Stop reasons
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-05.)
Stop reasons has 39 facts recorded in Dontopedia across 1 reference, with 4 live disagreements.
Mostly:includes reason(8), includes(4), has reason(4)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (8)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
partOfPart of(4)
- End Turn Stop Reason
ex:end-turn-stop-reason - Max Tokens Stop Reason
ex:max-tokens-stop-reason - Stop Sequence Stop Reason
ex:stop-sequence-stop-reason - Tool Use Stop Reason
ex:tool-use-stop-reason
hasPartHas Part(1)
- Sampling Section
ex:sampling-section
hasSubcomponentHas Subcomponent(1)
- Model Layer
ex:model-layer
hasSubsectionHas Subsection(1)
- Sampling Section
ex:sampling-section
implementsInterfaceImplements Interface(1)
- Sampling Section
ex:sampling-section
Other facts (38)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Includes Reason | End Turn | [1] |
| Includes Reason | Tool Use | [1] |
| Includes Reason | Max Tokens | [1] |
| Includes Reason | Stop Sequence | [1] |
| Includes Reason | End Turn Stop Reason | [1] |
| Includes Reason | Tool Use Stop Reason | [1] |
| Includes Reason | Max Tokens Stop Reason | [1] |
| Includes Reason | Stop Sequence Stop Reason | [1] |
| Includes | End Turn | [1] |
| Includes | Tool Use | [1] |
| Includes | Max Tokens | [1] |
| Includes | Stop Sequence | [1] |
| Has Reason | end_turn | [1] |
| Has Reason | tool_use | [1] |
| Has Reason | max_tokens | [1] |
| Has Reason | stop_sequence | [1] |
| Has Part | End Turn Stop Reason | [1] |
| Has Part | Tool Use Stop Reason | [1] |
| Has Part | Max Tokens Stop Reason | [1] |
| Has Part | Stop Sequence Stop Reason | [1] |
| Rdf:type | Concept | [1] |
| Controls | Sampling | [1] |
| Determines When | Sampling | [1] |
| Reason Count | 4 | [1] |
| Has Reasons | 4 | [1] |
| Has Number of Reasons | 4 | [1] |
| Termination Mechanism | model-layer | [1] |
| Part of | Sampling Section | [1] |
| Has Level | 2 | [1] |
| Has Item Count | 4 | [1] |
| Has Outline Position in Section | 3 | [1] |
| Has Word Count | 7 | [1] |
| Uses Colon to List | true | [1] |
| Uses Comma Separator | true | [1] |
| Item Count | 4 | [1] |
| Depth in Hierarchy | 2 | [1] |
| Contains Phrase | reasons | [1] |
| Phrase Function | causality indicator | [1] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (1)
ctx:discord/blah/agents/6- full textctx:discord/blah/agents/6text/plain1 KB
doc:discord/blah/agents/6Show excerpt
[2026-03-15 03:03] traves_theberge: The key insight: LLM + loop + tools = agent The Agent Loop The core while-loop Code: basic loop skeleton Stop conditions: end_turn, max_iterations, human approval Sampling (The Model Layer) Making API…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.