HAL9000
18d00c04c4
CI / lint (pull_request) Failing after 1m15s
CI / quality (pull_request) Successful in 1m21s
CI / typecheck (pull_request) Successful in 1m34s
CI / security (pull_request) Successful in 1m37s
CI / coverage (pull_request) Has been skipped
CI / unit_tests (pull_request) Failing after 1m37s
CI / docker (pull_request) Has been skipped
CI / build (pull_request) Successful in 33s
CI / helm (pull_request) Successful in 26s
CI / push-validation (pull_request) Successful in 19s
CI / e2e_tests (pull_request) Successful in 3m20s
CI / integration_tests (pull_request) Successful in 4m32s
CI / status-check (pull_request) Failing after 3s
Implements AgentSkillDiscovery class to support discovering Agent Skills from multiple configured directories across three scopes (global, project, local). Handles name collisions with precedence: local > project > global. Adds comprehensive BDD test coverage for multi-scope discovery scenarios including: - Global-only, project-only, and local-only discovery - Combined discovery from all scopes - Name collision resolution with proper precedence - Non-existent and empty scope directory handling - Multiple skills in same scope discovery ISSUES CLOSED: #9369
2.6 KiB
2.6 KiB
Session Domain Model
The Session domain model represents a persistent conversation thread tied to an orchestrator actor. It maintains message history across plans and serves as the user's natural-language interface.
Key Classes
| Class | Description |
|---|---|
Session |
Core session model with messages, token tracking, and export |
SessionMessage |
A single message within a session (ULID-identified, sequenced) |
MessageRole |
Enum: user, assistant, system, tool |
SessionTokenUsage |
Accumulated input/output token counts and cost |
Source Location
src/cleveragents/domain/models/core/session.py
Session Lifecycle
- Create --
Session(session_id=str(ULID()))with optionalactor_name - Append messages --
session.append_message(role, content)auto-sequences - Query --
session.get_messages(limit, offset)for paginated access - Export --
session.as_export_dict()produces a checksummed JSON dict - CLI rendering --
session.as_cli_dict()returns anOrderedDictfor display
Export Serialization Order
The as_export_dict() method produces keys in this fixed order:
schema_version, session_id, actor_name, namespace, messages,
linked_plan_ids, automation_level, token_usage, metadata,
created_at, updated_at, checksum
Running Tests
Behave (BDD unit tests)
nox -s unit_tests -- features/session_model.feature
Robot Framework (smoke / integration tests)
nox -s integration_tests -- robot/session_model.robot
Or run the Robot suite directly:
robot --outputdir build/reports/robot robot/session_model.robot
Robot Smoke Suite
The Robot smoke suite (robot/session_model.robot) validates:
- Session creation -- default fields (
session_id,namespace,is_empty) - Message append ordering -- auto-sequencing produces
[0, 1, 2, ...] - Export dict completeness -- all 12 required keys are present
- CLI dict completeness -- required display keys are present
- Export key order -- keys follow the canonical serialization order
The smoke tests delegate to robot/helper_session_model.py, which can also
be invoked standalone:
python robot/helper_session_model.py create
python robot/helper_session_model.py append-messages
python robot/helper_session_model.py export
python robot/helper_session_model.py cli-dict
python robot/helper_session_model.py export-key-order
ASV Benchmarks
nox -s benchmark
Benchmark suites in benchmarks/session_model_bench.py cover validation
throughput, append performance, and serialization speed.