Files
cleveragents-core/robot/helper_a2a_facade.py
T
hurui200320 87a7ce35d7
CI / benchmark-regression (push) Has been skipped
CI / helm (push) Successful in 38s
CI / lint (push) Successful in 1m14s
CI / build (push) Successful in 1m10s
CI / push-validation (push) Successful in 49s
CI / quality (push) Successful in 1m35s
CI / typecheck (push) Successful in 1m39s
CI / security (push) Successful in 1m45s
CI / integration_tests (push) Successful in 3m44s
CI / e2e_tests (push) Successful in 4m29s
CI / unit_tests (push) Successful in 5m10s
CI / docker (push) Successful in 1m55s
CI / coverage (push) Successful in 11m8s
CI / status-check (push) Successful in 3s
CI / benchmark-publish (push) Successful in 1h20m21s
CI / benchmark-publish (pull_request) Has been skipped
CI / benchmark-regression (pull_request) Failing after 1m35s
CI / docker (pull_request) Successful in 1m26s
CI / unit_tests (pull_request) Successful in 6m40s
CI / push-validation (pull_request) Successful in 1m24s
CI / quality (pull_request) Successful in 4m4s
CI / integration_tests (pull_request) Successful in 5m44s
CI / e2e_tests (pull_request) Failing after 6m5s
CI / helm (pull_request) Successful in 1m10s
CI / build (pull_request) Successful in 2m39s
CI / lint (pull_request) Successful in 2m58s
CI / typecheck (pull_request) Successful in 3m56s
CI / security (pull_request) Successful in 3m56s
CI / coverage (pull_request) Successful in 10m52s
CI / status-check (pull_request) Failing after 3s
feat(session): implement real LLM actor invocation in session tell
Replace the M3 stub in `agents session tell` with real orchestrator actor
invocation via `SessionWorkflow.tell()`. The stub echoed a canned
`Acknowledged: ...` response without calling any LLM or actor; this
commit wires up the full pipeline:

Architecture:
- New `SessionWorkflow` (Application layer) orchestrates LLM invocation
  for session tell. Accepts a `ProviderRegistry` and `ToolRegistry`;
  falls back to `FakeListLLM` when no provider is configured.
- `LangChainSessionCaller` implements the `LLMCaller` protocol, building
  history-aware LangChain message lists from the session conversation and
  invoking the LLM via `ToolCallingRuntime.run_tool_loop()`.
- `TellResult` (Pydantic BaseModel) carries the assistant response plus
  token usage (input_tokens, output_tokens, cost_usd, duration_ms).

Domain / service layer:
- `SessionActorNotConfiguredError` added to the session domain model;
  raised when tell is invoked with no actor on the session and no
  `--actor` override. Clear message; CLI exits with code 1.
- `SessionService.get_messages()` abstract method added (+ implementation
  in `PersistentSessionService`) to load ordered message history.

A2A facade:
- `A2aLocalFacade` gains `message/send` and `message/stream` standard
  A2A operation handlers that route to `SessionWorkflow.tell()`.
  Total supported operations count: 42 → 44.

CLI:
- `session tell` command delegates to `_build_session_workflow()`
  (patchable factory) instead of directly calling `SessionService`.
- Non-streaming: `SessionWorkflow.tell()` returns `TellResult`; output
  includes a Usage panel (Rich/Plain) or a `usage` object (JSON/YAML).
- Streaming: `SessionWorkflow.tell_stream()` yields tokens; CLI prints
  them via `console.print` (not raw `sys.stdout.write`).
- Token usage recorded via `SessionService.update_token_usage()` in
  both paths.

Tests:
- New Behave feature `session_tell_llm.feature` (4 scenarios): real LLM
  response persisted; streaming yields tokens; no-actor exits code 1;
  `--actor` override resolves correctly.
- New Robot suite `session_tell_llm.robot` (4 tests): end-to-end with
  stub LLM injected via monkey-patching `_resolve_llm`.
- Updated all existing `session tell` test steps to patch
  `_build_session_workflow` returning a mock `TellResult` so tests
  remain isolated from the LLM layer.
- Updated operation-count assertions (42 → 44) in
  `a2a_cli_facade_integration`, `consolidated_misc`,
  `m6_autonomy_acceptance` feature files and steps.

