opencode-llmstack 0.9.6__py3-none-any.whl → 0.9.7__py3-none-any.whl

llmstack/app.py

@@ -127,8 +127,6 @@ UPSTREAM = os.getenv("LLAMA_SWAP_URL", "http://127.0.0.1:10102").rstrip("/")
 FAST_MODEL = os.getenv("ROUTER_FAST_MODEL", "code-fast")
 AGENT_MODEL = os.getenv("ROUTER_AGENT_MODEL", "code-smart")
 ULTRA_MODEL = os.getenv("ROUTER_ULTRA_MODEL", "code-ultra")
-PLAN_MODEL = os.getenv("ROUTER_PLAN_MODEL", "plan")
-UNCENSORED_MODEL = os.getenv("ROUTER_UNCENSORED_MODEL", "plan-uncensored")
 
 # Step-DOWN ladder (see module docstring). Both ceilings are *upper
 # bounds* of a tier's sweet-spot range, expressed in estimated input

llmstack/generators/opencode.py

@@ -69,7 +69,7 @@ COMMANDS = {
         "agent":       "plan",
     },
     "nofilter": {
-        "template":    "[nofilter]",
+        "template":    "",
         "description": "Route to the uncensored planning model.",
         "agent":       "plan-nofilter",
     },

{opencode_llmstack-0.9.6.data → opencode_llmstack-0.9.7.data}/data/UPGRADING.md

@@ -266,7 +266,7 @@ How to evaluate:
 - Run `llama-bench -m <new>.gguf -p 512 -n 128 -ngl 999` for raw speed
 - Sniff test with a typical autocomplete prompt; latency should feel like
   the cursor is barely ahead of you
-- Aider leaderboard "edit format" column — proxy for FIM quality
+- [Aider leaderboard](https://aider.chat/docs/leaderboards/) "edit format" column — proxy for FIM quality
 
 Size budget: **~2–6 GB** weights (we want this resident permanently while
 sharing memory with the heavy tier).
@@ -287,10 +287,10 @@ What matters:
 - **Speed at full context** (MoE models win here on Apple Silicon)
 
 How to evaluate:
-- Aider's [LLM Leaderboard](https://aider.chat/docs/leaderboards/) — most
+- [Aider's LLM Leaderboard](https://aider.chat/docs/leaderboards/) — most
   honest signal for agentic coding
-- LiveCodeBench scores
-- SWE-Bench Verified (the "real PRs" benchmark)
+- [LiveCodeBench](https://livecodebench.github.io/leaderboard.html) scores
+- [SWE-Bench Verified](https://www.swebench.com/) (the "real PRs" benchmark)
 - Run an actual opencode session in `build` mode against your repo
 
 Size budget: **~30–55 GB** weights (must fit alongside `code-fast` ≈ 5 GB
@@ -311,8 +311,8 @@ What matters:
 - **Refusals on edge cases** — fine to refuse weird stuff in plain plan mode
 
 How to evaluate:
-- Open LLM Leaderboard (filter to chat/instruct, your size class)
-- Chatbot Arena — vibes-based but useful proxy
+- [Open LLM Leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) (filter to chat/instruct, your size class)
+- [Chatbot Arena](https://lmarena.ai/) — vibes-based but useful proxy
 - Hand-roll a "design this rate limiter" prompt and compare outputs
 
 Size budget: **~7–25 GB** weights — this tier shouldn't dominate memory.
@@ -360,12 +360,12 @@ Same size budget as `plan`.
 
 | Tier | Leaderboard |
 |---|---|
-| `code-fast` / `code-smart` | https://aider.chat/docs/leaderboards/ |
-|                            | https://livecodebench.github.io/leaderboard.html |
-|                            | https://www.swebench.com/ (Verified split) |
-| `plan` / `plan-uncensored` | https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard |
-|                            | https://lmarena.ai/ |
-|                            | https://livebench.ai/ |
+| `code-fast` / `code-smart` | [Aider LLM Leaderboard](https://aider.chat/docs/leaderboards/) |
+|                            | [LiveCodeBench](https://livecodebench.github.io/leaderboard.html) |
+|                            | [SWE-Bench Verified](https://www.swebench.com/) |
+| `plan` / `plan-uncensored` | [Open LLM Leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) |
+|                            | [Chatbot Arena](https://lmarena.ai/) |
+|                            | [LiveBench](https://livebench.ai/) |
 
