.forgejo/workflows/ci.yml

@@ -209,6 +209,7 @@ jobs:
                   path: build/nox-quality-output.log
                   retention-days: 30
 
+        timeout-minutes: 30
     unit_tests:
         runs-on: docker
         container:
@@ -282,6 +283,7 @@ jobs:
                   path: build/nox-unit-tests-output.log
                   retention-days: 30
 
+        timeout-minutes: 45
     integration_tests:
         runs-on: docker
         container:

CHANGELOG.md

@@ -198,6 +198,25 @@ ensuring data is stored with proper parameter values.
   LLM streaming output. A `SessionActorNotConfiguredError` is raised with exit
   code 1 when no actor is configured.
 
+
+### Added
+
+- **ContextStrategy Protocol and Plugin Registration System** (#10590): Implemented the
+  ``ContextStrategy`` protocol for pluggable context assembly strategies within the ACMS.
+  Includes six built-in strategy implementations: ``SimpleKeywordStrategy`` (keyword matching,
+  quality 0.3), ``SemanticEmbeddingStrategy`` (word-overlap similarity search, quality 0.6),
+  ``BreadthDepthNavigatorStrategy`` (UKO hierarchy traversal with depth/breadth projection,
+  quality 0.85), ``ARCEStrategy`` (multi-modal pipeline combining text/vector/graph backends,
+  quality 0.95), ``TemporalArchaeologyStrategy`` (historical pattern discovery from cold-tier data,
+  quality 0.5), and ``PlanDecisionContextStrategy`` (ancestor plan decision retrieval, quality 0.7).
+  The ``StrategyRegistry`` provides thread-safe registration, enable/disable configuration,
+  per-strategy timeout/fragment limits, circuit-breaker tracking, validation warnings, and plugin
+  discovery from ``"module:ClassName"`` strings with a module-prefix allowlist for security.
+  Seventy-seven (77) Behave scenarios cover strategy selection by confidence scoring, backend
+  capability matching, duplicate registration rejection, stale enabled-list detection,
+  MappingProxyType coercion validators, thread-safety under concurrent access, boundary value
+  validation via Pydantic model constraints, and per-strategy config updates.
+
 ### Added
 
 - **Automated CLI Docstring Example Validation** (#9106): Added `DocstringExampleValidator`
@@ -252,8 +271,6 @@ ensuring data is stored with proper parameter values.
   traceback in the structlog warning entry. Removed `@tdd_expected_fail` tag
   from the TDD test so both scenarios run as normal regression guards. (#988)
 
-### Added
-
 - **`pr-review-worker` review-started notification** (#11028): The `first_review`
   and `re_review` modes now post a "review started" notification comment to the
   PR at the beginning of the review, giving PR authors immediate visibility

CONTRIBUTORS.md

@@ -46,6 +46,9 @@ Below are some of the specific details of various contributions.
 * HAL 9000 has contributed the PureGraph BDD coverage suite (PR #9601 / issue #9531): wired the previously orphaned `features/steps/pure_graph_coverage_steps.py` definitions through the existing `features/consolidated_langgraph.feature` (topological ordering, function execution, missing function fallback, and non-functional node handling); created Robot Framework integration tests in `robot/langgraph/pure_graph.robot` backed by the `robot/langgraph/pure_graph_lib.py` Python library; and implemented ASV benchmarks in `benchmarks/pure_graph_bench.py` measuring execution throughput across varying node counts.
 * HAL 9000 has contributed comprehensive milestone documentation for v3.2.0 (Decisions + Validations + Invariants) and v3.3.0 (Corrections + Subplans + Checkpoints), including CLI command reference, decision system guide, and subplan/checkpoint documentation (PR #9796).
 * Rui Hu has contributed the v3 actor YAML schema validation fix (#5869): added `ActorConfigSchema` validation to the `agents actor add --config` CLI command, covering cycle detection, required field validation, and enum validation for v3 YAML actor definitions.
+* HAL 9000 has contributed the agent-evolution-pool-supervisor PR metadata assignment (#7888): the supervisor now automatically looks up the Type/Automation label and earliest open milestone before dispatching improvement PR creation workers, ensuring all generated improvement PRs have correct Type labels and milestone assignments.
+* HAL 9000 has contributed the decision recording hook for the Strategize phase (issue #8522): captures every decision point with question, chosen option, alternatives, confidence, rationale, and full context snapshot for replay and correction.
+* HAL 9000 has contributed the ContextStrategy protocol and StrategyRegistry plugin registration system (PR #10590 / issue #8616): implemented the pluggable context assembly strategy protocol with proper type-safe method signatures, created the central thread-safe StrategyRegistry supporting registration, lookup, entry-point discovery, and per-strategy configuration (timeout, fragments limits, workers, circuit breaker threshold). Six built-in strategies implemented and documented: simple-keyword, semantic-embedding, breadth-depth-navigator, arce, temporal-archaeology, and plan-decision-context. Full BDD test coverage including thread safety, boundary validation, and error handling tests. (Part of Epic #8505)
 * This project was made possible thanks to considerable donation of time, money, and resources by CleverThis, Inc.
 * HAL 9000 has contributed automated bug fixes, CLI output formatting improvements, and ongoing maintenance as part of the CleverAgents automation system.
 * HAL 9000 has contributed the pr-review-pool-supervisor tracking prefix documentation fix (#7891): aligned all documentation references from the outdated `AUTO-REV-POOL` prefix to the correct `AUTO-REV-SUP` prefix used in production.

