` example showcases several important A2A concepts:
```
- The `CurrencyAgentExecutor` (in `samples/langgraph/agent_executor.py`), when its `execute` method is called by the `DefaultRequestHandler`, interacts with the `RequestContext` which contains the current task (if any).
- For `Send Message`, the `DefaultRequestHandler` uses the `TaskStore` to persist and retrieve task state across interactions. The response to `Send Message` will be a full `Task` object if the agent's execution flow involves multiple steps or results in a persistent task.
- For `message/send`, the `DefaultRequestHandler` uses the `TaskStore` to persist and retrieve task state across interactions. The response to `message/send` will be a full `Task` object if the agent's execution flow involves multiple steps or results in a persistent task.
- The `test_client.py`'s `run_single_turn_test` demonstrates getting a `Task` object back and then querying it using `get_task`.
3. **Streaming with `TaskStatusUpdateEvent` and `TaskArtifactUpdateEvent`**:
- The `execute` method in `CurrencyAgentExecutor` is responsible for handling both non-streaming and streaming requests, orchestrated by the `DefaultRequestHandler`.
- As the LangGraph agent processes the request (which might involve calling tools like `get_exchange_rate`), the `CurrencyAgentExecutor` enqueues different types of events onto the `EventQueue`:
- `TaskStatusUpdateEvent`: For intermediate updates (e.g., "Looking up exchange rates...", "Processing the exchange rates...").
- `TaskStatusUpdateEvent`: For intermediate updates (e.g., "Looking up exchange rates...", "Processing the exchange rates..").
- `TaskArtifactUpdateEvent`: When the final answer is ready, it's enqueued as an artifact. The `lastChunk` flag is `True`.
- A final `TaskStatusUpdateEvent` with `state=TaskState.completed` is sent to signify the end of the task, closing the stream.
- The `test_client.py`'s `run_streaming_test` function will print these individual event chunks as they are received from the server.

View File

@ -8,8 +8,7 @@ The v1.0 release focuses on four major themes:
### 1. **Protocol Maturity and Standardization**
- Elevate a2a.proto from being a gRPC-specific implementation file to the universal, normative source of truth
- Leverage formal specification standards (RFC 8785, RFC 7515) and google.rpc.Status where possible
- Leverage formal specification standards (RFC 9457, RFC 8785, RFC 7515) where possible
- Stricter adherence to industry-standard patterns for REST, gRPC, and JSON-RPC bindings
- Enhanced versioning strategy with explicit backward compatibility rules
- Comprehensive error taxonomy with protocol-specific mappings
@ -92,11 +91,17 @@ The v1.0 release focuses on four major themes:
**v0.3.0 Behavior:**
- Operation unavailable.
- Operation named `tasks/list`
- Available in gRPC and REST only
- Basic pagination with page numbers
**v1.0 Changes:**
- **✅ NEW:** New operation **ListTasks** with filtering capabilities
- **✅ RENAMED:** Operation now **ListTasks**
- **✅ BREAKING:** Changed to cursor-based pagination for scalability
- Request: `cursor` (opaque token from previous response), `limit` (max results)
- Response: `tasks[]`, `nextCursor` (for next page)
- **✅ NEW:** Enhanced filtering capabilities with more explicit specifications
- **✅ CLARIFIED:** Task visibility scoped to authenticated caller
### Cancel Task (`tasks/cancel` → **CancelTask**)
@ -154,10 +159,9 @@ The v1.0 release focuses on four major themes:
**v1.0 Changes:**
- **✅ RENAMED:** Operations now **CreateTaskPushNotificationConfig**, **GetTaskPushNotificationConfig**, **ListTaskPushNotificationConfigs**, **DeleteTaskPushNotificationConfig**
- **✅ RENAMED:** Operations now **CreatePushNotificationConfig**, **GetPushNotificationConfig**, **ListPushNotificationConfigs**, **DeletePushNotificationConfig**
- **✅ NEW:** `createdAt` timestamp field added to PushNotificationConfig
- **✅ CLARIFIED:** Push notification payloads now use StreamResponse format
- **✅ BREAKING:** model changed for all methods, with TaskPushNotificationConfig flattened
### NEW: Multi-Tenancy Support
@ -168,10 +172,26 @@ The v1.0 release focuses on four major themes:
**v1.0 Changes:**
- **✅ NEW:** `tenant` field added to all request messages
- **✅ NEW:** `tenant` field added to all gRPC request messages
- **✅ NEW:** `tenant` field added to `AgentInterface` to specify default tenant
- **✅ CLARIFIED:** Tenant provided per-request, inherited from AgentInterface
- **✅ USE CASE:** Enables to serve multiple agents from a single endpoint
- **✅ CLARIFIED:** Tenant can be provided per-request or inherited from AgentInterface
- **✅ USE CASE:** Enables agents to serve multiple organizations from single endpoint
**Example:**
```protobuf
// Represents a request for the `SendMessage` method.
