Add qwen3-embedding-0.6b-16k embedder llamafile (from claude-hooks v1.4.0, sha 414f6166) for opencoti-server download+install testing (F2 M8 / F4 M8)

package_courier report: 7-column tile grid (14 tiles fit 2 rows)

package_courier: fix sampler (tps_ewma field, run-lifetime sampling, w-mode) + report (x-domain clipping, t0 anchor, aggregate-tps/max-ctx tiles) — bug-2223

bench: A4B Q4 floor-1 control (97/100, StateGraph agent) — floor-1 losses are precision-driven, not harness; correct README claim

readme: A4B Q4 20/25 + F16 ladder rows; F16-vs-Q4 cost + StateGraph zero-loss findings

bench: A4B ladders — Q4_K_M floors 20/25 (cap 64) + F16 full ladder 1/5/15/20/25, all 100/100 zero-loss

bench: defaults — parallel 8, tps-floor 15 scheduler-driven, stall timeout auto-scales with steps (bug-2222)

readme: add 35B-A3B stress-ladder results (100/100 all floors, fan-out knee)

bench: 35B-A3B courier stress ladder (floors 1/5/15/20/25, 100/100 at every rung)

cleanup: drop __pycache__/.ruff_cache/.pytest_cache bytecode + stray integrations/langgraph/bench duplicate

card: LangGraph reference impl is real (StateGraph episodes) + publish integrations/langgraph package

docs: package_courier harness = reference LangGraph implementation

bench/package_courier: true LangGraph StateGraph reference impl (capacity_gate->agent<->tools) + offline routing tests

integrations/langgraph: publish opencoti_langgraph package (reference LangGraph integration, bug-2220)

card: package_courier harness link + release archive layout

bench: publish package_courier harness (report_html.py)

bench: publish package_courier harness (work_server.py)

bench: publish package_courier harness (agent_app.py)

bench: publish package_courier harness (run.py)

bench: publish package_courier harness (README.md)

release layout: archive c3 under releases/archived/ (keep only latest cut at root)

c4: SHA256SUMS

c4: release notes

c4: package_courier doc

c4: polykv_api doc

c4: UPSTREAM_SYNC refresh

c4: patches README

c4: 0137 spec ctx_dft null-check

c4: 0136 polykv control-plane API

c4: 0134 regenerated (bug-2218)

c4: sbsa side-load DSO

c4: x86_64 side-load DSO

c4: aarch64 MANIFEST

c4: aarch64 artifact

c4: win MANIFEST

c4: win variant

c4: x86_64 MANIFEST

c4: x86_64 artifact

docs: PolyKV stress benchmark section (#742)

bench: package_courier PolyKV stress benchmark — reports + harness README (#742)

docs: Vodafone sponsorship footer

assets: Vodafone sponsorship logo

docs: CUDA toolchain 13.2 -> 13.3 (13.3u1, #713)

patches: README row for 0135 — sync from git ff969d8a8f

patches: 0135 SharedKVPool hybrid/recurrent exact-share guard (bug-2203) — sync from git ff969d8a8f

docs: PolyKV cross-arch evals (#710) + bug-2203 hybrid gotcha + pool-prefill token-array recipe — sync from git 9969839543

USAGE: #707 SharedKVPool measured gains table + --no-cache-idle-slots flag rename + RYS x pool matrix cell validated

docs: surface PolyKV by name (umbrella def, §3.4 retitle, per-pool tiering semantics) — sync from git fbc32c1f3a

Upload folder using huggingface_hub

Upload docs/protocols/UPSTREAM_SYNC.md with huggingface_hub