Devon Rifkin bf2a421727 gemma4: restore e2b-style nothink prompt (#15560) ... Gemma 4 prompts differ when thinking is disabled for different sized models: 26b/31b emit an empty thought block, while e2b/e4b do not. Before #15490, our shared Gemma 4 renderer effectively matched the e2b behavior. #15490 changed it to always emit the empty thought block, which regressed e2b/e4b nothink behavior and led to #15536 (and possibly This change restores the previous shared behavior by removing the empty trailing thought block. It also renames the checked-in upstream chat templates so the e2b and 31b fixtures are tracked separately. A follow-up will split Gemma 4 rendering by model size. Fixes: #15536		2026-04-13 14:26:15 -07:00
..
testdata	gemma4: restore e2b-style nothink prompt (#15560)	2026-04-13 14:26:15 -07:00
cogito.go	Renderer for Cogito v2 (#13139)	2025-11-18 19:06:34 -08:00
cogito_test.go	preserve tool definition and call JSON ordering (#13525)	2026-01-05 18:03:36 -08:00
deepseek3.go	DeepseekV3 Family Parser (#13484)	2025-12-16 18:56:30 -08:00
deepseek3_test.go	preserve tool definition and call JSON ordering (#13525)	2026-01-05 18:03:36 -08:00
functiongemma.go	preserve tool definition and call JSON ordering (#13525)	2026-01-05 18:03:36 -08:00
functiongemma_test.go	preserve tool definition and call JSON ordering (#13525)	2026-01-05 18:03:36 -08:00
gemma4.go	gemma4: restore e2b-style nothink prompt (#15560)	2026-04-13 14:26:15 -07:00
gemma4_reference_test.go	gemma4: restore e2b-style nothink prompt (#15560)	2026-04-13 14:26:15 -07:00
glm46.go	model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)	2026-01-19 12:47:17 -08:00
glm46_test.go	model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)	2026-01-19 12:47:17 -08:00
glm47.go	model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)	2026-01-19 12:47:17 -08:00
glm47_test.go	model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)	2026-01-19 12:47:17 -08:00
glmocr.go	model/renderers: fix glm-ocr image tags in renderer prompts (#14584)	2026-03-03 12:51:34 -08:00
glmocr_test.go	model/renderers: fix glm-ocr image tags in renderer prompts (#14584)	2026-03-03 12:51:34 -08:00
json.go	parsers/renderers: olmo3 think (#13290)	2025-12-09 10:41:47 -08:00
json_test.go	parsers/renderers: olmo3 think (#13290)	2025-12-09 10:41:47 -08:00
lfm2.go	model: support for qwen3.5 architecture (#14378)	2026-02-24 20:08:05 -08:00
lfm2_test.go	model: support for qwen3.5 architecture (#14378)	2026-02-24 20:08:05 -08:00
nemotron3nano.go	preserve tool definition and call JSON ordering (#13525)	2026-01-05 18:03:36 -08:00
nemotron3nano_test.go	preserve tool definition and call JSON ordering (#13525)	2026-01-05 18:03:36 -08:00
olmo3.go	preserve tool definition and call JSON ordering (#13525)	2026-01-05 18:03:36 -08:00
olmo3_test.go	olmo3: fix flaky test (#13629)	2026-01-05 22:37:20 -08:00
olmo3_think.go	renderers: add olmo3.1 and olmo3 fixes (#13447)	2025-12-15 11:26:43 -08:00
olmo3_think_test.go	preserve tool definition and call JSON ordering (#13525)	2026-01-05 18:03:36 -08:00
qwen3coder.go	model: add qwen3-next architecture (#14051)	2026-02-03 23:27:21 -08:00
qwen3coder_test.go	model: add qwen3-next architecture (#14051)	2026-02-03 23:27:21 -08:00
qwen3vl.go	model: support for qwen3.5 architecture (#14378)	2026-02-24 20:08:05 -08:00
qwen3vl_nonthinking_test.go	model: support for qwen3.5 architecture (#14378)	2026-02-24 20:08:05 -08:00
qwen3vl_thinking_test.go	model: support for qwen3.5 architecture (#14378)	2026-02-24 20:08:05 -08:00
qwen35.go	model: fix renderer and parser for qwen3.5 (#14605)	2026-03-03 20:58:29 -08:00
qwen35_test.go	model: fix renderer and parser for qwen3.5 (#14605)	2026-03-03 20:58:29 -08:00
renderer.go	Add support for gemma4 (#15214)	2026-04-02 11:33:33 -07:00
renderer_test.go	model: support for qwen3.5 architecture (#14378)	2026-02-24 20:08:05 -08:00
testhelpers_test.go	model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)	2026-01-19 12:47:17 -08:00