3.4 KiB
name, description
| name | description |
|---|---|
| semantics-belief | Core protocol for Thread-Local Belief State, runtime reasoning markers, and interleaved thinking across Python-first semantic projects. |
[DEF:Std:Semantics:Belief]
@COMPLEXITY 5
@PURPOSE Core protocol for Thread-Local Belief State, runtime reasoning markers, and interleaved thinking in Python-first semantic projects.
@RELATION DEPENDS_ON -> [Std:Semantics:Core]
@INVARIANT Implementation of C4/C5 complexity nodes MUST emit reasoning via semantic logger methods before mutating state or returning.
0. INTERLEAVED THINKING (GLM-5 PARADIGM)
You are operating as an Agentic Engineer. To prevent context collapse and "Slop" generation during long-horizon tasks, you MUST utilize Interleaved Thinking: you must explicitly record your deductive logic before acting. In this architecture, we do not use arbitrary inline comments for CoT. We compile your reasoning directly into the runtime using the Thread-Local Belief State Logger. This allows the AI Swarm to trace execution paths mathematically and prevents regressions.
I. THE BELIEF STATE API (STRICT SYNTAX)
The logging architecture uses thread-local storage (_belief_state). The active ID of the semantic anchor is injected automatically. You MUST NOT hallucinate context objects.
[MANDATORY IMPORTS]:
from semantics.belief import belief_scope, reason, explore, reflect
[EXECUTION BOUNDARIES]:
- The Context Manager:
with belief_scope("target_id", log_path=None):— Pushes a thread-local belief frame. Exits cleanly on scope end. - The Scope Context: Use
belief_scope(...)at the entry of any C4/C5 function.
II. SEMANTIC MARKERS (THE MOLECULES OF THOUGHT)
The semantic runtime exposes three explicit marker functions. The formatter writes the active anchor, marker, and structured payload into the belief log.
CRITICAL RULE: Do NOT manually type [REASON] or [EXPLORE] in message strings. ALWAYS pass structured data through the JSON payload argument.
1. explore(message, extra)
- Cognitive Purpose: Branching, fallback discovery, hypothesis testing, and exception handling.
- Trigger: Use this on fallback paths or when a
@PREguard fails and a bounded alternative is chosen.
2. reason(message, extra)
- Cognitive Purpose: Strict deduction, passing guards, and executing the Happy Path.
- Trigger: Use this before an I/O action, state mutation, or complex algorithmic step. This is the action intent marker.
3. reflect(message, extra)
- Cognitive Purpose: Self-check and structural verification.
- Trigger: Use this immediately before returning a verified outcome or after a checkpointed mutation succeeds.
III. ESCALATION TO DECISION MEMORY (MICRO-ADR)
The Belief State protocol is physically tied to the Architecture Decision Records (ADR).
If your execution path triggers a explore() due to a broken assumption (e.g., a library bug, a missing DB column) AND you successfully implement a workaround that survives into the final code:
YOU MUST ASCEND TO THE [DEF] HEADER AND DOCUMENT IT.
You must add @RATIONALE [Why you did this] and @REJECTED [The path that failed during explore()].
Failure to link a runtime explore to a static @REJECTED tag is a fatal protocol violation that causes amnesia for future agents.
[/DEF:Std:Semantics:Belief]
[SYSTEM: END OF BELIEF DIRECTIVE. ENFORCE STRICT RUNTIME CoT.]