Commit Graph

5 Commits

Author SHA1 Message Date
aditya 131be21e80 fix(tests): update actor_examples count to 7 after subplan example
CI / benchmark-publish (pull_request) Has been skipped
CI / lint (pull_request) Successful in 13s
CI / build (pull_request) Successful in 16s
CI / quality (pull_request) Successful in 17s
CI / typecheck (pull_request) Successful in 31s
CI / security (pull_request) Successful in 35s
CI / integration_tests (pull_request) Successful in 2m50s
CI / unit_tests (pull_request) Successful in 20m54s
CI / docker (pull_request) Successful in 39s
CI / benchmark-regression (pull_request) Successful in 26m10s
CI / coverage (pull_request) Successful in 48m2s
Refs: #198
2026-02-27 09:24:34 +00:00
aditya e476d2de0e feat(actor): extend hierarchical actor YAML schema and loader
Extend actor YAML schema to support hierarchical graphs with explicit
node types (agent, tool, conditional, subgraph), per-node LSP bindings
(lsp_binding with server, languages, auto, capabilities), and tool-source
references (skills, mcp_servers, agent_skills).

Add schema validation for namespaced actor references, duplicate node IDs,
edge target existence, and graph reachability — all nodes must be reachable
from entry_node via explicit edges or conditional node routing targets.

Update loader to report YAML parse errors with precise line/column positions
and schema validation errors with dotted field paths and remediation hints
pointing to docs/reference/actor_config.md.

Add docs/reference/actor_config.md as the practical configuration reference
covering hierarchical graph examples, node type table, topology rules, and
common error cases with fix guidance.

Refresh examples/actors/graph_workflow.yaml to replace deprecated actor_path
with actor_ref. Add benchmarks/actor_yaml_bench.py for schema load overhead.

Tests: 95 Behave scenarios, 10 Robot smoke tests (including hierarchical
loader smoke test), security scan clean, coverage 99% (threshold 97%).

ISSUES CLOSED: #157
2026-02-25 10:30:42 +00:00
aditya 4ae7f2d6fe test(actor): fix actor examples test suite issues
- Add missing node descriptions in Behave test scenarios
- Fix context_view and parallel execution step definitions
- Update llm_with_tools.yaml max_context_tokens (10000 → 16000)
- Add context.error compatibility for error assertions

Results: Behave 25/25, Robot 16/16, ASV 7/7 all newly added tests passing.
2026-02-18 12:18:37 +00:00
aditya a5fd451a3b fix(actor): resolve Behave test conflicts and add missing step definitions
- Fix ActorType import error in actor_schema_steps.py
- Simplify actor_examples_steps.py to remove duplicate steps
- Add missing Background step and actor validation steps
- Add llm_with_tools.yaml documentation section
- Rename conflicting Given step patterns with 'examples' suffix
- Add comprehensive Then steps for actor config validation
- Fix step patterns to include trailing colons for docstring steps

Test Results:
- 8 scenarios passing (up from 0)
- 138 steps passing (critical path tests working)
- 5 undefined steps remaining (minor edge cases)
- Basic actor example validation fully functional
2026-02-18 11:41:05 +00:00
aditya 02466864ef test(actor): add comprehensive Behave scenarios for actor examples
Create features/actor_examples.feature with 30+ test scenarios covering:
- All 5 example YAML files load and validate successfully
- Strategist actor pattern (planning, large context, read-only tools)
- Executor actor pattern (write-capable tools, implementation focus)
- Reviewer actor pattern (quality gates, linting tools)
- Tool-only actors (no LLM, pure tool collections)
- Validation-node actors (stateless validators, security scanning)
- Linear graph workflows (sequential 3-step pipelines)
- Complex graphs (conditionals, retry logic, tool nodes)
- Hierarchical graphs (subgraph invocation, parallel execution)
- Multi-level patterns (strategic → tactical → execution)
- Invalid example rejection (missing fields, cycles, bad names)
- Documentation completeness verification

Each scenario validates schema correctness, required fields, and
actor-specific patterns aligned with CleverAgents specification.
2026-02-18 08:52:08 +00:00