mirror of
https://github.com/semantica-agi/semantica.git
synced 2026-09-12 04:01:35 +00:00
e2fc76cea067b8bee8fb88674ccd40f79badab5d
9
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Shinde vinayak rao patil
|
d94d8f6ab8 |
Feat/crewai integration (#988)
* feat(crewai): add first-class CrewAI integration (#962) Add native CrewAI support so Crew agents can share a ContextGraph and AgentContext via BaseTool subclasses and a BaseKnowledgeSource, matching the existing agno integration pattern. - SemanticaKGTool: 5 KG actions (extract_entities, extract_relations, add_to_graph, query_graph, find_related) with sync run()/async arun() - SemanticaDecisionTool: 5 decision-intelligence actions (record_decision, find_precedents, trace_causal_chain, analyze_impact, check_policy) over AgentContext - SemanticaKnowledgeSource: serializes a ContextGraph into crew knowledge storage; bridges legacy load_content() and current validate_content()/aadd() contracts for crewai>=0.80.0 - All classes degrade gracefully when crewai is absent - New pip extra crewai=... included in the all bundle - 70 new tests (stub-based present-case + subprocess degradation path) - Docs: integrations/crewai.md, docs.json nav, README matrix updates * fix(crewai): harden tools against real Semantica dataclass shapes (#962) Bugs found during live testing with crewai 1.15.16: - SemanticaKGTool.add_to_graph crashed on real Entity/Relation dataclasses ('str' object has no attribute 'end_char'): string names were passed to extract_relations(entities=...), which requires Entity objects, and the tool read .name/.source/.target instead of Entity's .text/.label and Relation's .subject/.object. Add shape-agnostic field helpers. - SemanticaDecisionTool() created an AgentContext without a knowledge_graph, so _decision_backend was never set and record_decision raised 'Decision tracking is not enabled'. Wire in a ContextGraph. - record_decision hard-failed when the agent omitted optional fields; fall back to category='general', reasoning='agent decision', outcome='recorded'. Add tests covering real Entity/Relation dataclass shapes and the live auto-created AgentContext path (now 77 crewai tests, 212 total). * fix(crewai): make find_related traverse edges undirected (#962) ContextGraph.get_neighbors only follows outgoing edges, so a node whose only edge is incoming (A -> B) reported no related concepts. Rebuild a bidirectional adjacency from find_edges() in SemanticaKGTool._find_related so 'related' honors both directions. * fix(crewai): harden tools for checkpoint serialization and correct action semantics (#962) - Exclude live graph/context/extractor state from JSON serialization (model_dump(mode="json")) so CrewAI checkpointing no longer raises PydanticSerializationError; model_post_init self-heals defaults on restore - query_graph now searches node content via graph.query() plus id/type - trace_causal_chain returns an explicit error when causal tracing is unavailable instead of substituting similarity precedents; call trace_decision_causality(..., max_depth=...) with the correct kwarg name - find_precedents propagates max_precedents/limit to the backend instead of being silently capped at 10 - Serialize add_to_graph batches under a module lock to prevent concurrent double-counting; skip nameless entities instead of creating repr()-junk nodes - aadd() runs CPU-bound serialization in a thread executor - Mirror crewai args_schema serialize/restore in the conftest stub and add serialization regression tests (crewai: 92 tests) * fix(crewai): correct check_policy coercion, guard causal tracing, and harden concurrency (#962) - _eval_rule now coerces rule values type-aware: bool("false") was truthy, so 'enabled == false' reported a violation for enabled=false, and string datums like "0.90" were compared lexicographically instead of numerically - _trace_causal_chain no longer raises AttributeError (which escaped _run) when the decision context lacks knowledge_graph; returns honest error JSON - SemanticaKnowledgeSource storage failures log an actionable ERROR; without a configured crew embedder agents previously retrieved nothing silently - add_to_graph