Compare commits
18 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 3b9f769977 | |||
| 4b1ce228ea | |||
| 2add6333ea | |||
| 3803eb69e4 | |||
| a205099652 | |||
| 7a55f98279 | |||
| d67c3da13e | |||
| b85ab71892 | |||
| 4e992968da | |||
| 40777f0aa3 | |||
| dd9ae99748 | |||
| 3996ad987f | |||
| 66653c0e8e | |||
| 96eec447de | |||
| 90f9987e88 | |||
| 469f253c0d | |||
| 269c08a5a1 | |||
| 43844e0af0 |
@@ -139,14 +139,6 @@ jobs:
|
||||
/tmp/smoke/bin/python "$GITHUB_WORKSPACE/scripts/wheel_smoke.py"
|
||||
|
||||
- name: Publish to PyPI
|
||||
# working-directory matches the preceding Build/Verify steps. Without
|
||||
# this, twine runs from the default workspace checkout dir where
|
||||
# `dist/` doesn't exist and fails with:
|
||||
# ERROR InvalidDistribution: Cannot find file (or expand pattern): 'dist/*'
|
||||
# Caught on the first-ever successful dispatch of this workflow
|
||||
# (run 5097, 2026-05-11 02:08Z) — every other step in the publish
|
||||
# job already had this working-directory; Publish was missing it.
|
||||
working-directory: ${{ runner.temp }}/runtime-build
|
||||
env:
|
||||
# PYPI_TOKEN: repository secret scoped to molecule-ai-workspace-runtime.
|
||||
# Set via: Settings → Actions → Variables and Secrets → New Secret.
|
||||
|
||||
@@ -32,9 +32,11 @@ on:
|
||||
- '.gitea/workflows/publish-workspace-server-image.yml'
|
||||
workflow_dispatch:
|
||||
|
||||
# Serialize per-branch so two rapid main pushes don't race the same
|
||||
# :staging-latest tag retag. Allow parallel runs as they produce
|
||||
# different :staging-<sha> tags and last-write-wins on :staging-latest.
|
||||
# Serialize per-branch so two rapid staging pushes don't race the same
|
||||
# :staging-latest tag retag. Allow staging and main to run in parallel
|
||||
# (different GITHUB_REF → different concurrency group) since they
|
||||
# produce different :staging-<sha> tags and last-write-wins on
|
||||
# :staging-latest is acceptable across branches.
|
||||
#
|
||||
# cancel-in-progress: false → in-flight builds finish; the next push's
|
||||
# build queues. This avoids a partially-pushed image.
|
||||
|
||||
@@ -77,13 +77,6 @@ jobs:
|
||||
# works if we never check out PR HEAD. Same SHA the workflow
|
||||
# itself was loaded from.
|
||||
ref: ${{ github.event.pull_request.base.sha }}
|
||||
- name: Install jq
|
||||
# Gitea Actions runners (ubuntu-latest label) do not bundle jq.
|
||||
# The script uses jq extensively for all JSON parsing; install it
|
||||
# before the script runs. Using -qq for quiet output — diagnostic
|
||||
# info is already captured via SOP_DEBUG=1 on failure.
|
||||
run: apt-get update -qq && apt-get install -y -qq jq
|
||||
|
||||
- name: Verify tier label + reviewer team membership
|
||||
env:
|
||||
# SOP_TIER_CHECK_TOKEN is the org-level secret for the
|
||||
|
||||
@@ -365,7 +365,7 @@ jobs:
|
||||
cache: pip
|
||||
cache-dependency-path: workspace/requirements.txt
|
||||
- if: needs.changes.outputs.python == 'true'
|
||||
run: pip install -r requirements.txt pytest pytest-asyncio pytest-cov sqlalchemy>=2.0.0
