Add max_child_depth field to DecompositionConfig (default: 5, matching
plan.max-child-depth config) with validation in __post_init__. Update
_build_hierarchy() in DecompositionService to stop recursion and emit
a warning when the depth limit is reached.
BDD tests verify: max_child_depth guards trigger before max_depth
when more restrictive, warnings are logged, default config value is
correct, and invalid values are rejected.
ISSUES CLOSED: #10269
Wire subplan_service from the DI container into _get_plan_executor() so
PlanExecutor can spawn child plans during the Execute phase. When
SubplanService is available but SubplanExecutionService is not explicitly
injected, _execute_subplans() now lazily creates a SubplanExecutionService
on-the-fly using the parent plan's subplan_config and the new
_execute_child_plan callback.
- _get_plan_executor(): retrieve subplan_service from container, pass to
PlanExecutor constructor
- _execute_subplans(): lazily build SubplanExecutionService when only
SubplanService is wired (Forgejo #10268)
- _execute_child_plan(): new PlanExecutor method that runs a child plan's
strategize + execute phases, registered as executor_fn callback
ISSUES CLOSED: #10268
## Summary
This PR fixes issue #10878 where architecture reviews were truncated because the regex pattern for parsing file output would stop at the first ``` encountered in the Markdown report.
## Changes
- Change file delimiters from ``` to >>>>>>>/<<<<<<< to avoid Markdown conflicts
- Add tier hydration before strategize phase in plan_executor.py
- Increase max_tokens to 16384 in llm_actors.py for longer outputs
- Increase context_max_tokens_hot from 16000 to 32000 in settings.py
- Fix get_hot_view → get_hot_fragments in strategy_actor.py and plan_executor.py
- Add opencode to skip directories in context_tier_hydrator.py
- Change sandbox output location to plan-output/ directory in plan.py
- Add get_context_summary stub method to acms_service.py
## Testing
Run architecture review action and verify the output report is complete with all sections.
Reviewed-on: cleveragents/cleveragents-core#10938
Implements the full tool-calling path for `agents actor run --skill` so that LLM
actors can actually invoke tools through the ToolCallingRuntime loop when a skill
is attached.
Core changes:
- reactive/tool_caller.py (new): ToolCallingLLMCaller implements the LLMCaller protocol;
binds tool schemas via bind_tools(), threads SystemMessage+HumanMessage on first call
and AIMessage+ToolMessages on subsequent calls, extracts tool calls from LangChain
responses following the LangChainSessionCaller pattern.
- reactive/tool_caller.py: bidirectional tool name encoding via uppercase sentinels
(_encode_tool_name / _decode_tool_name) to make CleverAgents namespaced tool names
("builtin/file-read", "server:local/tool") compatible with Anthropic's tool name
pattern ^[a-zA-Z0-9_-]{1,128}$. Uses _C_ for ":" and _S_ for "/" — uppercase
sentinels are safe because valid CleverAgents tool names forbid uppercase letters.
Encoding applied in _resolve_llm() before bind_tools(); decoding applied in invoke()
when extracting tool calls from the LLM response.
- reactive/tool_agent.py (new): ToolCallingAgent builds a per-run local ToolRegistry from
resolved skill tool entries by looking up names in the shared builtin_registry; drives
ToolCallingRuntime.run_tool_loop(); exposes last_result for tool_calls surfacing.
- reactive/application.py: (ST-1) _make_agent_instance() now always merges skill tools
instead of silently dropping them when actor has no base tools list; routes
tools+llm→ToolCallingAgent, tools+non-llm→SimpleToolAgent, no-tools+llm→SimpleLLMAgent;
(ST-4) _builtin_registry created at startup with register_file_tools/git/subplan;
(ST-6) _tally_tool_calls() + last_run_tool_calls property.
- reactive/graph_executor.py: (ST-5) ToolCallingAgent added to isinstance check in
_invoke_agent() so context dict is forwarded for Jinja2 rendering.
- cli/commands/actor_run.py: prints "Tool Calls: {n}" when > 0.