message SendMessageRequest {
// Optional tenant, provided as a path parameter.
string tenant = 4;
// The message to send to the agent.
Message message = 1 [(google.api.field_behavior) = REQUIRED];
// Configuration for the send request.
SendMessageConfiguration configuration = 2;
// A flexible key-value map for passing additional context or parameters.
google.protobuf.Struct metadata = 3;
}
```
### Protocol Simplifications
@ -200,13 +220,19 @@ The v1.0 release focuses on four major themes:
- **✅ BREAKING:** Removed `/v1` prefix from HTTP+JSON URL paths
- **✅ NEW:** Examples: `POST /message:send`, `GET /tasks/{id}`
- **✅ RATIONALE:** Version can be part of the base url if required by agent owner
- **✅ RATIONALE:** Version specified in `AgentInterface.protocolVersion` field instead
- **✅ BENEFIT:** Cleaner URLs, version management at interface level
---
## Structural Changes in Core Model Objects
### Task Object
**Removed Fields:**
- ⛔ `kind`: Discriminator field removed (was always "task")
### TaskStatus Object
**Modified Fields:**
@ -421,6 +447,20 @@ if ("text" in part) { ... } // v1.0
### AgentCapabilities Object
**Removed Fields:**
- ⛔ `stateTransitionHistory` - Removed as no API implementation existed for this feature
**Rationale:**
The `stateTransitionHistory` capability flag was misleading as v1.0 has no corresponding API to:
- Store status history in Task objects
- Retrieve status history via Get/List operations
- Query historical state transitions
This capability may be reintroduced in a future version with proper implementation.
**Modified Fields:**
- ✅ `extendedAgentCard`: Moved from top-level `supportsAuthenticatedExtendedCard` field
@ -556,11 +596,11 @@ v1.0 introduces several new formal dependencies on industry-standard specificati
### Added Specifications
#### ✅ google.rpc.Status / google.rpc.ErrorInfo
#### ✅ RFC 9457 - Problem Details for HTTP APIs
- **Purpose:** Standardized error response model with ProtoJSON representation
- **Usage:** Error responses for HTTP+JSON and JSON-RPC bindings
- **Impact:** Replaces RFC 9457 for HTTP errors. Enforces structured `ErrorInfo` with `reason` and `domain` for A2A-specific errors.
- **Purpose:** Standardized error response format
- **Usage:** HTTP+JSON binding error responses
- **Impact:** More consistent, machine-readable error handling in REST APIs
#### ✅ RFC 8785 - JSON Canonicalization Scheme (JCS)
@ -758,85 +798,16 @@ const message = { role: "ROLE_USER", parts: [...] };
- `file.mimeType` → `mediaType`
- Operation names (aliases provided during transition)
#### 7. Standardized Error Handling via google.rpc.Status (HIGH IMPACT)
HTTP+JSON error responses have been updated to use the ProtoJSON representation of `google.rpc.Status` instead of RFC 9457 (Problem Details). JSON-RPC and HTTP+JSON bindings now use `google.rpc.ErrorInfo` within the `data` / `details` array to provide A2A-specific error context.
**Changes:**
- **HTTP+JSON Content-Type:** Changed from `application/problem+json` to `application/json`.
- **Error Model:** Uses `google.rpc.Status` fields (`code`, `message`, `details`).
- **A2A Error Info:** MUST include a `google.rpc.ErrorInfo` object in `details` with `reason` (UPPER_SNAKE_CASE from A2A error types) and `domain: "a2a-protocol.org"`.