|
||||
run: pip install -r requirements.txt pytest pytest-asyncio pytest-cov
|
||||
# Coverage flags + fail-under floor moved into workspace/pytest.ini
|
||||
# (issue #1817) so local `pytest` and CI use identical config.
|
||||
- if: needs.changes.outputs.python == 'true'
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
staging trigger
|
||||
@@ -11,9 +11,6 @@ services:
|
||||
- "5432:5432"
|
||||
volumes:
|
||||
- pgdata:/var/lib/postgresql/data
|
||||
networks:
|
||||
- molecule-core-net
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-dev}"]
|
||||
interval: 2s
|
||||
@@ -28,8 +25,6 @@ services:
|
||||
environment:
|
||||
POSTGRES_USER: ${POSTGRES_USER:-dev}
|
||||
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-dev}
|
||||
networks:
|
||||
- molecule-core-net
|
||||
command:
|
||||
- /bin/sh
|
||||
- -c
|
||||
@@ -50,9 +45,6 @@ services:
|
||||
- "6379:6379"
|
||||
volumes:
|
||||
- redisdata:/data
|
||||
networks:
|
||||
- molecule-core-net
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "redis-cli", "ping"]
|
||||
interval: 2s
|
||||
@@ -60,9 +52,7 @@ services:
|
||||
retries: 10
|
||||
|
||||
# digest-pinned 2026-05-10 (sha256:5b296e0ba1da74efea3143c773ddd60245f249fb7c72eb1d866c2d6ebc759fbe, linux/amd64)
|
||||
# Named langfuse-clickhouse (not clickhouse) to match the service name used in
|
||||
# docker-compose.yml's depends_on block for the main langfuse service.
|
||||
langfuse-clickhouse:
|
||||
clickhouse:
|
||||
image: clickhouse/clickhouse-server@sha256:5b296e0ba1da74efea3143c773ddd60245f249fb7c72eb1d866c2d6ebc759fbe
|
||||
environment:
|
||||
CLICKHOUSE_DB: langfuse
|
||||
@@ -70,8 +60,6 @@ services:
|
||||
CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-langfuse-dev}
|
||||
volumes:
|
||||
- clickhousedata:/var/lib/clickhouse
|
||||
networks:
|
||||
- molecule-core-net
|
||||
healthcheck:
|
||||
test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://127.0.0.1:8123/ping || exit 1"]
|
||||
interval: 5s
|
||||
@@ -116,7 +104,7 @@ services:
|
||||
langfuse-web:
|
||||
image: langfuse/langfuse@sha256:e7aafd3ccf721821b40f8b2251220b4bb8af5e4877b5c5a8846af5b3318aaf1d
|
||||
depends_on:
|
||||
langfuse-clickhouse:
|
||||
clickhouse:
|
||||
condition: service_healthy
|
||||
langfuse-db-init:
|
||||
condition: service_completed_successfully
|
||||
@@ -125,8 +113,8 @@ services:
|
||||
# Langfuse v2 expects the HTTP interface (port 8123). The previous
|
||||
# clickhouse://...:9000 native-protocol URL is rejected with
|
||||
# "ClickHouse URL protocol must be either http or https".
|
||||
CLICKHOUSE_URL: http://langfuse-clickhouse:8123
|
||||
CLICKHOUSE_MIGRATION_URL: clickhouse://langfuse-clickhouse:9000
|
||||
CLICKHOUSE_URL: http://clickhouse:8123
|
||||
CLICKHOUSE_MIGRATION_URL: clickhouse://clickhouse:9000
|
||||
CLICKHOUSE_USER: langfuse
|
||||
CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-langfuse-dev}
|
||||
NEXTAUTH_SECRET: ${LANGFUSE_SECRET:-changeme-langfuse-secret}
|
||||
|
||||
+79
-1
@@ -3,7 +3,85 @@ include:
|
||||
- docker-compose.infra.yml
|
||||
|
||||
services:
|
||||
# --- Infrastructure ---
|
||||
# digest-pinned 2026-05-10 (sha256:4941ef97aaa2633ce9808f7766f8b8d746dd039ce8c51ca6da185c3dc63ab579, linux/amd64)
|
||||
postgres:
|
||||
image: postgres@sha256:4941ef97aaa2633ce9808f7766f8b8d746dd039ce8c51ca6da185c3dc63ab579
|
||||
environment:
|
||||
POSTGRES_USER: ${POSTGRES_USER:-dev}