Test fixes:
- features/steps/actor_cli_run_steps.py: _make_app() sets last_run_tool_calls=0 to avoid
MagicMock>int TypeError in Python 3.13.
- features/steps/actor_run_signature_resolve_steps.py: same fix.
- robot/helper_actor_run_signature.py: same fix.
- features/reactive_application_coverage_boost.feature: updated scenario to verify new
correct behavior (LLM+skills → ToolCallingAgent, not silently kept as SimpleLLMAgent).
BDD coverage: 34 scenarios in features/actor_run_tool_calling.feature covering
tool call success, multi-turn loop, no-skill regression, silent-drop fix, LLMCaller
internals, _build_tool_registry edge cases, last_run_tool_calls tallying,
tool name encoding/decoding, and LLM response decoding.
ISSUES CLOSED: #11211
Fixed _resolve_hot_max_tokens() to read hot_max_tokens from the correct
sub-key in context_policy_json. The value is stored under
context_policy_json["acms_config"]["hot_max_tokens"] by
'agents project context set --hot-max-tokens', not at the top level.
The previous read (config_dict.get("hot_max_tokens")) always returned
None, causing the assembler to silently use the global 16K default even
when a project-level override was configured.
Also adds two Behave regression scenarios with @tdd_issue @tdd_issue_11035
tags that exercise the real DB query code path via a mocked
NamespacedProjectModel row, verifying:
1. hot_max_tokens=32000 in acms_config is applied to CoreContextBudget
and ContextRequest (override path).
2. Missing hot_max_tokens falls back to the constructor-injected global
default of 4096 (fallback path).
Module-level import json added to steps file; redundant inline MagicMock
import removed.
ISSUES CLOSED: #11035
ISSUES CLOSED: #11215
Two code paths in the reactive actor run pipeline silently discarded the
options: block from v3 actor YAML, preventing custom OpenAI-compatible
backends (llama.cpp, Ollama, etc.) from being used.
Review fixes applied:
- Fix 1: Relabeled issue #11223 from Type/Task to Type/Bug; added
@tdd_issue/@tdd_issue_11223 tags to all 5 Behave scenarios.
- Fix 2: openai_api_key in options now routes through the registry's
__api_key_sentinel mechanism so user-provided keys correctly override
environment defaults. (stream_router.py)
- Fix 3: type: graph actors now propagate actor-level options to
individual node configs via setdefault. (config_parser.py)
- Fix 4: Options keys are validated against an explicit allowlist;
reserved keys (provider_type, model_id) are excluded; unrecognized
keys log a WARNING instead of being silently forwarded. (stream_router.py)
- Fix 5: Updated _build_from_v3 docstring to list options as a
propagated field. (config_parser.py)
- Fix 6: Removed inconsistent and options_raw emptiness guard; empty
options dicts are now preserved consistently. (config_parser.py)
- Fix 7: Reserved keys provider_type and model_id are excluded from
the options merge loop to prevent TypeError. (stream_router.py)
- Fix 8: Added Behave scenario verifying top-level temperature takes
precedence over options duplicate. (consolidated_routing.feature + steps)
- Fix 9: Strengthened "no extra kwargs" assertion to assert kwargs == {}
directly instead of using an allow-list filter. (stream_router steps)
- Fix 10: Strengthened options assertion to exact dict equality.
(actor_v3_schema_extended_steps.py)
- N1: Comment style aligned to M5: prefix convention.
- N2: Type annotations changed from Any to Context (behave.runner).
- N3: Added Behave scenario for empty options: {} dict behavior.
Tests: 5 new Behave scenarios (3 in actor_v3_schema.feature, 2 in
consolidated_routing.feature) with @tdd_issue/@tdd_issue_11223 tags.
ISSUES CLOSED: #11223
Fix formatting issues detected by CI lint check:
- Simplify multi-line decorator arguments to single line
- Simplify multi-line assertion error messages to single line
This resolves the format --check failure blocking CI.
The Behave scenario at line 671 of consolidated_domain_models.feature
asserts 'the effective set should have {count:d} invariants' but no
step handler existed, causing UndefinedStepError and CI failure.
