Skip to content

Context: Practices and Principles

Who is this for (2)

Context: Practices and Principles

Terms describing operating principles for glossary-semantic-integrity execution.

Mostly Invisible Process

DefinitionGlossary checks should run by default with minimal interruption during normal flow.
ContextPractices & Principles
Statuscanonical
Applicable to1.x, 2.x

Highly Visible Outcomes

DefinitionConflict results, block reasons, and clarification decisions must be visible in artifacts/logs.
ContextPractices & Principles
Statuscanonical
Applicable to1.x, 2.x

Append-Only Semantic History

DefinitionTerm/sense changes and conflict decisions are recorded as immutable events, not rewritten in place.
ContextPractices & Principles
Statuscanonical
Applicable to1.x, 2.x

Deterministic Gate, Human Clarification

DefinitionConflict detection/gating is deterministic; only ambiguity resolution requires human input.
ContextPractices & Principles
Statuscanonical
Applicable to1.x, 2.x

High-Severity Block Rule

DefinitionUnder the default medium glossary strictness, generation is blocked only when high-severity semantic conflicts remain unresolved. max strictness blocks on any unresolved conflict and off never blocks (should_block in src/glossary/strictness.py).
ContextPractices & Principles
Statuscanonical
Applicable to1.x, 2.x

Human-in-Charge (Cross-Reference)

DefinitionThe principle that the human remains responsible and accountable for all decisions. Agents assist and propose; the HiC owns the final call. See full definition in Identity context.
ContextPractices & Principles
Statuscanonical
Applicable to1.x, 2.x
Canonical entryHuman-in-Charge (HiC)