Delta OL-03 — Ollama dossier

DELTA OL-03 / Ollama

Streaming layer returns empty content with finish_reason "stop" in place of tool_calls delta chunks — all tool-dependent agent skills fail silently

openopened 2026-04

Description

Re-checked 2026-06-11: vendor docs now document tool calling with streaming, and the closest upstream issue (#16212) was closed "completed" the same day it was filed after its reporter marked it opened in error. Both are re-verification triggers, not closures (DC-2); no TD re-verification yet.

UPDATE 2026-06-28: root cause confirmed open via #15497 (HTTP 200); PR #15467 patched only 8 models; MLX manifestation #16279 open; bug is path-specific (/v1 drops deltas, /api/chat preserves).
UPDATE 2026-07-17: #15497 and #16279 both still open, no merged fix; v0.32.1 release notes list Gemma 4 tool-calling and MLX cache-leak fixes only, nothing addressing the legacy-parser index bug or MLX streaming buffering.

Closes when

An agent receives tool_calls delta chunks (correct incrementing indices, finish_reason "tool_calls") over a streaming response in default configuration, with no stream:false workaround — TD re-verified on a current release

Evidence

[1][2][3][4][5]Re-verified open 2026-06-28 against v0.30.11Re-verified open 2026-07-17 against v0.32.1 — #15497 and #16279 remain open, unmerged