Files
ss-tools/backend/src/models/assistant.py
busya 8e8a3c3235 feat: attention-optimized semantic protocol v2.7
Core changes:
- Add @defgroup/@ingroup to 1791 C2+ contracts (555 files) for HCA 128× pre-training DSA grouping
- Add §0.1 Pre-Training Frequency matrix to semantics-core
- Add §VIII Attention Architecture rules (ATTN_1-4) with MLA/CSA/HCA/DSA mechanics
- Add @defgroup/@ingroup to canonical syntax (§II) and all contract examples

Agent prompts (5 files):
- Add ZERO-STATE RATIONALE with MLA/CSA/HCA/DSA compression mechanics
- Add pre-training note: @RATIONALE/@REJECTED are in-context learned tags
- svelte-coder: add missing #region contract, fix Svelte rule violations
- python-coder/fullstack-coder: honor function contracts from speckit plan
- qa-tester: add attention compliance audit (P3 ATTN_1-4 checks)

Skills (6 files):
- Translate all axiom_config descriptions to English
- Fix doc_dirs to index .opencode/ and .specify/
- Deduplicate 5× complexity_rules → single global_tags catalog
- Reduce semantics-svelte 591→485 lines (remove duplicate code blocks)
- Fix semantics-testing: 'Short IDs' → 'Short hierarchical IDs'
- Fix all examples: flat IDs → hierarchical Domain.Name format
- Fix Svelte examples: replace raw Tailwind + <button> with semantic tokens + /ui

Speckit workflow (commands + templates):
- speckit.plan: add Function-Level Contracts for C3+ with @PRE/@POST/@TEST_EDGE
- speckit.plan: add Attention Compliance Gate (ATTN_1-4 before contract generation)
- speckit.tasks: add function contract inlining format (constraints in task description)
- speckit.specify: load semantics-core for spec density rules
- spec-template: add #region contract, @SEMANTICS grouping, hierarchical IDs
- ux-reference-template: add #region wrapper
- plan-template: add attention gate, @defgroup/@ingroup guidance
- tasks-template: add attention audit + rebuild + orphan check tasks
- constitution.md: translate to English, add Principle VIII (attention-optimized contracts)

Reference modules rewritten (hierarchical IDs + full contracts):
- Auth.Jwt: 6 child contracts with @RATIONALE/@REJECTED/@TEST_EDGE
- Api.Auth: 5 endpoints with @TEST_EDGE + molecular CoT markers
- Migration.Model: @defgroup Migration with 18 @ACTION + 6 @INVARIANT

Scripts:
- add_defgroup_ingroup.py: zero-risk additive @ingroup migration (1791 insertions)
- migrate_hierarchical.py: flat→hierarchical ID dry-run analysis (792 contracts)
- merge_prompts.py: merge all prompts/skills/commands into one review file

Config:
- axiom_config.yaml: 749→395 lines (-47%), English, doc_dirs include prompts
- Fix test_datasets.py import collision (rename → test_datasets_routes.py)
- Fix test_preview.py: SupersetClient→get_superset_client, AsyncMock, logger f-string
2026-06-08 16:30:59 +03:00

85 lines
3.4 KiB
Python

# #region AssistantModels [C:3] [TYPE Module] [SEMANTICS sqlalchemy, assistant, model, schema, audit, assistant-audit-record]
# @defgroup Models Module group.
# @BRIEF SQLAlchemy models for assistant audit trail and confirmation tokens.
# @LAYER Domain
# @RELATION DEPENDS_ON -> MappingModels
# @INVARIANT Assistant records preserve immutable ids and creation timestamps.
# @SIDE_EFFECT Defines assistant audit/message/confirmation tables
# @DATA_CONTRACT AssistantData -> AssistantRecord
from datetime import UTC, datetime
from sqlalchemy import JSON, Column, DateTime, String, Text
from .mapping import Base
# #region AssistantAuditRecord [C:3] [TYPE Class]
# @defgroup Models Module group.
# @BRIEF Store audit decisions and outcomes produced by assistant command handling.
# @RELATION INHERITS -> MappingModels
# @PRE user_id must identify the actor for every record.
# @POST Audit payload remains available for compliance and debugging.
class AssistantAuditRecord(Base):
__tablename__ = "assistant_audit"
id = Column(String, primary_key=True)
user_id = Column(String, index=True, nullable=False)
conversation_id = Column(String, index=True, nullable=True)
decision = Column(String, nullable=True)
task_id = Column(String, nullable=True)
message = Column(Text, nullable=True)
payload = Column(JSON, nullable=True)
created_at = Column(DateTime, default=lambda: datetime.now(UTC), nullable=False)
# #endregion AssistantAuditRecord
# #region AssistantMessageRecord [C:3] [TYPE Class]
# @defgroup Models Module group.
# @BRIEF Persist chat history entries for assistant conversations.
# @RELATION INHERITS -> MappingModels
# @PRE user_id, conversation_id, role and text must be present.
# @POST Message row can be queried in chronological order.
class AssistantMessageRecord(Base):
__tablename__ = "assistant_messages"
id = Column(String, primary_key=True)
user_id = Column(String, index=True, nullable=False)
conversation_id = Column(String, index=True, nullable=False)
role = Column(String, nullable=False) # user | assistant
text = Column(Text, nullable=False)
state = Column(String, nullable=True)
task_id = Column(String, nullable=True)
confirmation_id = Column(String, nullable=True)
payload = Column(JSON, nullable=True)
created_at = Column(DateTime, default=lambda: datetime.now(UTC), nullable=False)
# #endregion AssistantMessageRecord
# #region AssistantConfirmationRecord [C:3] [TYPE Class]
# @defgroup Models Module group.
# @BRIEF Persist risky operation confirmation tokens with lifecycle state.
# @RELATION INHERITS -> MappingModels
# @PRE intent/dispatch and expiry timestamp must be provided.
# @POST State transitions can be tracked and audited.
class AssistantConfirmationRecord(Base):
__tablename__ = "assistant_confirmations"
id = Column(String, primary_key=True)
user_id = Column(String, index=True, nullable=False)
conversation_id = Column(String, index=True, nullable=False)
state = Column(String, index=True, nullable=False, default="pending")
intent = Column(JSON, nullable=False)
dispatch = Column(JSON, nullable=False)
expires_at = Column(DateTime, nullable=False)
created_at = Column(DateTime, default=lambda: datetime.now(UTC), nullable=False)
consumed_at = Column(DateTime, nullable=True)
# #endregion AssistantConfirmationRecord
# #endregion AssistantModels