Adds the missing step: @then('the effective set should have {count:d} invariants')
to step_invariant_models_steps.py, mirroring the existing invariant-set count pattern.
Fixes list_invariants(effective=True) to forward action_name to
get_effective_invariants when scope is ACTION, ensuring action-scoped
invariants are included in effective invariant lists.
Also applies ruff formatting to the return statement in get_effective_invariants.
Addresses reviewer observation about list_invariants gap.
Refs: #9126
The 4-tier invariant precedence chain (plan > action > project > global) was
broken at the domain layer — merge_invariants() and InvariantSet.merge() only
accepted 3 parameters (plan, project, global), silently dropping all action-
scoped invariants. Added action_invariants as a fourth parameter with proper
backward compatibility (default to empty list). Updated module docstrings,
InvariantScope docstring, and InvariantService.get_effective_invariants() to
reflect the correct precedence chain. Added comprehensive BDD test scenarios
covering four-tier merge precedence, action-before-project ordering, and effective
invariant computation with all four scopes.
ISSUES CLOSED: #9126
Add TokenAuthMiddleware to emit AUTH_SUCCESS/AUTH_FAILURE with spec-aligned audit details and wire it through the DI container using server.token resolution.
Add Behave and Robot coverage for auth event emission and end-to-end audit persistence, and update audit subscriber producer notes and changelog.
ISSUES CLOSED: #714
Added _resolve_effective_budget() method to
ACMSExecutePhaseContextAssembler that reads each linked project's
settings.hot_max_tokens and uses the maximum override value as the
pipeline budget instead of the hardcoded global default.
Updated assemble() to use the resolved effective budget for both
CoreContextBudget and ContextRequest.
Added Behave regression scenario with @tdd_issue @tdd_issue_11035 tags
verifying the pipeline receives the project-level budget.
Removed test artifact ANALYSIS.md left over from scenario 20.
Fixes: #11035Fixes: #11215
The plan tree command reported zero decision nodes after strategize because
PlanExecutor.run_strategize() never persisted strategy decisions as domain
Decision objects. Added _persist_strategy_decisions() to the PlanExecutor,
wired decision_service from the DI container in _get_plan_executor(), and
ensure each strategy decision is recorded with correct DecisionType mapping.
ISSUES CLOSED: #10813
Fixed MCPToolAdapter.infer_resource_slots() to handle null values
in JSON Schema by using instead of
which returned None when the key exists with a null value.
The @tdd_expected_fail tag was removed from TDD issue #10470 since the fix is now applied.
- Resolve CHANGELOG.md conflict to include both entries, referencing issue #8164 instead of PR #11161
- Resolve CONTRIBUTORS.md conflict, fix leading space in new entry
- Remove duplicate create_sequence_node function (dead code)
Merges master into feat/structural-output-validation branch
Two defects in ActorConfiguration._extract_v3_actor() prevented YAML files
using the spec-canonical nested actors map format from being registered:
Defect A: The method looked for the 'type' field inside the 'config:' block
(config_block.get('type')) instead of at the actor-entry level
(first_entry.get('type')). Because the spec places 'type' at
actors.<name>.type — a sibling of 'config:', not a child of it — the v3
detection branch never fired for nested-actors-map YAMLs, causing
_extract_v3_actor() to return (None, None, None, False) immediately.
Defect B: Even if the type was found, the method only consulted separate
config.provider and config.model keys; it never parsed the combined
config.actor: 'provider/model' shorthand. Without the combined-field
fallback, provider and model remained None for all spec-canonical YAMLs
that use the shorthand, causing from_blob() to raise
'BadParameter: provider is required'.
Both defects had to be fixed together because Defect A blocked the code
from ever reaching the path where Defect B would otherwise have been
encountered.
The combined-format parser (config.actor split on first '/') is inserted
after the explicit config.provider / config.model lookups so that explicit
separate fields always take precedence over the shorthand when both are
present.
Parsing logic extracted into _parse_combined_actor_field() helper to
eliminate DRY violation. Both provider and model halves validated
consistently (empty provider half was previously silently inferred).