|
||||
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-dev}
|
||||
POSTGRES_DB: ${POSTGRES_DB:-molecule}
|
||||
command: ["postgres", "-c", "wal_level=logical"]
|
||||
ports:
|
||||
- "5432:5432"
|
||||
volumes:
|
||||
- pgdata:/var/lib/postgresql/data
|
||||
networks:
|
||||
- molecule-core-net
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-dev}"]
|
||||
interval: 2s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
|
||||
langfuse-db-init:
|
||||
image: postgres@sha256:4941ef97aaa2633ce9808f7766f8b8d746dd039ce8c51ca6da185c3dc63ab579
|
||||
depends_on:
|
||||
postgres:
|
||||
condition: service_healthy
|
||||
environment:
|
||||
POSTGRES_USER: ${POSTGRES_USER:-dev}
|
||||
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-dev}
|
||||
command:
|
||||
- /bin/sh
|
||||
- -c
|
||||
- |
|
||||
export PGPASSWORD="$${POSTGRES_PASSWORD}"
|
||||
until pg_isready -h postgres -U "$${POSTGRES_USER}" -d postgres >/dev/null 2>&1; do
|
||||
sleep 1
|
||||
done
|
||||
if ! psql -h postgres -U "$${POSTGRES_USER}" -d postgres -tAc "SELECT 1 FROM pg_database WHERE datname = 'langfuse'" | grep -q 1; then
|
||||
psql -h postgres -U "$${POSTGRES_USER}" -d postgres -c "CREATE DATABASE langfuse"
|
||||
fi
|
||||
networks:
|
||||
- molecule-core-net
|
||||
|
||||
# digest-pinned 2026-05-10 (sha256:b1addbe72465a718643cff9e60a58e6df1841e29d6d7d60c9a85d8d72f08d1a7, linux/amd64)
|
||||
redis:
|
||||
image: redis@sha256:b1addbe72465a718643cff9e60a58e6df1841e29d6d7d60c9a85d8d72f08d1a7
|
||||
command: ["redis-server", "--notify-keyspace-events", "KEA"]
|
||||
ports:
|
||||
- "6379:6379"
|
||||
volumes:
|
||||
- redisdata:/data
|
||||
networks:
|
||||
- molecule-core-net
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "redis-cli", "ping"]
|
||||
interval: 2s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
|
||||
# --- Observability ---
|
||||
# digest-pinned 2026-05-10 (sha256:5b296e0ba1da74efea3143c773ddd60245f249fb7c72eb1d866c2d6ebc759fbe, linux/amd64)
|
||||
langfuse-clickhouse:
|
||||
image: clickhouse/clickhouse-server@sha256:5b296e0ba1da74efea3143c773ddd60245f249fb7c72eb1d866c2d6ebc759fbe
|
||||
environment:
|
||||
CLICKHOUSE_DB: langfuse
|
||||
CLICKHOUSE_USER: langfuse
|
||||
CLICKHOUSE_PASSWORD: langfuse
|
||||
volumes:
|
||||
- clickhousedata:/var/lib/clickhouse
|
||||
networks:
|
||||
- molecule-core-net
|
||||
healthcheck:
|
||||
test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://127.0.0.1:8123/ping || exit 1"]
|
||||
interval: 5s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
|
||||
# digest-pinned 2026-05-10 (sha256:e7aafd3ccf721821b40f8b2251220b4bb8af5e4877b5c5a8846af5b3318aaf1d, linux/amd64)
|
||||
langfuse:
|
||||
image: langfuse/langfuse@sha256:e7aafd3ccf721821b40f8b2251220b4bb8af5e4877b5c5a8846af5b3318aaf1d
|
||||
@@ -217,7 +295,7 @@ services:
|
||||
- "4000:4000"
|
||||
volumes:
|
||||
- ./infra/litellm_config.yml:/app/config.yaml:ro
|
||||
command: ["--config", "/app/config.yaml", "--port", "4000", "--num_workers", 4]
|
||||
command: ["--config", "/app/config.yaml", "--port", "4000", "--num_workers", "4"]
|
||||
environment:
|
||||
# Pass provider API keys through — only the ones you have are needed
|
||||
ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-}
|
||||
|
||||
@@ -44,4 +44,3 @@
|
||||
{"name": "mock-bigorg", "repo": "molecule-ai/molecule-ai-org-template-mock-bigorg", "ref": "main"}
|
||||
]
