PyTorch in the Nix env is CPU-only, so the bundled omnivoice.cpp
runtime (ggml Vulkan) is the only GPU path.
Put vulkan-tools on the backend PATH: the app finds the adapter by
running `vulkaninfo` and otherwise reports none, since NixOS has no
FHS library directories for its fallback probe.
Default OMNIVOICE_GGUF_BACKEND=vulkan so the runtime opens the GPU or
fails loudly instead of falling back to the CPU. Overridable.
Refs: nix-overlay-ltr
The app's first-run setup downloads uv's generic CPython into
~/.config/VoiceStudio/runtime, which NixOS cannot execute (stub-ld).
Do the same frozen `uv sync` at build time against upstream's nixpkgs
python, in a fixed-output derivation, and point the app at it through
OMNIVOICE_BACKEND_CMD so it no longer manages a runtime of its own.
The ctranslate2 executable-stack flag is cleared at build time with
upstream's own repair, since the store is read-only.
CPU torch only. Adds an import-probe check.
Refs: nix-overlay-2r3
VoiceStudio ships its own flake that builds the Electron app, the Rust
dictation helper and the OmniVoice GGUF runtime. Re-export it instead of
repackaging: its package needs electron_44-bin, which our pinned nixpkgs
lacks, so the input keeps its own nixpkgs rather than following ours.
Build and upstream's six packaging checks pass on x86_64-linux.
Refs: nix-overlay-kk7
Rebased arbitrary-http-headers.patch onto the new main: upstream renamed
resolve_validator_backend to resolve_validator_backend_with_lease, added
backend_urls/validator_backend_urls to SpecialistConfig, replaced
MCP_REQUEST_TIMEOUT with per-server cfg.request_timeout(), and restructured
McpManager::boot_one behind connect_client. cargoHash is unchanged because
Cargo.lock did not move.
Signed-off-by: Alexander Miroshnichenko <alex@millerson.name>
Give two-session Qwen serving a bounded, opt-in decode grace for large cold prompts. Returning to normal interleaving at the deadline bounds the wait when the running reply takes longer than expected.
Bead: nix-overlay-qfi
Update the upstream flake pin and correct version reporting docs.
Evaluation reports 1.8.26. Build and test verification remains pending
on a remote builder or CI; do not build on this workstation.
Strata 0.2.14 leaves llama.cpp's MMQ prompt kernels out by default, so
STRATA_MMQ_KQ does nothing and UD-Q5_K_XL's Q6_K layer runs on Strata's
int8 kernel. On ms-s1-max, 0.2.15 with the gfx1151 prompt set and
STRATA_MMQ_KQ=1 gives first-token logits bit-identical to 0.2.13 over
15 cold prompts at the same speed (~1180 tok/s at 16K); without MMQ an
agent prompt reached KL 0.199 against 0.2.13. The engine grows from 39
to 54 MB.
Bead: nix-overlay-481
Strata 0.2.14 runs the prompt on its own kernels and vendors llama.cpp
(third_party/strata-llama), so the separate llama.cpp fetch for the
vision encoder goes. The build keeps upstream's halo flags: MMQ stays
out (STRATA_MMQ defaults to OFF), 47 of 48 UD-Q5_K_XL layers run on the
fused kernels, and the ROCm 10.1 hipBLASLt table still ships.
UD-Q5_K_XL on ms-s1-max, 16K cold prompts: 715 -> ~810 tok/s on the
defaults, ~1180 tok/s with the gfx1151 prompt set (unchanged).
Bead: nix-overlay-ydg
Upstream's gfx1151-hipblaslt-100401.txt was calibrated on TheRock 7.14.1.
therock-rocm 10.1.0rc3 reports the same hipBLASLt version, so the engine
accepted the table, but its solution ids do not exist in that build and
every prompt GEMM fell back to the heuristic. The table now comes from
tools/hip/tune_hipblaslt run on gfx1151 against therock-rocm 10.1 and is
installed in bin/tuning/, where the engine finds it by itself.
UD-Q5_K_XL, 17.5K cold prompt on ms-s1-max: 418 -> 700-725 tok/s.
Bead: nix-overlay-2yv
Maintain the gfx1151 SDK locally using the official AMD archive. Use the TheRock patchelf pin and adapt LLVM auxiliary tools for pure Nix builds.
Verify SDK installation, HIP and rocBLAS GPU operations, and rebuild its consumers. Document the internal rc3 stamp and upstream migration findings.
nix-overlay-v09 keeps the completed migration evidence and the outstanding
ms-s1-max build gate; nix-overlay-y5r is tombstoned after the duplicate
codex-oauth-proxy work was superseded.
1.1.1 omits the model from normalizeModel's allowlist, so requests for gpt-6.1-terra are rewritten to gpt-5.5. ChatGPT accounts are not entitled to gpt-5.5, so the request fails with model_not_found.
Add the model to the allowlist, allowed reasoning efforts, and default effort. Covered by the transform tests.
Serena rewrote its project config: new language-server IDs in the
comment list plus included_apis, excluded_apis and agent_interface keys.
All new keys keep their empty defaults, so no setting changes.
Remove content that no longer matches the workflow: package templates
already covered by the "Adding a New Package" steps, per-package notes,
the duplicated beads command reference, and the mandatory git push steps.
Drop the sequentialthinking MCP requirement and add a rule that AGENTS.md
changes need an explicit user request.
Packages dvcrn/codex-oauth-proxy, which exposes a ChatGPT Codex account through OpenAI-compatible APIs, as a buildGoModule derivation. Builds only cmd/codex-oauth-proxy because the worker package is js/wasm code, and passes -buildvcs=false because the Nix source has no .git. Upstream Go tests run offline, so doCheck is enabled.
Add magg, an MCP aggregator / meta-MCP server, to the overlay. It is a
Python package on the hatchling backend, built with
python3Packages.buildPythonApplication from the v1.3.0 source tarball,
so no upstream release artifacts are fetched. Ships both console
scripts declared upstream: magg (the aggregator CLI/server) and mbro
(the MCP browser). License is AGPL-3.0-or-later.
The install check runs the upstream pytest suite with
-m "not integration", because the integration-marked tests need a live
server. A forced nix build .#magg --rebuild passes with 329 passed,
3 skipped, 3 deselected, 0 failed, and both binaries smoke-test clean.
Also adds the README and AGENTS.md package rows, the upstream and build
research notes, and the verification report in docs/magg_build_report.md.