src/cleveragents/application/services/acms_service.py

@@ -111,13 +111,27 @@ logger = structlog.get_logger(__name__)
 
 
 # ---------------------------------------------------------------------------
-# Strategy capabilities (spec ~line 25167)
+# StrategyCapabilities — pipeline-specific variant (backward-compatible)
 # ---------------------------------------------------------------------------
+# The domain-model ``StrategyCapabilities`` in
+# ``domain/models/acms/strategy.py`` declares backend-usage flags
+# (uses_text, uses_vector, uses_graph, etc.).  ACMSPipeline uses a
+# simpler dataclass for its internal strategy selectors.  Both are
+# re-exported here for backward compatibility; the pipeline-specific
+# variant is used only by :class:`RelevanceStrategy`,
+# :class:`RecencyStrategy`, :class:`TieredStrategy`, and
+# :class:`SpecStrategyAdapter`.
 
 
 @dataclass(frozen=True)
 class StrategyCapabilities:
-    """Capabilities declared by a context strategy."""
+    """Pipeline-specific capabilities declared by a context strategy.
+
+    This is a backward-compatible variant of the domain-model
+    ``~cleveragents.domain.models.acms.strategy.DomainStrategyCapabilities``.
+    For production strategies that implement the true spec protocol, use
+    ``DomainStrategyCapabilities`` instead.
+    """
 
     supports_semantic_search: bool = False
     supports_graph_navigation: bool = False
@@ -127,18 +141,33 @@ class StrategyCapabilities:
 
 
 # ---------------------------------------------------------------------------
-# Context strategy protocol (spec ~line 25167)
+# ContextStrategy — pipeline-compatible protocol for ACMSPipeline
 # ---------------------------------------------------------------------------
+# The domain-model ``ContextStrategy`` Protocol in
+# ``domain/models/acms/strategy.py`` uses the full spec signature
+# ``can_handle(request, backends) -> confidence`` /
+# ``assemble(request, backends, budget, plan_context) -> fragments``.
+# ACMSPipeline's internal strategies (Relevance, Recency, Tiered) and
+# the SpecStrategyAdapter use a simpler pipeline-compatible Protocol
+# because they operate on pre-fetched fragments rather than querying
+# backends directly.  SpecStrategyAdapter bridges between the two.
+# When issue #3491 resolves protocol consolidation, this local Protocol
+# can be replaced with ``DomainContextStrategy`` from
+# ``cleveragents.domain.models.acms.strategy``.
 
 
 @runtime_checkable
 class ContextStrategy(Protocol):
-    """Protocol for context strategies.
+    """Pipeline-compatible Protocol for context strategies.
 
-    Based on ``docs/specification.md`` ~line 25167.  Each strategy declares
-    a ``name`` and ``capabilities``, can report its confidence for a request
-    via ``can_handle``, produce fragments via ``assemble``, and explain its
-    approach via ``explain``.
+    ACMSPipeline's internal strategies (Relevance, Recency, Tiered) and
+    the SpecStrategyAdapter implement this interface.  The domain-model
+    ``DomainContextStrategy`` uses a different signature that queries
+    backends directly during :meth:`assemble`.  SpecStrategyAdapter bridges
+    between the two by ranking pre-fetched fragments by relevance score.
+
+    When issue #3491 is resolved, this Protocol can be removed in favour of
+    ``DomainContextStrategy`` from ``cleveragents.domain.models.acms.strategy``.
     """
 
     @property