Adds Behave scenarios covering: nested actors map + combined config.actor
(success), explicit config.provider precedence over config.actor,
explicit config.model precedence over config.actor, genuinely missing
provider/model raising validation error, and malformed combined values
(empty model half, empty provider half, missing delimiter). Adds a Robot
integration test for the combined-actor YAML path with provider/model
assertions via show. Restores accidentally deleted TOOL and GRAPH Robot
integration tests. Mirrors provider/model extraction in
step_run_actor_update for assertion step compatibility.
ISSUES CLOSED: #11189
The Behevare-parallel runner in this project does not support inline
parameter substitution for '{param}' or '<param>' markers within
Scenario Outline Examples. All 4 original Scenario Outlines were failing
because parameters were not being substituted, causing UndefinedStep and
ValueError failures.
Fix: Convert all Scenario Outline scenarios to regular Scenarios with
explicit literal step definitions. Each unique Gherkin line gets its own
@Given/@When/@Then step definition matching the exact string.
Also fix pre-existing bugs identified in PR review #8719:
- Fix undefined step by quoting {{seq}} in feature (line 46)
- Fix ctx.decision_result → ctx.validation_result context variable (line 184)
- Fix ctx.struct_result → ctx.validation_result context variable (line 210)
- Replace # type: ignore[arg-type] with proper Callable[[Any], dict] type
- Add missing literal step definitions for structured_output tests
ISSUES CLOSED: #11161
Replace exact character matching with structural component checking
for output validation. Implements three validators covering plan tree
output, decision CLI dicts, and structured session snapshots.
- validate_plan_tree: validates node dicts for required keys (decision_id, type, sequence, question, children), ULID format, correct types, and sibling ordering
- validate_decision_dict: validates decision CLI output against Decision.as_cli_dict() schema with field presence, type, ULID, confidence range [0..1], bool fields
- validate_structured_output: validates StructuredOutput envelope for command, session_id (ULID), status membership, exit_code, elements integrity
- validate_structured_component_output: unified dispatcher by target_type
BDD tests in features/structural_validation.feature.
ISSUES CLOSED: #11147
Chose Option B (fallback): remove orphaned BDD scenarios for two retired agents.
Commit 3c8cf601 deleted .opencode/agents/agent-evolution-pool-supervisor.md
and .opencode/agents/implementation-pool-supervisor.md as part of a large-scale
restructuring of agent definition files. However, their corresponding Behave feature
files and step definitions were not cleaned up, causing nox -s unit_tests to fail
with AssertionError on master.
Removed files:
- features/agent_evolution_pool_supervisor_metadata.feature (7 scenarios testing
agent-evolution-pool-supervisor.md existence and content)
- features/steps/agent_evolution_pool_supervisor_metadata_steps.py (382 lines of
step definitions for the above feature)
- features/pr_compliance_pool_supervisor.feature (10 scenarios testing
implementation-pool-supervisor.md existence and content)
- features/steps/pr_compliance_pool_supervisor_steps.py (219 lines of step
definitions for the above feature)
Both agent definition files were permanently retired by the restructuring commit
and are not expected to return. Keeping orphaned tests that assert on deleted files
is not valid; removal is the correct resolution per the project's handling of
obsolete tests policy.
Quality gates verified:
- nox -s unit_tests: 694 features passed, 0 failed (was failing on master)
- nox -s lint: all checks passed
- nox -s typecheck: 0 errors, 3 warnings (pre-existing import warnings)
- nox -s coverage_report: 96.5% (meets 96.5% threshold)
- nox -s integration_tests: 1998 tests passed, 0 failed
ISSUES CLOSED: #11208
Add _closed flag and close() method to ReactiveEventBus to complete the
RxPY Subject, preventing subscriber resource leaks. close() is idempotent
and raises RuntimeError when called on a closed bus.
