chore: release main

[github-actions]

🤖 I have created a release beep boop

higgs: 1.0.0

1.0.0 (2026-04-26)

⚠ BREAKING CHANGES

• higgs start is now config/profile-only, attach is a strict daemon dashboard, shellenv/exec fail fast on invalid or unreachable targets, and exact local model matches now take precedence over regex routes.

Features

• add --profile CLI flag, TUI routing tab, and config visibility (#45) (95dda05)
• add higgs exec -- <command> subcommand (#49) (b61dbf5)
• add higgs run -- <command> subcommand (#47) (72339d2)
• add name field to ModelConfig (#43) (54147e0)
• add qwen3.5/qwen3.6 turboquant stack (4f165ee)
• API routes — thinking mode streaming and tool call validation (5f7e62c)
• harden CLI, dashboard, routing, and MLX runtime (4dfc930)
• resize routing sidebar (913e015)
• server config — TurboQuant, thinking budget, chunked prefill settings (5b63e4c)
• ship mlx.metallib alongside the higgs binary (#39) (deaa322)
• tune qwen3.6 thinking defaults (6969834)
• unified AI gateway with proxy routing and format translation (#38) (7c5668b)

Bug Fixes

• address coderabbit issues (6f10bc6)
• address follow-up review issues (5c857ce)
• address review comments (36c6484)
• address review follow-ups (d2b312e)
• backtick TcpListener in doc comment for clippy doc_markdown (94acea7)
• cargo fmt + restore higgs crate build on PR #74 (050af95)
• clarify metallib recovery hint (645dbb0)
• clear lint and review blockers (9c8b878)
• config: timeout validation and figment model merge (441884d)
• correct comment about signal handler behavior (81cbd71)
• improve Anthropic API compatibility (16ee50d)
• improve Anthropic API compatibility (ff7e96c)
• log warning instead of silently discarding signal handler error (6946974)
• make pre-push pass on dust stack (2695165)
• normalize auto_router.model to a name like routes do (1e741c5)
• normalize auto_router.model to a name like routes do (3b52db4)
• remove incorrect default_value on Option<u8> CLI arg — PR #75 (bf87bbd)
• resolve auto_router model by basename when config uses full path (#41) (7220fa2)
• restore higgs crate build on PR #75 — chat.rs usage stubs (f92d139)
• restore pattern matching fallback in force routing mode (c1bb2c3)
• restore pattern matching fallback in force routing mode (217249f)
• routes: close think tag on length-stopped reasoning in OpenAI path (5c2ea56)
• satisfy clippy duration lint (20c6aae)
• stabilize dust stack CI (8e629e3)
• strip thinking tags from Anthropic route, fix force routing, add proxy usage tracking (89f8db2)
• strip thinking tags, fix force routing, add proxy usage metrics (0ffbabb)
• support clippy across toolchains (abc316d)
• support mlx qwen3.6 smoke (7046849)
• use 128+signal convention for signal-killed child exit codes (89b7ae0)

higgs-engine: 1.0.0

1.0.0 (2026-04-26)

⚠ BREAKING CHANGES

• higgs start is now config/profile-only, attach is a strict daemon dashboard, shellenv/exec fail fast on invalid or unreachable targets, and exact local model matches now take precedence over regex routes.

Features

• add qwen3.5/qwen3.6 turboquant stack (4f165ee)
• harden CLI, dashboard, routing, and MLX runtime (4dfc930)
• inference engine — chunked prefill, prefix cache, thinking budget, MTP (4fa0971)
• Qwen3.5 model architecture, TurboQuant KV cache, and model-level optimizations (1514737)
• thinking mode support — reasoning parser and chat template (a3cc52e)
• tune qwen3.6 thinking defaults (6969834)

Bug Fixes

• address coderabbit issues (6f10bc6)
• address follow-up review issues (5c857ce)
• address remaining draft review issues (4396e88)
• address review items across models and engine — PR #74 (8863e2d)
• cargo fmt + restore higgs crate build on PR #74 (050af95)
• clear lint and review blockers (9c8b878)
• engine,models: cache config propagation, ndim guards, FSM ordering (37d2ddd)
• engine,models: clippy clean lib targets on PR #74 (51→0 errors) (ebf3192)
• engine: clippy clean 6 files on PR #74 (85→51 errors) (7dc7370)
• engine: prefix cache full-hit, scheduler leak, gather bounds check (3e35b3f)
• make pre-push pass on dust stack (2695165)
• stabilize dust stack CI (8e629e3)

higgs-models: 1.0.0

1.0.0 (2026-04-26)

⚠ BREAKING CHANGES

• higgs start is now config/profile-only, attach is a strict daemon dashboard, shellenv/exec fail fast on invalid or unreachable targets, and exact local model matches now take precedence over regex routes.

Features

• add qwen3.5/qwen3.6 turboquant stack (4f165ee)
• harden CLI, dashboard, routing, and MLX runtime (4dfc930)
• Qwen3.5 model architecture, TurboQuant KV cache, and model-level optimizations (1514737)

Bug Fixes

• address coderabbit issues (6f10bc6)
• address review items across models and engine — PR #74 (8863e2d)
• align turboquant tests with rand 0.10 (d0617c4)
• cargo fmt + restore higgs crate build on PR #74 (050af95)
• clear lint and review blockers (9c8b878)
• engine,models: cache config propagation, ndim guards, FSM ordering (37d2ddd)
• engine,models: clippy clean lib targets on PR #74 (51→0 errors) (ebf3192)
• gate rng import to tests (1161eaa)
• honor qwen3 next gate quantization (00958e1)
• make pre-push pass on dust stack (2695165)
• models: clippy clean for higgs-models on PR #74 (part 2/2) (1b4470b)
• models: clippy clean in 5/7 files on PR #74 (part 1/2) (af57c32)
• restore rng import and checkout pin (8771fa0)
• satisfy clippy on qwen3.6 tests (ab2920a)
• stabilize dust stack CI (8e629e3)
• support mlx qwen3.6 smoke (7046849)

---

This PR was generated with Release Please. See documentation.