Ticket graphs

Every ticket as the root of its provenance graph — goal, patch, approval, runs and (as the ticket-class build lands) mandate, manifestations, guarantees, journey, artifacts and children. Rendered through the <<<TicketGraphList>>> tag.

← all ticket-graphs

REQUESTED#175 jazz-agents

Research: Ollama tool-calling / structured-output reliability for Gemma 3 & Qwen2.5-Coder (MAKE-OR-BREAK)

goal

The whole design depends on agents emitting STRUCTURED outputs (dispatch plans, verdicts, work-done envelopes) and TOOL CALLS reliably — local models are weaker at this than Claude. Empirically measure, via Ollama /api/chat tools: how often gemma3 and qwen2.5-coder emit valid tool calls / parseable JSON on our exact schemas across N trials, with vs without few-shot examples and format=json / grammar constraints. This GATES the design: if reliability is too low, we need constrained decoding (GBNF grammars) or a validate-and-retry wrapper. OUTPUT: reliability numbers per model/schema + the required mitigation to hit a usable threshold. Spawns a build ticket.

patch

none

approval

unapproved

runs

no runs recorded

mandate (clauses)

not yet recorded — lands with the ticket-class build

manifestations

not yet recorded — lands with the ticket-class build

guarantees

not yet recorded — lands with the ticket-class build

journey (blunders & successes)

not yet recorded — lands with the ticket-class build

artifacts (forge)

not yet recorded — lands with the ticket-class build

source (forge tree)

browse congruency source (forge-parked tree)

children

#176 Build: Ollama agent adapter — drop-in replacement for `claude -p` in pair_loop (spawned · DONE)