Cycle 7 (Review ID 8088) fixes:
- Blocker 4: Split `session_workflow.py` (was 801 lines) into two files:
  `session_workflow.py` (467 lines) and `session_caller.py` (318 lines).
  Extracted: `LangChainSessionCaller`, `extract_content`,
  `extract_token_usage`, `estimate_cost`, `estimate_tokens`,
  `history_to_langchain_messages`, and stub classes.
- Blocker 5: Route CLI streaming path through
  `_facade_dispatch("message/stream", ...)` instead of directly
  calling `workflow.tell_stream()`. The facade's
  `_handle_message_stream` falls back to non-streaming with
  `streamed: false` (acceptable for this milestone per the spec).
- Updated streaming test assertion to validate full response presence
  (no longer checks token-by-token word positions, since the facade
  fallback returns a complete message).

ISSUES CLOSED: #5784
2026-05-11 04:39:29 +00:00

129 lines
3.8 KiB
Python

"""Helper script for a2a_facade.robot smoke tests.
Each subcommand is a self-contained check that prints a sentinel on success.
"""
from __future__ import annotations
import sys
from pathlib import Path
# Ensure local source tree is importable
_SRC = str(Path(__file__).resolve().parents[1] / "src")
if _SRC not in sys.path:
sys.path.insert(0, _SRC)
from cleveragents.a2a.errors import ( # noqa: E402
A2aNotAvailableError,
A2aVersionMismatchError,
)
from cleveragents.a2a.events import A2aEventQueue # noqa: E402
from cleveragents.a2a.facade import A2aLocalFacade # noqa: E402
from cleveragents.a2a.models import A2aEvent, A2aRequest # noqa: E402
from cleveragents.a2a.transport import A2aHttpTransport # noqa: E402
from cleveragents.a2a.versioning import A2aVersionNegotiator # noqa: E402
# ---------------------------------------------------------------------------
# Subcommands
# ---------------------------------------------------------------------------
def facade_dispatch() -> None:
"""Dispatch session.create via local facade."""
facade = A2aLocalFacade()
request = A2aRequest(method="session.create")
response = facade.dispatch(request)
if (
response.error is None
and response.result is not None
and "session_id" in response.result
):
print("a2a-facade-dispatch-ok")
else:
print(f"FAIL: unexpected response {response}", file=sys.stderr)
sys.exit(1)
def transport_stub() -> None:
"""Verify transport stub raises A2aNotAvailableError."""
transport = A2aHttpTransport()
try:
transport.connect("http://localhost:8080")
print("FAIL: should have raised", file=sys.stderr)
sys.exit(1)
except A2aNotAvailableError:
pass
if transport.is_connected() is False:
print("a2a-transport-stub-ok")
else:
print("FAIL: is_connected should be False", file=sys.stderr)
sys.exit(1)
def event_queue() -> None:
"""Verify local event queue publish/subscribe."""
queue = A2aEventQueue()
received: list[A2aEvent] = []
queue.subscribe_local(lambda e: received.append(e))
queue.publish(A2aEvent(event_type="test.event"))
if len(received) == 1 and received[0].event_type == "test.event":
print("a2a-event-queue-ok")
else:
print(f"FAIL: received={received}", file=sys.stderr)
sys.exit(1)
def version_negotiate() -> None:
"""Verify version negotiation."""
negotiator = A2aVersionNegotiator()
result = negotiator.negotiate("1.0")
if result != "1.0":
print("FAIL: expected 1.0", file=sys.stderr)
sys.exit(1)
try:
negotiator.negotiate("2.0")
print("FAIL: should have raised", file=sys.stderr)
sys.exit(1)
except A2aVersionMismatchError:
pass
print("a2a-version-negotiate-ok")
def list_operations() -> None:
"""Verify list_operations returns expected operations."""
facade = A2aLocalFacade()
ops = facade.list_operations()
expected = {"session.create", "plan.create", "plan.execute", "context.get"}
if expected.issubset(set(ops)) and len(ops) == 44:
print("a2a-list-operations-ok")
else:
print(f"FAIL: ops={ops}", file=sys.stderr)
sys.exit(1)
# ---------------------------------------------------------------------------
# Dispatch
# ---------------------------------------------------------------------------
_COMMANDS = {
"facade-dispatch": facade_dispatch,
"transport-stub": transport_stub,
"event-queue": event_queue,
"version-negotiate": version_negotiate,
"list-operations": list_operations,
}
def main() -> None:
if len(sys.argv) < 2 or sys.argv[1] not in _COMMANDS:
print(f"Usage: {sys.argv[0]} <{'|'.join(_COMMANDS)}>", file=sys.stderr)
sys.exit(2)
_COMMANDS[sys.argv[1]]()
if __name__ == "__main__":
main()