**JSON-RPC Example Migration:**
```json
// v0.3.0
"error": {
"code": -32001,
"message": "Task not found",
"data": { "taskId": "123" }
}
// v1.0
"error": {
"code": -32001,
"message": "Task not found",
"data": [
{
"@type": "type.googleapis.com/google.rpc.ErrorInfo",
"reason": "TASK_NOT_FOUND",
"domain": "a2a-protocol.org",
"metadata": { "taskId": "123" }
}
]
}
```
**HTTP+JSON Example Migration:**
```http
// v0.3.0 (Draft using RFC 9457)
HTTP/1.1 404 Not Found
Content-Type: application/problem+json
{
"type": "https://a2a-protocol.org/errors/task-not-found",
"title": "Task Not Found",
"status": 404,
"detail": "The specified task ID does not exist"
}
// v1.0
HTTP/1.1 404 Not Found
Content-Type: application/json
{
"error": {
"code": 404,
"status": "NOT_FOUND",
"message": "The specified task ID does not exist",
"details": [
{
"@type": "type.googleapis.com/google.rpc.ErrorInfo",
"reason": "TASK_NOT_FOUND",
"domain": "a2a-protocol.org"
}
]
}
}
```
### New Capabilities to Leverage
#### 1. Execution Mode Control
#### 1. Blocking Parameter Control
```typescript
// Wait for task completion (Default)
const result = await sendMessage(message, { returnImmediately: false });
// Wait for task completion
const result = await sendMessage(message, { blocking: true });
// Return immediately, poll later
const task = await sendMessage(message, { returnImmediately: true });
const task = await sendMessage(message, { blocking: false });
```
#### 2. Agent Card Signature Verification
@ -964,7 +935,7 @@ class A2AClient {
- Implement cursor-based pagination
- Update enum value handling (state field)
- Add return_immediately parameter support
- Add blocking parameter support
#### Medium (Within 3 Months)

View File

@ -20,7 +20,6 @@ extra:
# Navigation
nav:
- Home: index.md
- 🆕 Announcing Version 1.0: announcing-1.0.md
- Documentation:
- What is A2A?: topics/what-is-a2a.md
- Core Concepts: topics/key-concepts.md
@ -28,8 +27,6 @@ nav:
- Enterprise Features: topics/enterprise-ready.md
- Life of a Task: topics/life-of-a-task.md
- Extensions: topics/extensions.md
- Custom Protocol Bindings: topics/custom-protocol-bindings.md
- Extension & Binding Governance: topics/extension-and-binding-governance.md
- Streaming & Asynchronous Operations: topics/streaming-and-async.md
- A2A and MCP: topics/a2a-and-mcp.md
- Tutorials and Samples:
@ -43,10 +40,9 @@ nav:
- Interact with Server: tutorials/python/6-interact-with-server.md
- Streaming & Multiturn: tutorials/python/7-streaming-and-multiturn.md
- Next Steps: tutorials/python/8-next-steps.md
- DeepLearning.AI Course: https://goo.gle/dlai-a2a
- Specification:
- 🆕 Specification:
- Overview: specification.md
- What's New in v1.0: whats-new-v1.md
- 🆕 What's New in V1: whats-new-v1.md
- Protocol Definition: definitions.md
- SDK Reference:
- sdk/index.md

View File

@ -152,12 +152,10 @@ message SendMessageConfiguration {
// value of zero is a request to not include any messages. The server MUST NOT
// return more messages than the provided value, but MAY apply a lower limit.
optional int32 history_length = 3;
// If `true`, the operation returns immediately after creating the task,
// even if processing is still in progress.
// If `false` (default), the operation MUST wait until the task reaches a
// terminal (`COMPLETED`, `FAILED`, `CANCELED`, `REJECTED`) or interrupted
// (`INPUT_REQUIRED`, `AUTH_REQUIRED`) state before returning.
bool return_immediately = 4;
// If `true`, the operation MUST wait until the task reaches a terminal state
// (`COMPLETED`, `FAILED`, `CANCELED`, `REJECTED`) or an interrupted state
// (`INPUT_REQUIRED`, `AUTH_REQUIRED`) before returning. Default is `false`.
bool blocking = 4;
}
// `Task` is the core unit of action for A2A. It has a current status