Also adds:
- emit() guard against post-close calls (RuntimeError)
- __enter__/__exit__ context manager protocol for automatic cleanup
- BDD scenarios in event_bus.feature and TDD tests in
tdd_reactive_event_bus_close.feature
ISSUES CLOSED: #10378
Implements concrete StdioMCPTransport class that:
- Spawns MCP server as subprocess and communicates via JSON-RPC 2.0 over stdio
- Performs MCP handshake (initialize + notifications/initialized)
- Supports tools/list and tools/call methods
- Uses RLock for thread-safe concurrent access
- Auto-selected when transport='stdio' in MCPServerConfig
Adds BDD tests for stdio transport covering:
- Connection lifecycle and error handling
- Tool discovery and invocation
- MCPToolAdapter integration
ISSUES CLOSED: #4918
Executes the systematic ACP -> A2A module rename per ADR-047.
- Renamed all legacy ACP references to A2A throughout cleveragents.a2a module
- Standardized all 22 exported symbols to A2A naming conventions
- Added BDD test suite validating export completeness, zero ACP remnants, and documentation accuracy
Closes#10583
Parent Epic: #8569 (A2A Standard Adoption)
SubplanService.spawn() now re-records all invariant_enforced decisions from
the parent plan decision tree onto each child plan decision tree. This
satisfies the spec requirement: 'recorded as invariant_enforced decisions that
propagate to child plans.' (Glossary → Invariant)
Previously, child plans started Strategize with a completely empty invariant
set, violating the spec's propagation requirement. non_overridable global
invariants enforced on the parent were not guaranteed to be enforced on child
plans.
The fix adds _propagate_invariant_decisions() to SubplanService which queries
the parent plan's invariant_enforced decisions and re-records each one on the
child plan using DecisionService.record_decision(). The DecisionService is
already injected into SubplanService, so no new dependencies are required.
BDD regression coverage added in features/tdd_invariant_propagation_subplan.feature
with 4 scenarios covering: single invariant propagation, multiple invariant
propagation, non_overridable invariant propagation, and clean spawn with no
parent invariants.
ISSUES CLOSED: #9131
Add BDD regression test for Forgejo issue 4321: ActorRegistry.add()
fails to extract provider and model from nested actor config.
The test verifies that when type is only at the nested actors map level
(not at top level), provider and model are correctly extracted from the
nested config block.
This scenario is already handled correctly by the _extract_nested_v3_config()
function added in commit 78be0887 (issue #4300). The test confirms the fix
works as expected and prevents future regressions.
Tags: @tdd_issue @tdd_issue_4321
ISSUES CLOSED: #4321
Bug #11121: _create_sandbox_for_plan() called GitWorktreeSandbox.cleanup_stale()
unconditionally, destroying the cleveragents/plan-<id> git branch when
agents plan execute was re-invoked on a plan already in execute/complete
state (awaiting apply). This caused plan apply to find zero artifacts.
Fix: Add a phase/state guard inside _create_sandbox_for_plan() that returns
the flat fallback early when the plan is execute/complete, preserving the
worktree branch intact for plan apply to merge.
- TDD regression test from issue #11120 (without @tdd_expected_fail)
- Verified sandbox lifecycle tests still pass
ISSUES CLOSED: #11121
Add two Behave scenarios tagged @tdd_issue, @tdd_issue_11121, and @tdd_expected_fail
that capture bug #11121: _create_sandbox_for_plan() calls
GitWorktreeSandbox.cleanup_stale() unconditionally on every execute invocation,
including when the plan is already in execute/complete state awaiting apply.
Scenario 1 asserts that the cleveragents/plan-<id> branch survives a second call
to _create_sandbox_for_plan() on an execute/complete plan. This assertion fails
because cleanup_stale deletes the branch regardless of plan state.
Scenario 2 asserts that plan apply would find at least one artifact after a
re-invoked execute on an execute/complete plan. This assertion fails because the
branch (holding execute output) was destroyed by cleanup_stale.
Both scenarios use @tdd_expected_fail so CI passes while the bug is unfixed.
The @mock_only tag ensures no database is created for these git-only tests.
The companion fix is tracked in issue #11121.