|
||||
}
|
||||
// Triggered by Integration Tester at 2026-05-10T08:52Z
|
||||
|
||||
@@ -50,7 +50,6 @@ from pathlib import Path
|
||||
# without updating this set), which broke every workspace startup with
|
||||
# `ModuleNotFoundError: No module named 'transcript_auth'`.
|
||||
TOP_LEVEL_MODULES = {
|
||||
"_sanitize_a2a",
|
||||
"a2a_cli",
|
||||
"a2a_client",
|
||||
"a2a_executor",
|
||||
|
||||
@@ -49,7 +49,6 @@ import (
|
||||
"net/http"
|
||||
"os"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/Molecule-AI/molecule-monorepo/platform/pkg/provisionhook"
|
||||
@@ -99,19 +98,7 @@ func (h *GitHubTokenHandler) GetInstallationToken(c *gin.Context) {
|
||||
token, expiresAt, err := generateAppInstallationToken()
|
||||
if err != nil {
|
||||
log.Printf("[github] fallback token generation failed: %v", err)
|
||||
// #388: when GITHUB_APP_ID/INSTALLATION_ID are unset (e.g. post
|
||||
// org suspension or Gitea-canonical deployments), this is a
|
||||
// configuration gap, not an internal server error. Return 501 so
|
||||
// callers (workspace polling loop) can distinguish "feature off"
|
||||
// from "transient error" and stop polling.
|
||||
if strings.Contains(err.Error(), "required") {
|
||||
c.JSON(http.StatusNotImplemented, gin.H{
|
||||
"error": "GitHub integration not configured",
|
||||
"scm": "gitea",
|
||||
})
|
||||
} else {
|
||||
c.JSON(http.StatusInternalServerError, gin.H{"error": "token refresh failed"})
|
||||
}
|
||||
c.JSON(http.StatusInternalServerError, gin.H{"error": "token refresh failed"})
|
||||
return
|
||||
}
|
||||
c.JSON(http.StatusOK, gin.H{"token": token, "expires_at": expiresAt})
|
||||
|
||||
@@ -76,16 +76,14 @@ func TestGitHubToken_NilRegistry(t *testing.T) {
|
||||
// implement TokenProvider (e.g. a non-GitHub mutator in the chain).
|
||||
//
|
||||
// Post-#960/#1101 the handler now falls back to direct env-based App
|
||||
// token generation (GITHUB_APP_ID / INSTALLATION_ID / PRIVATE_KEY_FILE).
|
||||
//
|
||||
// When GITHUB_APP_ID or INSTALLATION_ID is unset (e.g. post org suspension
|
||||
// or Gitea-canonical deployments without GitHub App), generateAppInstallationToken
|
||||
// returns an error with "required" in the message. The handler now returns
|
||||
// 501 Not Implemented with {"error":"GitHub integration not configured","scm":"gitea"}
|
||||
// so callers can distinguish "feature off" from "transient error" and stop
|
||||
// polling (#388). Other errors (e.g. network failures reading the private key)
|
||||
// still return 500.
|
||||
func TestGitHubToken_NoTokenProvider_MissingConfigReturns501(t *testing.T) {
|
||||
// token generation (GITHUB_APP_ID / INSTALLATION_ID / PRIVATE_KEY_FILE)
|
||||
// when no registered provider matches. In the test environment those
|
||||
// env vars are unset, so the fallback fails with 500 "token refresh
|
||||
// failed" — a clean retryable signal for the workspace credential
|
||||
// helper. Previously this path returned 404; the new 500 matches the
|
||||
// ProviderError shape so callers don't have to branch on "missing
|
||||
// provider" vs "provider failed".
|
||||
func TestGitHubToken_NoTokenProvider(t *testing.T) {
|
||||
reg := provisionhook.NewRegistry()
|
||||
reg.Register(&mockMutatorOnly{name: "other-plugin"})
|
||||
h := NewGitHubTokenHandler(reg)
|
||||
@@ -93,20 +91,12 @@ func TestGitHubToken_NoTokenProvider_MissingConfigReturns501(t *testing.T) {
|
||||
|
||||
h.GetInstallationToken(c)
|
||||
|
||||
// GITHUB_APP_ID/INSTALLATION_ID are unset in test env → "required" error → 501
|
||||
if w.Code != http.StatusNotImplemented {
|
||||
t.Fatalf("expected 501 for missing GITHUB_APP_ID/INSTALLATION_ID, got %d: %s",
|
||||
if w.Code != http.StatusInternalServerError {
|
||||
t.Fatalf("expected 500 (env-based fallback fails with unset GITHUB_APP_* vars), got %d: %s",
|
||||
w.Code, w.Body.String())
|
||||
}
|
||||
var body map[string]string
|
||||
if err := json.Unmarshal(w.Body.Bytes(), &body); err != nil {
|
||||
t.Fatalf("response is not valid JSON: %v", err)
|
||||
}
|
||||
if body["error"] == "" {
|
||||
t.Error("expected non-empty error field in 501 response")
|
||||
}
|
||||
if body["scm"] != "gitea" {
|
||||
t.Errorf("expected scm=gitea, got %q", body["scm"])
|
||||
if !strings.Contains(w.Body.String(), "token refresh failed") {
|
||||
t.Errorf("expected body to contain 'token refresh failed', got: %s", w.Body.String())
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -51,7 +51,6 @@ from shared_runtime import (
|
||||
from executor_helpers import (
|
||||
collect_outbound_files,
|
||||
extract_attached_files,
|
||||
read_delegation_results,
|
||||
)
|
||||
from builtin_tools.telemetry import (
|
||||
A2A_TASK_ID,
|
||||
@@ -216,17 +215,6 @@ class LangGraphA2AExecutor(AgentExecutor):
|
||||
3. Message(final_text) — terminal event
|
||||
"""
|
||||
user_input = extract_message_text(context)