uses a per-graph re-entrant lock (WeakKeyDictionary) instead of a process-global one: independent graphs no longer serialize each other and re-entrant extractor callbacks cannot deadlock - entity/relation confidence=None normalizes to 1.0 instead of failing the whole extraction with float(None) - add subprocess integration test against real crewai covering Crew-level serialization round-trip and checkpoint restore (stub tests cannot see it) - docs: embedder requirement for SemanticaKnowledgeSource; resume contract note * fix(crewai): surface knowledge-source save failures at ERROR when storage is wired (#962) Re-verification against real crewai showed the embedder-missing failure raises ValueError even though storage IS wired, so the old except-ValueError branch mislabeled it as 'storage not wired' and logged DEBUG — hiding the failure. Distinguish by storage presence instead of exception type: storage is None -> DEBUG keep-in-memory (legitimate standalone use); storage wired but save() raises -> actionable ERROR. Add regression test mirroring real crewai's ValueError-on-missing-embedder behavior. * fix(crewai): expose run()/arun() entry points in degraded mode (#962) The public crewai contract is run()/arun(); without crewai installed they were missing (only the private _run existed), so the documented 'usable without crewai' path raised AttributeError at the entry point. Define them in degraded mode only, leaving crewai's BaseTool implementations untouched when present. Extend the degradation subprocess test to exercise run() and arun(). * fix(crewai): standardize query shape, field-name rules, and restore-state flag - _query_graph: id/type matches now return the same schema as content matches (id/type/label/content/score) instead of a bare list - _eval_rule: non-greedy field capture so hyphen/dot/space JSON keys (e.g. "risk-score >= 0.9") are addressable in policy rules - add had_live_state/reconstructed_state so checkpoint-restored tools and knowledge sources signal that their live graph/context was lost and an empty one reconstructed; knowledge source no longer hides the loss by eagerly rebuilding its graph inside __init__ (pydantic calls __init__ during model_validate) * fix(crewai): address Qodo review — confidence errors, string trim, holistic availability - record_decision: stop calling float() in _run, so malformed confidence values surface as JSON errors (via _record_decision's handling) instead of crashing the tool - _coerce_value: return the stripped string for non-numeric literals so whitespace-padded decision_data fields match policy rules - centralize crewai availability in _availability.py so the exported CREWAI_AVAILABLE flag is holistic across tools and knowledge source (previously each module probed crewai independently and the package flag came from decision_tool only) * ci: regenerate requirements-ci.txt for the crewai extra The crewai extra in pyproject.toml brings in crewai, crewai-tools and transitive deps (chromadb, lancedb, ...). Recompile with uv==0.12.1 per CONTRIBUTING.md so the CI staleness check passes. * ci: keep crewai out of the locked CI dependency set crewai (all versions) hard-requires chromadb~=1.1.0, which carries a pre-authentication code-injection advisory (CVE-2026-45829 / GHSA-f4j7-r4q5-qw2c) with NO fixed release — even the latest 1.5.9 is affected. Keeping crewai in the 'all' extra failed pip-audit and the safety check on requirements-ci.txt. - drop crewai from the 'all' aggregate (standalone semantica[crewai] extra is unchanged and still installs crewai) - stop listing crewai-tools in the extra: the integration only uses crewai core (BaseTool, BaseKnowledgeSource) and crewai-tools pulled extra transitive deps - regenerate requirements-ci.txt: OSV/pip-audit 0 vulnerabilities, safety 0 vulnerabilities, staleness check matches * docs(crewai): document crewai extra scope and chromadb CVE-2026-45829 - CHANGELOG: extra is crewai>=0.80.0 only (no crewai-tools) and is not part of the 'all' bundle, with the chromadb CVE-2026-45829 reason - integrations/crewai/README.md: add a security warning that installing the extra pulls chromadb~=1.1.0, which is affected by the unpatched pre-auth code-injection CVE-2026-45829 --------- |