Additional CI fixes bundled in this commit:
- Fixed PlanGenerationGraph recursion bug: _should_retry() was mutating state
in-place but LangGraph conditional edge functions cannot persist state
mutations. Replaced with a proper _handle_retry() node that increments
retry_count via state returns, resolving the GraphRecursionError that was
crashing the integration tests. Updated the graph to include handle_retry
as the 5th node, routing validate→should_retry→handle_retry→analyze.
- Fixed TDD quality gate (scripts/tdd_quality_gate.py): Renamed @tdd_bug_N
tags to @tdd_issue_N to match the CONTRIBUTING.md specification. Added
_diff_is_tdd_issue_capture() detection so that TDD issue-capture PRs
(which add @tdd_expected_fail rather than remove it) pass the quality gate
correctly. Updated all related tests (Behave unit tests, Robot integration
tests, and test helpers) to use the new tag naming.
ISSUES CLOSED: #11120
Implements ADR-021 §Global CLI Flags and ADR-024 §Resolution Chain.
All three global options were missing from main_callback(), causing any
invocation with these flags to crash with 'No such option'.
Changes:
- src/cleveragents/cli/main.py
* Add _VERBOSITY_LOG_LEVELS tuple mapping verbose count to log levels
(0=CRITICAL/silent, 1=ERROR, 2=WARNING, 3=INFO, 4=DEBUG, 5+=DEBUG)
* Add --data-dir PATH option: validates path is a directory if it exists,
sets CLEVERAGENTS_DATA_DIR env var, resets Settings singleton
* Add --config-path PATH option: validates file exists and is a file,
sets CLEVERAGENTS_CONFIG_PATH env var for ConfigService to pick up
* Add -v (count=True) option: wires verbose count to configure_structlog
* Store all three values in ctx.obj for subcommand access
* Update _print_basic_help() to include the three new global options so
'cleveragents --help' (fast path) also lists them
* In the catch-all Exception handler, print the original exception
type+message directly to err_console so actionable details remain
visible even when log level is CRITICAL (e.g. 'No such option')
- src/cleveragents/application/services/config_service.py
* ConfigService.__init__ now checks CLEVERAGENTS_CONFIG_PATH env var
when no explicit config_path is passed, completing the resolution
chain for --config-path CLI override
Tests (all passing):
- features/cli_global_options.feature (21 Behave scenarios)
- features/steps/cli_global_options_steps.py
- robot/cli_global_options.robot (8 Robot Framework integration tests)
- robot/helper_cli_global_options.py
Quality gates: lint ✓ typecheck ✓ unit_tests ✓ integration_tests ✓
Coverage: 96.52% (threshold 96.5% ✓)
ISSUES CLOSED: #6785
Add an automated quality gate that enforces TDD bug fix workflow rules
on pull requests. The gate parses PR descriptions for bug-closing
keywords (Closes/Fixes/Resolves #N, ISSUES CLOSED: #N), searches the
codebase for corresponding TDD tests tagged @tdd_bug_N, and verifies
that @tdd_expected_fail tags have been removed.
Key components:
- scripts/tdd_quality_gate.py: Main quality gate script with PR
description parsing, TDD test discovery, and tag removal verification.
All public functions validate arguments fail-fast and are statically
typed.
- noxfile.py: New tdd_quality_gate session that reads PR_DESCRIPTION
from the environment and runs the quality gate script.
- .forgejo/workflows/ci.yml: New tdd_quality_gate CI job that runs
only on pull_request events, passing the PR body as PR_DESCRIPTION.
- features/tdd_quality_gate.feature: 46 Behave scenarios covering PR
parsing, TDD test search, tag removal verification, full gate logic,
robot diff handling, edge cases, argument validation, bool guards,
co-located bug false-positive guard, and main() CLI entry point.
- features/steps/tdd_quality_gate_steps.py: Step definitions for all
Behave scenarios using temporary directories for isolation.
- robot/tdd_quality_gate.robot: 15 Robot Framework integration tests
exercising the gate end-to-end via a helper subprocess.
- robot/helper_tdd_quality_gate.py: Helper script for Robot tests with
sentinel-based sub-commands.