|
||||
# Inject delegation results from prior turns. Heartbeat writes
|
||||
# completed delegation rows to DELEGATION_RESULTS_FILE and sends
|
||||
# a self-message to wake the agent; this consumes the file and
|
||||
# surfaces the results as context so the agent can act on them
|
||||
# without needing an explicit check_task_status call.
|
||||
# Results are prepended so they are visible even when the
|
||||
# self-message text is overwritten by a subsequent user message.
|
||||
pending_results = read_delegation_results()
|
||||
if pending_results:
|
||||
logger.info("A2A execute: injecting %d delegation result(s)", pending_results.count("\n") + 1)
|
||||
user_input = f"[Delegation results available]\n{pending_results}\n\n{user_input}"
|
||||
# Pull attached files from A2A message parts (kind: "file") and
|
||||
# append a manifest to the prompt so the agent knows they exist.
|
||||
# LangGraph tools (filesystem, bash, skills) can then open the
|
||||
|
||||
@@ -194,7 +194,7 @@ def parse(data: Any) -> Variant:
|
||||
method,
|
||||
data.get("queue_id", "?"),
|
||||
)
|
||||
return Queued(method=method, delivery_mode="push")
|
||||
return Queued(method=method)
|
||||
|
||||
# Poll-queued envelope. Both keys must be present — the workspace
|
||||
# server sets them together; if only one is present the body is
|
||||
|
||||
@@ -77,16 +77,6 @@ async def delegate_task(workspace_id: str, task: str) -> str:
|
||||
return str(result) if isinstance(result, str) else "(no text)"
|
||||
elif "error" in data:
|
||||
err = data["error"]
|
||||
# Handle both string-form errors ("error": "some string")
|
||||
# and object-form errors ("error": {"message": "...", "code": ...}).
|
||||
msg = ""
|
||||
if isinstance(err, dict):
|
||||
msg = err.get("message", "")
|
||||
elif isinstance(err, str):
|
||||
msg = err
|
||||
else:
|
||||
msg = str(err)
|
||||
return f"Error: {msg}"
|
||||
msg = ""
|
||||
if isinstance(err, dict):
|
||||
msg = err.get("message", "")
|
||||
|
||||
@@ -51,22 +51,6 @@ class AdaptorSource:
|
||||
|
||||
def _load_module_from_path(module_name: str, path: Path):
|
||||
"""Import a Python file by absolute path. Returns the module or None on failure."""
|
||||
# Ensure the plugins_registry package and its submodules are importable in the
|
||||
# fresh module namespace created by module_from_spec(). Plugin adapters
|
||||
# (molecule-skill-*/adapters/*.py) use "from plugins_registry.builtins import ..."
|
||||
# which requires plugins_registry and its submodules to already be in sys.modules.
|
||||
# We import and register them before exec_module so the plugin's own
|
||||
# from ... import statements resolve correctly.
|
||||
import sys
|
||||
import plugins_registry
|
||||
sys.modules.setdefault("plugins_registry", plugins_registry)
|
||||
for _sub in ("builtins", "protocol", "raw_drop"):
|
||||
try:
|
||||
sub = importlib.import_module(f"plugins_registry.{_sub}")
|
||||
sys.modules.setdefault(f"plugins_registry.{_sub}", sub)
|
||||
except Exception:
|
||||
# Submodule may not exist in all versions; skip if absent.
|
||||
pass
|
||||
spec = importlib.util.spec_from_file_location(module_name, path)
|
||||
if spec is None or spec.loader is None:
|
||||
return None
|
||||
|
||||
@@ -1,60 +0,0 @@
|
||||
"""Tests for _load_module_from_path sys.modules injection fix (issue #296).