 **Community signal** (qualitative but valuable):
 

{opencode_llmstack-0.9.6.dist-info → opencode_llmstack-0.9.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opencode-llmstack
-Version: 0.9.6
+Version: 0.9.7
 Summary: Multi-tier local LLM stack: llama-swap + FastAPI auto-router + opencode wiring.
 Author: llmstack
 License: MIT License
@@ -78,14 +78,14 @@ client (opencode / curl / Cursor / etc.)
         │
         ▼
   http://127.0.0.1:10101           <-- FastAPI router (llmstack.app)
-        │   • model="auto" → classify → rewrite to one of 4 tiers
+        │   • model="auto" → classify → rewrite to one of 3 coder tiers
         │   • everything else → pass-through
         ▼
   http://127.0.0.1:10102           <-- llama-swap (binary, manages model lifecycle)
         │   • loads/unloads llama-server processes per model
         │   • matrix solver allows {code-fast + one heavy model} co-resident
         ▼
-  llama-server <code-fast | code-smart | plan | plan-uncensored>
+  llama-server <code-fast | code-smart | code-ultra>
         │
         ▼
   GGUF in ~/.cache/huggingface/hub/...
@@ -101,7 +101,7 @@ A 64 GB unified memory M4 Max can comfortably hold **one always-on tiny coder +
 
 - **Agent work** (multi-file edits, tool use, refactors) → coder models, which are trained on tool-call protocols and code edits.
 - **Planning** (design discussions, architecture, "what's the best approach") → chat-tuned models, which are better at high-level reasoning and don't try to start writing code in response to every message.
-- **Uncensored planning** is a separate plan-tier model, opted in either by request (`agent.plan-nofilter` in opencode) or by an inline `[nofilter]` trigger in the prompt.
+- **Uncensored planning** is a separate plan-tier model, opted in by explicit agent selection (`/agent plan-nofilter` in opencode).
 
 Routing decisions cost ~zero — they're a few regex checks in the FastAPI router, not an LLM call.
 
@@ -135,20 +135,18 @@ matches how these models actually behave on this stack:
   than priors, so they tend to *improve* relative to top-tier as the
   conversation grows.
 
-First match wins:
+First match wins (auto-routing only; `plan` and `plan-uncensored` are not auto-routed):
 
 | # | Condition | → Model | Reason |
 |---|---|---|---|
-| 1 | last user msg contains `[nofilter]`, `[uncensored]`, `[heretic]`, or starts with `uncensored:` / `nofilter:` | `plan-uncensored` | explicit opt-in |
-| 2 | `[ultra]` / `[opus]` / `ultra:` trigger AND `code-ultra` tier configured | `code-ultra` | explicit top-tier opt-in |
-| 3 | plan verbs (*design, architect, approach, trade-off, should we, explain why, …*) AND no code blocks / agent verbs / tools | `plan` | pure design discussion (orthogonal track) |
-| 4 | estimated input ≤ 12 000 tokens | `code-ultra` *(or `code-smart` if ultra unwired)* | top tier — context still being built, latency/$ are best here |
-| 5 | estimated input ≤ 32 000 tokens | `code-smart` | mid-context, local heavy coder is at its sweet spot |
-| 6 | otherwise (long context) AND ≥ 10 user turns | `code-smart` | floor: deep agentic loop, keep the heavy model |
-| 7 | otherwise (long context) | `code-fast` | 128k YaRN window + always-resident + free |
+| 1 | `[ultra]` / `[opus]` / `ultra:` trigger AND `code-ultra` tier configured | `code-ultra` | explicit top-tier opt-in |
+| 2 | estimated input ≤ 12 000 tokens | `code-ultra` *(or `code-smart` if ultra unwired)* | top tier — context still being built, latency/$ are best here |
+| 3 | estimated input ≤ 32 000 tokens | `code-smart` | mid-context, local heavy coder is at its sweet spot |
+| 4 | otherwise (long context) AND ≥ 10 user turns | `code-smart` | floor: deep agentic loop, keep the heavy model |
+| 5 | otherwise (long context) | `code-fast` | 128k YaRN window + always-resident + free |
 
 Token estimates are `chars / 4` over all message text + `prompt`. The
-`code-ultra` rungs (2 and 4) are gated on availability: when no
+`code-ultra` rungs (1 and 2) are gated on availability: when no
 `[code-ultra]` section is loaded from `models.ini`, both silently fall
 back to `code-smart` so vanilla installs don't 404.
 