Review-round fixes applied:
- check_expected_fail_removed now uses _contains_tag_token for
word-boundary matching (avoids false positives on partial tag names)
- Diff expected-fail removal detection tracks flags at file level
instead of per-hunk (fixes false negatives when tags span hunks)
- parse_bug_refs filters out issue number zero
- Redundant double error reporting eliminated (file-level check
short-circuits the diff-level check)
- run_quality_gate returns (errors, bug_refs) tuple to avoid
redundant re-parsing in main()
- Regex compilation cached via functools.lru_cache
- Nox session no longer installs the full project (stdlib only)
- CI checkout uses fetch-depth: 0 for reliable merge-base resolution
Review-round 2 fixes applied:
- _diff_has_expected_fail_removal_for_bug now requires the removed
line to contain both the expected-fail tag and the specific bug tag
(fixes false positives when two bugs share the same test file)
- check_expected_fail_removed error messages use the correct tag
prefix per file type (@tdd_bug_N for .feature, tdd_bug_N for .robot)
- bool values rejected by bug-number validation guards in
find_tdd_tests, check_expected_fail_removed, and
_diff_has_expected_fail_removal_for_bug
- File-read error handling catches UnicodeDecodeError alongside OSError
(root-safe unreadable-file handling via invalid-UTF-8 test fixture)
- Temp directory cleanup added to after_scenario hook in environment.py
- 8 new Behave scenarios: bool type guards (2), co-located bug
false-positive regression (1), run_quality_gate argument validation
(3), and main() CLI entry point exit codes (2)
Review-round 3 fixes applied:
- Synthetic PR diff helper (_default_pr_diff_for_bug_refs) now
auto-detects .robot vs .feature file type from the temp search
tree and generates the matching diff format (fixes under-tested
robot-format diff code path in multi-bug integration scenarios)
- check_expected_fail_removed test step now filters files by bug
tag via find_tdd_tests before checking (matches production path
in run_quality_gate)
- after_scenario temp directory cleanup no longer sets
context.temp_dir = None (fixes cleanup conflict with
cli_init_yes_flag_steps.py cleanup functions that run after hooks)
- 2 new Behave scenarios: multi-line PR description parsing, and
non-string pr_diff type guard for run_quality_gate
ISSUES CLOSED: #629
Duplicate step definitions for 'the pyproject.toml file exists at',
'I read the project dependencies from pyproject.toml',
'I attempt to import the module', and 'the import should succeed without
errors' were present in both security_pyyaml_dependency_steps.py and
tdd_a2a_sdk_dependency_steps.py, causing a behave.AmbiguousStep error
that failed the unit_tests CI gate.
Removed the 4 duplicate step definitions from security_pyyaml_dependency_steps.py,
keeping only the 3 PyYAML-specific step definitions. The shared steps are
now exclusively provided by tdd_a2a_sdk_dependency_steps.py.
Also resolved merge conflicts from master in CONTRIBUTORS.md: preserved
all master additions (database resource types entry) alongside the existing
PyYAML upgrade entry.
ISSUES CLOSED: #9055
- Move _flatten_toml_dict to module level: eliminates nested function
definition that ruff format reformats unexpectedly; makes the helper
independently testable and clearly documented.
- Rename helper to _flatten_toml_dict (was _flatten) for unambiguous
module-level identity and improved readability.
- Add _PROJECT_ROOT constant computed from __file__ so pyproject.toml
is always resolved via an absolute path regardless of the process
working directory — fixes brittle relative-path lookup that fails
when behave-parallel forks workers whose cwd differs from the repo root.
- Fix ruff format violations: wrap long assert message, normalise
decorator quote style, ensure trailing newline, fix import ordering
(behave imports before packaging).
- All quality gates pass: lint, format --check, security_scan, dead_code.
ISSUES CLOSED: #9055
- Added `pyyaml>=6.0.3` dependency constraint to pyproject.toml after
aiohttp to prevent installation of vulnerable older versions with known
YAML parsing security issues.
- Updated uv.lock package dependencies and requires-dist to include pyyaml
entry with specifier '>=6.0.3'.