||
|
Sameer KadamandKaifAhmad1
|
76edaeb1c0 |
fix(agno): make _eval_rule raise instead of silently returning compliant=True on unevaluable rules (closes #778) (#822)
* fix(agno): surface unevaluable policy rules (#778) * fix(agno): fixed qodo reviews check_policy previously let unevaluable policy rules silently return compliant=True with no signal (issue #778): a rule referencing a field missing from decision_data, or a rule string not matching the expected <field> <op> <value> format, both fell through _eval_rule's `return True` and were treated as passed. Both now raise ValueError, which routes through check_policy's existing exception handler and surfaces as a `warnings` entry instead. compliant/ violations semantics are unchanged for every case that previously worked correctly; an unevaluable rule is not counted as a violation since it's genuinely unknown whether it would have passed. Follow-up fixes from code review: - policy_rules decoded via json.loads without checking it was a list; a JSON-encoded bare string decoded to a Python str, so iterating it evaluated one "rule" per character, amplifying a single input-shape mistake into a wall of per-character warnings. A decoded string is now treated as a single rule; any other non-list shape or non-string list element produces exactly one warning instead. - _eval_rule used `data.get(field) is None` to detect a missing field, which can't distinguish an absent key from a key present with JSON null - both produced the same "undefined field" warning. Field presence is now checked with `field not in data` first, and a present-but-null value gets its own distinct message. Added regression tests for all of the above in tests/integrations/agno/test_decision_kit.py (38 tests in the file, 128 passing across tests/integrations/agno/). * fix(agno): reject non-object decision_data in check_policy check_policy only validated that decision_data was well-formed JSON, not that it decoded to an object. When it decoded to a list, `field not in data` in _eval_rule silently became list-membership testing of values instead of a dict key check - e.g. "confidence" not in ["confidence", 0.95] evaluates to False - so a matching rule fell through to data["confidence"], raising a raw internal TypeError ("list indices must be integers or slices, not str") instead of any meaningful diagnostic. Numbers, strings, and bools produced similarly opaque TypeErrors deep inside _eval_rule. check_policy now checks isinstance(data, dict) right after decoding and rejects any other shape with a single clear violations entry, the same way it already rejects malformed JSON. Added 5 regression tests in tests/integrations/agno/test_decision_kit.py covering list/number/string/bool/null decision_data shapes (43 tests in the file, 133 passing across tests/integrations/agno/). Addresses Copilot PR review comment on the #778 fix branch. * docs(changelog): reference PR #822 in the check_policy changelog entry --------- Co-authored-by: KaifAhmad1 <kaifahmad087@gmail.com> |
||
|
Sameer6305
|
aa58b46d4d | Merge semantica-agi/main into fix/779-record-decision-logging | ||
|
Sameer6305
|
d21e5e9944 | fix(agno): log decision tracking failures in shared context - #779 | ||
|
Sameer6305
|
66be1630fa | fix(agno): fail fast on toolkit registration failures - #780 | ||
|
Mohd KaifandCopilot Autofix powered by AI
|
c77690129d |
Potential fix for pull request finding 'Imprecise assert'
Co-authored-by: Copilot Autofix powered by AI <223894421+github-code-quality[bot]@users.noreply.github.com> |
||
|
KaifAhmad1andClaude Sonnet 4.6
|
655a24b77e |
fix: correct three test failures in unreleased changelog test suite
- Remove orphaned unclosed parenthesis (syntax error) in test_unreleased_changelog_comprehensive.py (OllamaProvider block) - Fix test_invalid_json_returns_error to assert compliant=False and non-empty violations instead of missing "error" key — aligns with check_policy() return schema - Fix test_as_of_filters_future_decisions to extract scenario via p["decision"]["scenario"] (correct nesting) and pass similarity_threshold=0.0 so word-overlap doesn't filter out Bob's decision below the 0.5 default Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