|
||||
|
||||
Verifies that plugin adapters using "from plugins_registry.builtins import ..."
|
||||
can be loaded via _load_module_from_path() without ModuleNotFoundError.
|
||||
"""
|
||||
import sys
|
||||
import tempfile
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
# Ensure the plugins_registry package is importable
|
||||
import plugins_registry
|
||||
|
||||
from plugins_registry import _load_module_from_path
|
||||
|
||||
|
||||
def test_load_adapter_with_plugins_registry_import():
|
||||
"""Plugin adapter using 'from plugins_registry.builtins import ...' loads cleanly."""
|
||||
# Write a temp adapter file that does the exact import from the bug report.
|
||||
with tempfile.NamedTemporaryFile(
|
||||
mode="w", suffix=".py", delete=False, dir=tempfile.gettempdir()
|
||||
) as f:
|
||||
f.write("from plugins_registry.builtins import AgentskillsAdaptor as Adaptor\n")
|
||||
f.write("assert Adaptor is not None\n")
|
||||
adapter_path = Path(f.name)
|
||||
|
||||
try:
|
||||
module = _load_module_from_path("test_adapter", adapter_path)
|
||||
assert module is not None, "module should load without error"
|
||||
assert hasattr(module, "Adaptor"), "module should expose Adaptor"
|
||||
finally:
|
||||
os.unlink(adapter_path)
|
||||
|
||||
|
||||
def test_load_adapter_with_full_plugins_registry_import():
|
||||
"""Plugin adapter using 'from plugins_registry import ...' loads cleanly."""
|
||||
with tempfile.NamedTemporaryFile(
|
||||
mode="w", suffix=".py", delete=False, dir=tempfile.gettempdir()
|
||||
) as f:
|
||||
f.write("from plugins_registry import InstallContext, resolve\n")
|
||||
f.write("from plugins_registry.protocol import PluginAdaptor\n")
|
||||
f.write("assert InstallContext is not None\n")
|
||||
f.write("assert resolve is not None\n")
|
||||
f.write("assert PluginAdaptor is not None\n")
|
||||
adapter_path = Path(f.name)
|
||||
|
||||
try:
|
||||
module = _load_module_from_path("test_adapter_full", adapter_path)
|
||||
assert module is not None, "module should load without error"
|
||||
assert hasattr(module, "InstallContext"), "module should expose InstallContext"
|
||||
assert hasattr(module, "resolve"), "module should expose resolve"
|
||||
assert hasattr(module, "PluginAdaptor"), "module should expose PluginAdaptor"
|
||||
finally:
|
||||
os.unlink(adapter_path)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_load_adapter_with_plugins_registry_import()
|
||||
test_load_adapter_with_full_plugins_registry_import()
|
||||
print("ALL TESTS PASS")
|
||||
@@ -1201,94 +1201,3 @@ async def test_terminal_error_routes_via_updater_failed():
|
||||
assert not eq._complete_calls, (
|
||||
"complete() should not fire when execute() raises"
|
||||
)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Issue #354 — delegation results auto-resume gap
|
||||
# ---------------------------------------------------------------------------
|
||||
# heartbeat.py's _check_delegations writes completed delegation rows to
|
||||
# DELEGATION_RESULTS_FILE and sends a self-message to wake the agent.
|
||||
# read_delegation_results() in executor_helpers.py atomically reads+consumes
|
||||
# that file. The fix wires this consumer into _core_execute so the agent
|
||||
# receives delegation results as context in the next turn — closing the gap
|
||||
# where parallel delegate_task calls return after the SDK turn ends and the
|
||||
# agent has no way to discover the results.
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_delegation_results_injected_into_user_input(monkeypatch):
|
||||
"""When delegation results exist, they are prepended to the user input
|
||||
passed to the agent so the agent can act on them without an explicit
|
||||
check_task_status call."""