- Added changelog Security section entry under [Unreleased] documenting the
upgrade for issue #9055.
- Updated CONTRIBUTORS.md with contribution note (PR #9244).
- Added BDD test scenario verifying PyYAML security dependency constraint.
ISSUES CLOSED: #9055
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
- Actor configuration in V3 is now obtained from the nested configuration parameter, according to the specification.
- Removed the legacy V2 fallback support and the tests affected by that removal. Mocked existing steps to allow remaining V2 features to be covered/tested.
- Fix add() to pass unsafe flag to add_v3() for proper unsafe actor handling
- Add _extract_nested_v3_config() to extract provider/model from nested
actors.<name>.config block before v3 schema validation
- Remove v2 extraction test scenarios from consolidated_actor.feature
that call removed _extract_v2_actor() and _extract_v2_options() methods
- Update test YAML in actor_registry_spec_yaml_steps.py to exercise nested type detection (no top-level type field)
- Add @tdd_issue_4300 regression test tag to existing spec-compliant
actors map scenario
ISSUES CLOSED: #4300
- Remove @tdd_expected_fail from Tree with json format scenario in
plan_explain.feature (bug is now fixed by the envelope implementation)
- Update scenario assertions to verify new spec-required envelope format
instead of old bare-array format
- Add step_tree_json_valid_envelope step definition in plan_explain_steps.py
- Fix ruff format violation in plan_explain_cli_coverage_steps.py
ISSUES CLOSED: #9163
The pr_compliance_pool_supervisor_steps.py file defined @then step texts
identical to those in the pre-existing pr_compliance_checklist_steps.py,
causing Behave's ambiguous-step detection to reject the test run.
Fix: prefix all pool-supervisor @then decorators with 'Pool:' so they're
uniquely identifiable by Behave while reusing the same validator logic.
Also fix PROJECT_ROOT from parents[3] -> parents[2] for correct repo root
resolution in step files located at features/steps/.
ISSUES CLOSED: #9824
Add a new implementation-pool-supervisor agent definition with an embedded
8-item PR Compliance Checklist. Workers dispatched by the pool supervisor
must complete all 8 items before creating any PR: CHANGELOG.md update,
CONTRIBUTORS.md update, commit footer (ISSUES CLOSED: #N), CI verification,
BDD tests, Epic reference, label application via forgejo-label-manager,
and milestone assignment. Includes concrete markdown examples for each
subsection and compliance verification pseudocode.
Also adds BDD test coverage (pr_compliance_pool_supervisor.feature + steps)
to verify the pool supervisor agent definition contains all 8 checklist items.
Parent Epic: #9779
ISSUES CLOSED: #9824
Rebases the TUI prompt symbol fix onto the latest master, resolving
conflicts with the TextArea→Input refactor and the dollar-prefix shell
mode addition. Adds the missing CHANGELOG.md entry for #6431 and
removes the now-obsolete tui_prompt_textarea feature/steps that tested
the old TextArea-based implementation.
ISSUES CLOSED: #6431
Fixes issue #10972 where _path_matches() used PurePath.full_match()/match()
which requires the entire path to match. Since fragment metadata stores
absolute paths (e.g. /app/.opencode/skills/SKILL.md) while project context
--exclude-path/--include-path settings produce relative globs (.opencode/*,
docs/*), include/exclude filters were silently ineffective.
Added _matches_any() static helper in execute_phase_context_assembler.py that:
- Tries full_match(pattern) as-is for relative paths and anchored patterns
- Auto-prefixes relative patterns with **/ so they match absolute paths
Updated _matches_pattern() in context_phase_analysis.py with same logic plus
zero-depth compatibility shim.
Added 7 new BDD regression scenarios with @tdd_issue tags:
- 5 in execute_phase_context_assembler_coverage.feature (absolute path matching)
- 1 extra trailing ** glob exclusion test
- 1 in project_context_phase_analysis.feature (phase analysis exclusion)
ISSUES CLOSED: #10972
CoreRasurae
brent.edwards
hurui200320
hamza.khyari
freemo
HAL9000
HAL9000