@@ -198,7 +196,8 @@ your global setup unchanged.
 | **`agent.plan-nofilter`** (custom uncensored planner) | `llama.cpp/plan-uncensored` |
 
 Inside opencode you can switch agents with `/agent` or by `@plan-nofilter`-mentioning
-a custom one. Slash-commands `/review`, `/nofilter` are also available.
+a custom one. The `plan` and `plan-uncensored` tiers are **not auto-routed** from the build agent —
+they're only accessible via explicit agent selection (`/agent plan` or `/agent plan-nofilter`).
 
 Want a second terminal into the same stack? Install the activate hook
 once (`eval "$(llmstack activate zsh)"`) and any new shell that `cd`s
@@ -266,8 +265,9 @@ Per-project state (gitignored) is created lazily under `<work-dir>/.llmstack/`:
 ```
 
 The `llama-swap` binary lives outside any project at
-`$XDG_DATA_HOME/llmstack/bin/llama-swap` (override with
-`LLMSTACK_BIN_DIR`). One download is reused across all projects.
+`$XDG_DATA_HOME/llmstack/bin/llama-swap` on macOS/Linux (override with
+`LLMSTACK_BIN_DIR`), or `%LOCALAPPDATA%\llmstack\bin\llama-swap.exe` on Windows.
+One download is reused across all projects.
 
 ## Quick start
 
@@ -358,8 +358,9 @@ Notes:
   or a package like `winget install ggml.llama-cpp` and put it on
   `PATH` (or set `$env:LLAMA_SERVER_BIN`). The Mac-only
   `iogpu.wired_limit_mb` step does not apply.
-- The `[llmstack:<channel>]` prompt prefix shows up in PowerShell too;
-  `cmd.exe` gets a simpler `[llmstack:<channel>]` prompt via `doskey`.
+- The `[llmstack:<channel>]` prompt prefix shows up in PowerShell; `cmd.exe`
+  does not support custom prompts in the same way, so activation is
+  PowerShell-only.
 - Stopping daemons uses `taskkill /T /F` under the hood, so the
   llama-server children get cleaned up as well.
 
@@ -465,7 +466,7 @@ llmstack restart --next                # cycle into the next channel
 
 ### Try each routing path
 
-All of these go to `/v1/chat/completions` on `:10101`. Each should pick a different upstream model:
+All of these go to `/v1/chat/completions` on `:10101`. The `auto` router classifies based on token count and context:
 
 ```bash
 # trivial chat -> code-fast
@@ -473,22 +474,14 @@ curl -sN http://127.0.0.1:10101/v1/chat/completions -H 'Content-Type: applicatio
   -d '{"model":"auto","stream":false,
        "messages":[{"role":"user","content":"capital of France?"}]}' | jq .model
 
