response.in_progress and built-in-tool event families
Scope-narrowing note (2026-06-12 positioning): split this issue's three parts. (1) response.in_progress — worth emitting; cheap, real clients key spinner state off it; part of the same…
Elevated by the 2026-06-12 reframing: adding this to the 7 → 8 milestone. For the agent workloads helexa actually serves (conversation N+1 = conversation N + a new turn), prefix reuse is the…
Still in scope, and elevated by the 2026-06-12 reframing (README positioning + the 7→8 milestone): cold-load latency is one of the operator-felt metrics the benchmark harness (#22) will measure…
previous_response_id chained conversations
Reframing note (2026-06-12 positioning): still relevant — Responses-API clients that chain via previous_response_id fall under the "point your tooling at it once and it keeps working" contract.…
Closing as out-of-scope — counterproductive under the project's stability contract (README, 2026-06-12). cortex's value as the per-operator proxy is that it is transparent and predictable: what…
Closing as out-of-scope under the sharpened project positioning (README, 2026-06-12): helexa's niche is near-frontier models on consumer hardware, served predictably — not stack purity. "First…
Closing as completed. Dynamic resolution landed on main: Qwen smart_resize with native-aspect buckets (c97a865), operator pixel-budget override + docs (d311c8c, C5), and the max_pixels cap…
Closing as completed — all three Stage C parts are on main: C1 streaming SSE chat completion with vision (766c20b), C2 Responses→chat image translation contract test (dd592d9), C3 vision-capa…
Closing as implemented and deployed. Stage 1 (error-faults → poison → auto unload/reload) merged and was verified live on beast 2026-06-08. Stage 2 (hang case: bounded leader wait + `ncclCommAbor…
Closing as completed. TP vision is on main: VisionTower is wired into tp/tp_qwen3_5.rs (replicated tower per the scope here), chunked TP-vision prefill landed in fa01350, interleaved M-RoPE…
Closing as completed. The code is in front of the real 27B in production: vision requests against Qwen/Qwen3.6-27B on beast (TP=2) were verified end-to-end through the gateway on 2026-06-04 (see…
image_url) is dropped — multimodal chat requests are processed as text-only
Closing as completed. Stage B (24968e9) shipped end-to-end text+image chat; the reporter verified the fix from the consumer side on 2026-06-04 (prompt_tokens 62 → 225, accurate frame description…
image_url) is dropped — multimodal chat requests are processed as text-only