|
||||
import a2a_executor
|
||||
from unittest.mock import patch
|
||||
|
||||
pending_results = (
|
||||
"- [completed] Delegation abc123: Checked 3 issues\n"
|
||||
" Response: 3 open, 0 critical\n"
|
||||
"- [failed] Delegation def456: Scan PR #352\n"
|
||||
" Error: peer workspace offline"
|
||||
)
|
||||
|
||||
# Patch read_delegation_results at the module level where a2a_executor
|
||||
# imported it so the _core_execute call picks it up.
|
||||
with patch.object(a2a_executor, "read_delegation_results", return_value=pending_results):
|
||||
agent = MagicMock()
|
||||
agent.astream_events = MagicMock(return_value=_stream(_text_chunk("Got it")))
|
||||
executor = LangGraphA2AExecutor(agent)
|
||||
|
||||
part = MagicMock()
|
||||
part.text = "What's the status?"
|
||||
context = _make_context([part], "ctx-deleg", task_id="task-deleg")
|
||||
eq = _make_event_queue()
|
||||
eq._complete_calls = []
|
||||
eq._failed_calls = []
|
||||
|
||||
await executor.execute(context, eq)
|
||||
|
||||
# Verify the agent received the injected context
|
||||
agent.astream_events.assert_called_once()
|
||||
call_args = agent.astream_events.call_args
|
||||
messages = call_args[0][0]["messages"]
|
||||
|
||||
# The last message should be a human turn with the injected context
|
||||
human_turn = messages[-1]
|
||||
assert human_turn[0] == "human"
|
||||
# Must contain the delegation results marker
|
||||
assert "[Delegation results available]" in human_turn[1]
|
||||
# Must contain the completed delegation
|
||||
assert "abc123" in human_turn[1]
|
||||
assert "3 open" in human_turn[1]
|
||||
# Must contain the failed delegation
|
||||
assert "def456" in human_turn[1]
|
||||
# Must contain the original user message
|
||||
assert "What's the status?" in human_turn[1]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_no_delegation_results_no_injection(monkeypatch):
|
||||
"""When no delegation results exist, user input is passed through unchanged."""
|
||||
import a2a_executor
|
||||
from unittest.mock import patch
|
||||
|
||||
with patch.object(a2a_executor, "read_delegation_results", return_value=""):
|
||||
agent = MagicMock()
|
||||
agent.astream_events = MagicMock(return_value=_stream(_text_chunk("ok")))
|
||||
executor = LangGraphA2AExecutor(agent)
|
||||
|
||||
part = MagicMock()
|
||||
part.text = "Hello"
|
||||
context = _make_context([part], "ctx-clean", task_id="task-clean")
|
||||
eq = _make_event_queue()
|
||||
eq._complete_calls = []
|
||||
eq._failed_calls = []
|
||||
|
||||
await executor.execute(context, eq)
|
||||
|
||||
agent.astream_events.assert_called_once()
|
||||
call_args = agent.astream_events.call_args
|
||||
messages = call_args[0][0]["messages"]
|
||||
human_turn = messages[-1]
|
||||
assert human_turn[0] == "human"
|
||||
# Must NOT contain the injection marker
|
||||
assert "[Delegation results available]" not in human_turn[1]
|
||||
assert human_turn[1] == "Hello"
|
||||
|
||||
@@ -105,27 +105,6 @@ _FIXTURES = {
|
||||
"status": "queued",
|
||||
"delivery_mode": "poll",
|
||||
},
|
||||
# Push-mode queue envelope: returned when a push-mode workspace is at
|
||||
# capacity. The platform queues the request and returns
|
||||
# {queued: true, message: "...", queue_id: "..."}. The ``delivery_mode``
|
||||
# field is not present in this envelope (distinguishes it from poll-mode).
|
||||
"push_queued_full": {
|
||||
"queued": True,
|
||||
"method": "message/send",
|
||||
"queue_id": "q-abc-123",
|
||||
},
|
||||
"push_queued_notify": {
|
||||
"queued": True,
|
||||
"method": "notify",
|
||||
},
|
||||
"push_queued_no_method": {
|
||||
"queued": True,
|
||||
},
|
||||
"push_queued_no_queue_id": {
|
||||
# queue_id is purely informational — parser must not raise on its absence.
|
||||
"queued": True,
|
||||
"method": "message/send",
|
||||
},
|
||||
"malformed_empty_dict": {},
|
||||
"malformed_unexpected_keys": {"foo": "bar", "baz": 42},
|
||||
"malformed_status_queued_no_delivery_mode": {
|
||||
@@ -180,62 +159,6 @@ class TestQueuedVariant:
|
||||
a2a_response.parse(_FIXTURES["poll_queued_full"])
|
||||
assert any("queued for poll-mode peer" in r.message for r in caplog.records)
|
||||
|
||||
# --- Push-mode queue (handleA2ADispatchError → EnqueueA2A → 202 {queued: true}) ---
|
||||
|
||||
def test_push_queued_full_returns_queued_with_delivery_mode_push(self):