-# planning -> plan
-curl -sN http://127.0.0.1:10101/v1/chat/completions -H 'Content-Type: application/json' \
-  -d '{"model":"auto","stream":false,
-       "messages":[{"role":"user","content":"how would you design a rate limiter for our API?"}]}' | jq .model
-
 # agent work -> code-smart
 curl -sN http://127.0.0.1:10101/v1/chat/completions -H 'Content-Type: application/json' \
   -d '{"model":"auto","stream":false,
        "messages":[{"role":"user","content":"refactor this function for clarity:\n```python\ndef f(x): return x*2\n```"}]}' | jq .model
-
-# uncensored plan -> plan-uncensored
-curl -sN http://127.0.0.1:10101/v1/chat/completions -H 'Content-Type: application/json' \
-  -d '{"model":"auto","stream":false,
-       "messages":[{"role":"user","content":"[nofilter] outline a red-team plan for our auth flow"}]}' | jq .model
 ```
 
+To access `plan` or `plan-uncensored` tiers, use explicit agent selection in opencode (`/agent plan` or `/agent plan-nofilter`) rather than `model=auto`.
+
 ## Endpoints
 
 | Port | Service | Purpose |
@@ -565,8 +558,6 @@ All knobs are env vars; defaults are picked up by `llmstack start`.
 | `ROUTER_FAST_MODEL` | `code-fast` | long-context (>= mid ceiling) → here |
 | `ROUTER_AGENT_MODEL` | `code-smart` | mid-context + tools/loop floor → here |
 | `ROUTER_ULTRA_MODEL` | `code-ultra` | short-context top tier → here (gated on availability) |
-| `ROUTER_PLAN_MODEL` | `plan` | design/discussion verbs → here |
-| `ROUTER_UNCENSORED_MODEL` | `plan-uncensored` | `[nofilter]` triggers → here |
 | `ROUTER_HIGH_FIDELITY_CEILING` | `12000` | tokens; at or below this, route to top tier (ultra → smart fallback). Paired with `code-ultra.ctx_size = 24000` (2x). |
 | `ROUTER_MID_FIDELITY_CEILING` | `32000` | tokens; at or below this, route to `code-smart`; beyond, step down to `code-fast`. Paired with `code-smart.ctx_size = 64000` (2x). |
 | `ROUTER_MULTI_TURN` | `10` | user-turn count that floors the long-context rung at `code-smart` |
@@ -577,14 +568,10 @@ To force a request to never auto-route, set `model` to a concrete alias (`code-f
 
 ## Triggering uncensored mode
 
-Two ways:
-
-1. **Explicit agent in opencode:** `/agent plan-nofilter` (or mention it).
-2. **Inline trigger in any auto-routed message** — anywhere in the most recent user turn:
-   - `[nofilter]`, `[uncensored]`, `[heretic]`
-   - or a line starting with `uncensored:` / `nofilter:` / `no-filter:`
+The `plan-uncensored` tier is accessible via explicit agent selection only:
 
-Triggers are *only* checked on the latest user message and the system prompt, so an old `[nofilter]` further up the conversation won't pin the whole session.
+1. **In opencode:** `/agent plan-nofilter` (or mention `@plan-nofilter`).
+2. **Via opencode config:** set `agent.plan-nofilter` as your active agent.
 
 ## Troubleshooting
 
@@ -594,7 +581,7 @@ Triggers are *only* checked on the latest user message and the system prompt, so
 
 **OOM / unexplained slowdown** → run `top -o mem -stats pid,rsize,command` to see what's resident. The matrix should prevent two heavy models loading together; if it somehow happens, `llmstack restart`.
 
-**Auto picks the wrong model** → adjust the regex in `llmstack/app.py` (`AGENT_SIGNALS` / `PLAN_SIGNALS` / `UNCENSORED_TRIGGERS`) or move the ladder ceilings via `ROUTER_HIGH_FIDELITY_CEILING` / `ROUTER_MID_FIDELITY_CEILING`. To force a request to never auto-route, pass an explicit `model` (e.g. `code-smart`) instead of `auto`.
