Raise default agent token budget for reasoning models

The tracker mapping, common-pattern enrichment, and third-party
disambiguation agents default to a small max-tokens budget on the
premise that their final output is tiny structured JSON. On
reasoning models such as the GPT-5 family, reasoning tokens count
against max_tokens, so a small budget is consumed by reasoning and
the JSON is truncated, surfacing as "unexpected end of JSON input".

Raise the defaults to 4096 (1024 -> 4096 for tracker mapping, 512
-> 4096 for disambiguation) to leave headroom for the reasoning
phase. Update the bootstrap builder default, its test, and the
production values example to match.

Signed-off-by: Émile Ré <emile@probo.com>

pkg/bootstrap/builder_test.go

@@ -218,7 +218,7 @@ func TestBuilder_Build_Defaults(t *testing.T) {
 	assert.Empty(t, cfg.Probod.Agents.TrackerMapping.Provider)
 	assert.Empty(t, cfg.Probod.Agents.TrackerMapping.ModelName)
 	assert.Nil(t, cfg.Probod.Agents.TrackerMapping.Temperature)
-	assert.Equal(t, new(1024), cfg.Probod.Agents.TrackerMapping.MaxTokens)
+	assert.Equal(t, new(4096), cfg.Probod.Agents.TrackerMapping.MaxTokens)
 
 	// Tracker worker tuning — defaults
 	assert.Equal(t, 10, cfg.Probod.TrackerMappingWorker.Interval)