|
||||
# The push-mode path must set delivery_mode="push", not silently default to "poll".
|
||||
# Callers that branch on v.delivery_mode will mis-route poll-mode responses
|
||||
# as push-mode (and vice versa) if this field is wrong.
|
||||
v = a2a_response.parse(_FIXTURES["push_queued_full"])
|
||||
assert isinstance(v, a2a_response.Queued)
|
||||
assert v.method == "message/send"
|
||||
assert v.delivery_mode == "push"
|
||||
|
||||
def test_push_queued_notify(self):
|
||||
v = a2a_response.parse(_FIXTURES["push_queued_notify"])
|
||||
assert isinstance(v, a2a_response.Queued)
|
||||
assert v.method == "notify"
|
||||
assert v.delivery_mode == "push"
|
||||
|
||||
def test_push_queued_missing_method_defaults_to_message_send(self):
|
||||
# Push-mode servers should always send method, but we handle absence gracefully.
|
||||
v = a2a_response.parse(_FIXTURES["push_queued_no_method"])
|
||||
assert isinstance(v, a2a_response.Queued)
|
||||
assert v.method == "message/send"
|
||||
assert v.delivery_mode == "push"
|
||||
|
||||
def test_push_queued_missing_queue_id_still_parsed(self):
|
||||
# queue_id is purely informational — its absence must not break parsing.
|
||||
v = a2a_response.parse(_FIXTURES["push_queued_no_queue_id"])
|
||||
assert isinstance(v, a2a_response.Queued)
|
||||
assert v.method == "message/send"
|
||||
assert v.delivery_mode == "push"
|
||||
|
||||
def test_push_queued_is_distinct_from_poll_queued(self):
|
||||
# Both paths return Queued, but from different wire envelopes.
|
||||
# Verify both parse correctly and are independent.
|
||||
push_v = a2a_response.parse(_FIXTURES["push_queued_full"])
|
||||
poll_v = a2a_response.parse(_FIXTURES["poll_queued_full"])
|
||||
assert isinstance(push_v, a2a_response.Queued)
|
||||
assert isinstance(poll_v, a2a_response.Queued)
|
||||
assert push_v.method == poll_v.method == "message/send"
|
||||
assert push_v.delivery_mode == "push"
|
||||
assert poll_v.delivery_mode == "poll"
|
||||
|
||||
def test_push_queued_logs_queue_id(self, caplog):
|
||||
with caplog.at_level(logging.INFO, logger="a2a_response"):
|
||||
a2a_response.parse(_FIXTURES["push_queued_full"])
|
||||
assert any("q-abc-123" in r.message for r in caplog.records)
|
||||
|
||||
def test_queued_string_yes_is_malformed_not_push_queued(self):
|
||||
# ``{"queued": "yes"}`` is not True, so it must NOT enter the push branch.
|
||||
v = a2a_response.parse({"queued": "yes"})
|
||||
assert isinstance(v, a2a_response.Malformed)
|
||||
|
||||
def test_queued_false_is_malformed(self):
|
||||
v = a2a_response.parse({"queued": False})
|
||||
assert isinstance(v, a2a_response.Malformed)
|
||||
|
||||
|
||||
class TestResultVariant:
|
||||
"""``parse()`` extracts the JSON-RPC ``result`` envelope into
|
||||
@@ -513,10 +436,6 @@ class TestRegressionGate:
|
||||
"poll_queued_full": a2a_response.Queued,
|
||||
"poll_queued_notify": a2a_response.Queued,
|
||||
"poll_queued_no_method": a2a_response.Queued,
|
||||
"push_queued_full": a2a_response.Queued,
|
||||
"push_queued_notify": a2a_response.Queued,
|
||||
"push_queued_no_method": a2a_response.Queued,
|
||||
"push_queued_no_queue_id": a2a_response.Queued,
|
||||
"malformed_empty_dict": a2a_response.Malformed,
|
||||
"malformed_unexpected_keys": a2a_response.Malformed,
|
||||
"malformed_status_queued_no_delivery_mode": a2a_response.Malformed,
|
||||
|
||||
Reference in New Issue
Block a user