KaifAhmad1andClaude Sonnet 4.6
|
b2a2d24b14 |
fix: address all Qodo code review issues in Agno integration
Package & distribution - pyproject.toml: add integrations* to packages.find include so pip install semantica[agno] ships the integration context_store.py - upsert_memory(): run NERExtractor after store() to index entities into the ContextGraph - delete_memory() / drop_table() / clear(): call AgentContext.forget() to propagate deletions to vector/graph storage - find_precedents(): pass limit parameter to find_precedents_advanced() - retrieve(): pass limit as max_results to AgentContext.retrieve() - add get_context_for_prompt() for automatic system-prompt injection knowledge_graph.py - __init__: wire graph_builder.graph_store = self._graph so build() persists into the ContextGraph - add internal AgentContext for vector retrieval (shared ContextGraph) - search(): use AgentContext.retrieve() for vector similarity; keyword scoring as fallback - _ingest_text(): add paragraph-level chunking before NER/relation extraction (parse → split → NER → relation extract → graph build) - get_graph_context(): return structured subgraph with edge types via ContextGraph.get_neighbors() - load_urls(): validate scheme (http/https only) to prevent SSRF decision_kit.py - check_policy(): replace broken PolicyEngine.check_compliance() call with inline _eval_rule() that evaluates simple field-op-value rules; return compliant=False (not True) on failure — closes security bug kg_toolkit.py - add_to_graph(): fix add_node(node_id=, node_type=) and add_edge(source_id=, target_id=, edge_type=) to match real API - query_graph(): use find_nodes() (no label param) + keyword filter - find_related(): use get_neighbors(node_id=) returning List[Dict] - infer_facts() / export_subgraph(): use find_nodes() public API instead of private _nodes dict shared_context.py - _AgentScopedStore: store shared context as self._context (not self._ctx) so all inherited AgnoContextStore methods work correctly tests/integrations/agno/test_kg_toolkit.py - _FakeGraph: rewrite to match real ContextGraph signatures — find_nodes(node_type=), add_node(node_id, node_type, **), add_edge(source_id, target_id, edge_type, **), get_neighbors(node_id, hops=1, ...) returning List[Dict] Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
KaifAhmad1andClaude Sonnet 4.6
|
62c7970b32 |
feat(integrations): add Agno agentic framework integration (#249)
Implements the full Semantica × Agno integration stack as described in issue #249, wiring Semantica's semantic intelligence layer into Agno's agent/team primitives via five focused components. ## New components ### integrations/agno/ - `AgnoContextStore` — graph-backed MemoryDb (AgentMemory/storage) - `AgnoKnowledgeGraph` — relational AgentKnowledge with multi-hop GraphRAG - `AgnoDecisionKit` — Agno Toolkit: 6 decision-intelligence tools - `AgnoKGToolkit` — Agno Toolkit: 7 knowledge-graph tools - `AgnoSharedContext` — team-level shared ContextGraph with role scoping ### tests/integrations/agno/ - 110 tests, 0 failures - conftest.py installs comprehensive agno stubs for offline testing - Covers MemoryDb protocol, tool registration, shared memory pool, thread-safety, GraphRAG search, NER/relation extraction, and inference ### cookbook/integrations/ - agno_decision_intelligence.ipynb (finance/loan underwriting) - agno_graphrag_context.ipynb (regulatory compliance GraphRAG) - agno_multi_agent_shared_context.ipynb (multi-agent product strategy team) ### docs/integrations/agno.md - Full reference documentation with examples for all 5 components ## pyproject.toml - Added `agno = ["agno>=1.0.0"]` optional dependency - Added agno to the `all` extra ## Design notes - Zero breaking changes — fully additive - Graceful degradation when agno is not installed - Auto-creates VectorStore(backend="faiss") when none provided - _tools always populated for inspection regardless of agno install state - Works with both real agno package and offline stubs Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> |