+**Auto picks the wrong model** → adjust the regex in `llmstack/app.py` (`ULTRA_TRIGGERS`) or move the ladder ceilings via `ROUTER_HIGH_FIDELITY_CEILING` / `ROUTER_MID_FIDELITY_CEILING`. To force a request to never auto-route, pass an explicit `model` (e.g. `code-smart`) instead of `auto`.
 
 **Want a pure pass-through (no auto routing)** → change opencode's `baseURL` to `http://127.0.0.1:10102/v1` (llama-swap directly) and only use concrete model names. (Note: this skips the bedrock dispatcher; only GGUF tiers will be reachable.)
 

{opencode_llmstack-0.9.6.dist-info → opencode_llmstack-0.9.7.dist-info}/RECORD

@@ -2,7 +2,7 @@ llmstack/AGENTS.md,sha256=4DVUkqJ1-EP-cDNRCpznzghOOX6dAMbVWdcwyfFCALw,528
 llmstack/__init__.py,sha256=Ie-86h7q7pEsE9zTlWfjBEYDIoR4mC8ZutdC5Nx-x8k,855
 llmstack/__main__.py,sha256=wXHd5-BmCCHUfNEmy2rbilBSyVhi4KD1dSIO_4NlxuE,199
 llmstack/_platform.py,sha256=eDY3T9krkaBigG5xXxqzIbH3MhdZqX3BWe7bozOsAso,13099
-llmstack/app.py,sha256=CiqIGpEbcjuSGDFNH951LiWZlE7Ju2_w5FHL5ieiAog,25952
+llmstack/app.py,sha256=NjF9WohKu9qXREbufWKzLO2CU_MNCGiXws2cE1m3cpg,25825
 llmstack/check_models.py,sha256=WvTS2Td4acp-Q0-yWXUgXAgAgFOmpxiaeSDuAoivirw,4559
 llmstack/cli.py,sha256=Om70PzHrmU81y2Mw1sB6eeUs1fRHP0PnsCEVNC0UNvI,11341
 llmstack/models.ini,sha256=7ObeGrScRm0pGjyjAencr5lg8gEsMpjNvvF4o4Fxhps,19860
@@ -29,13 +29,13 @@ llmstack/download/binary.py,sha256=xpv15wF4viv8uFC5UqfSIf36CIoPpmaNUaVtjF-vTWA,8
 llmstack/download/ggufs.py,sha256=2hCr-svUiPIV2I3ruwTbXo6lPn9m-VBOqa3DFbvdIcA,5435
 llmstack/generators/__init__.py,sha256=LfbcReuyYBCdVuT9J5RKo7-f8n585YBU3Hus6DsxqTs,1189
 llmstack/generators/llama_swap.py,sha256=KdYH9N6TJECotZvyxvAjaa3kRyzn4YOi2T6D2UdyVKw,14785
-llmstack/generators/opencode.py,sha256=8-eVGD3ZTgta3DHQ5gu6I9CkYZt7x-EdMw2qNzgyoQ4,11191
-opencode_llmstack-0.9.6.data/data/CHANGELOG.md,sha256=58feU0rA9bBYvecDoFaLcwwgezLPkD3MSt0vRUVjdF8,5837
-opencode_llmstack-0.9.6.data/data/LICENSE,sha256=6G-Otw6BHIM1WJSBlJ04P1rDVCqbDEzKpdOlSr5CqIY,1078
-opencode_llmstack-0.9.6.data/data/UPGRADING.md,sha256=0XSNZ9trCviFLH5EL3Jz02fO2_8AfqB8_9aX0-o1bik,24927
-opencode_llmstack-0.9.6.dist-info/licenses/LICENSE,sha256=6G-Otw6BHIM1WJSBlJ04P1rDVCqbDEzKpdOlSr5CqIY,1078
-opencode_llmstack-0.9.6.dist-info/METADATA,sha256=VHLq0f7YxR0BAPnGYC7uLS4jqNGB0Ki5GPZq0ER1nW8,36323
-opencode_llmstack-0.9.6.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
-opencode_llmstack-0.9.6.dist-info/entry_points.txt,sha256=soomjpqvl4KzFScgpQbu96vgcLriOtkB9MbiSC0rvZ8,47
-opencode_llmstack-0.9.6.dist-info/top_level.txt,sha256=tMv9sDWp8RW_DNNY8cuM4Uy4sND-KwTLcsScl5gdcEQ,9
-opencode_llmstack-0.9.6.dist-info/RECORD,,
+llmstack/generators/opencode.py,sha256=aeaHCdiU1GwtQe8LGeH3JHaC2m3GWLzUlQbDlh0SKSw,11181
+opencode_llmstack-0.9.7.data/data/CHANGELOG.md,sha256=58feU0rA9bBYvecDoFaLcwwgezLPkD3MSt0vRUVjdF8,5837
+opencode_llmstack-0.9.7.data/data/LICENSE,sha256=6G-Otw6BHIM1WJSBlJ04P1rDVCqbDEzKpdOlSr5CqIY,1078
+opencode_llmstack-0.9.7.data/data/UPGRADING.md,sha256=v8An-KwNAiDF0Ez86tjFOesMdxZt6zDsNZXwd6Cw0Uw,25248
+opencode_llmstack-0.9.7.dist-info/licenses/LICENSE,sha256=6G-Otw6BHIM1WJSBlJ04P1rDVCqbDEzKpdOlSr5CqIY,1078
+opencode_llmstack-0.9.7.dist-info/METADATA,sha256=mFvTReZmyrrALK5oobW-xtW8JqN6K3ROXkqwAPeIaDg,35443
+opencode_llmstack-0.9.7.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+opencode_llmstack-0.9.7.dist-info/entry_points.txt,sha256=soomjpqvl4KzFScgpQbu96vgcLriOtkB9MbiSC0rvZ8,47
+opencode_llmstack-0.9.7.dist-info/top_level.txt,sha256=tMv9sDWp8RW_DNNY8cuM4Uy4sND-KwTLcsScl5gdcEQ,9
+opencode_llmstack-0.9.7.dist-info/RECORD,,