robot_lab-to 0.2.8 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 43c5ef1239f3c91dcf0b033466a2a346f3dafb385897d1e5696e2952a752a49d
-  data.tar.gz: 29fb0fda8e3fbd13f079a3244c577c69e53fcb4e1c8dbdc5066b32c059bd7f67
+  metadata.gz: 3dad27a958d30948be8ed4f93401f169e799c24d3a4d77fc4d205bf00c80849c
+  data.tar.gz: bdd675595bb524d3e4f2f1e24dce9df7b7ef2070195b5b60e3317780c4e51163
 SHA512:
-  metadata.gz: 7af7eca43dac57ae02b21b24b9ad8b7a813e473b5470372ee5048980948d0bb431e6b164d88f532394da9cd946d7ed75cafe2746efac41f79dc2cc1c0a1aaad6
-  data.tar.gz: beb2270499d125d74f2a3333610c44b9cd030f8ee9142bf4b2b3e87b1f0e410b9f768ffdb83c7187e80e0d1d593ce77ebbf5f89cdee9b5d640432d788b429733
+  metadata.gz: 92a7c42b8b8586085a9894c15d2443e809b65147db939707b1d1c1ec2b83eeaec09752a165fa2193fb38d9f7fb10211fe33b8c0cce8a86b4a40a4987affb4be8
+  data.tar.gz: 06bd6bf4074ea7a35e969736de4ba5946db22a2313ee7551528d93630950fddfc2572acee1e3116bf923fe5b9aeffcbc198234106a7f32e9ebbd67d758887b57

data/.envrc

@@ -4,4 +4,4 @@ source_up
 
 export RR=$(pwd)
 
-export BUNDLE_GEMFILE=Gemfile
+# BUNDLE_GEMFILE is inherited from the project root .envrc (asgard dev|prod)

data/README.md

@@ -244,16 +244,18 @@ RobotLab::To.run(
 ## Local models
 
 `robot_lab-to` can drive a local model running offline against
-[Ollama](https://ollama.com) — no API keys, no per-token cost.
+[LM Studio](https://lmstudio.ai) via the
+[ruby_llm-providers-lms](https://github.com/madbomber/ruby_llm-providers-lms)
+gem — no API keys, no per-token cost.
 
 ```bash
-ollama pull gpt-oss:20b
+lms server start
+lms get qwen/qwen3.8-27b
 
 robot-to "Add a greet(name) method in greeter.rb" \
-  --provider openai \
-  --model gpt-oss:20b \
+  --provider lms \
+  --model qwen/qwen3.8-27b \
   --local-guards \
-  --no-stream \
   --max-iterations 5
 ```
 
@@ -320,8 +322,8 @@ export ROBOT_LAB_TO_STREAM=false
 
 API keys are read by the underlying provider (via RobotLab / RubyLLM), **not** by
 `robot_lab-to` itself — e.g. `ANTHROPIC_API_KEY`, `OPENAI_API_KEY`. Local
-[Ollama](https://ollama.com) models need no key; see the
-[Local Models guide](https://madbomber.github.io/robot_lab-to/local-models/ollama/).
+[LM Studio](https://lmstudio.ai) models need no key; see the
+[Local Models guide](https://madbomber.github.io/robot_lab-to/local-models/lm-studio/).
 
 ---
 

data/docs/concepts/stop-conditions.md

@@ -37,9 +37,9 @@ limit.
 
 - **Streaming runs** (the default) account tokens per chunk and can interrupt an
   in-flight iteration the moment the budget is exhausted.
-- **Non-streaming runs** (`--no-stream`, used for local models) account tokens
-  from each iteration's result and stop at the next iteration boundary. See
-  [Local Models](../local-models/ollama.md#streaming-and-tool-calls).
+- **Non-streaming runs** (`--no-stream`) account tokens from each iteration's
+  result and stop at the next iteration boundary. See
+  [Local Models](../local-models/index.md).
 
 ### Consecutive failures
 

data/docs/configuration/cli.md

@@ -43,7 +43,7 @@ echo "Add request logging middleware and tests" | robot-to
 | `--commit-format` | `default`\|`conventional` | `default` | Commit message format. |
 | `--run-dir` | `PATH` | `.robot_lab_to` | Directory for run state. |
 | `--local-guards` | — | off | Add built-in file tools + small-model guardrails. |
-| `--no-stream` | — | streaming on | Disable streaming (required for local Ollama tool calls). |
+| `--no-stream` | — | streaming on | Disable streaming (tokens are then accounted per iteration instead of per chunk). |
 | `--debug` | — | off | Keep verbose provider logging enabled. |
 | `--version` | — | — | Print version and exit. |
 | `-h`, `--help` | — | — | Show help and exit. |
@@ -92,14 +92,13 @@ robot-to "Write an opinionated guide to the Viable Systems Model" \
   --stop-on-plateau 3
 ```
 
-A fully local run on Ollama (see [Local Models](../local-models/index.md)):
+A fully local run on LM Studio (see [Local Models](../local-models/index.md)):
 
 ```bash
 robot-to "Add a greet(name) method in greeter.rb" \
-  --provider openai \
-  --model gpt-oss:20b \
+  --provider lms \
+  --model qwen/qwen3.8-27b \
   --local-guards \
-  --no-stream \
   --max-iterations 5
 ```
 

data/docs/configuration/index.md

@@ -43,10 +43,9 @@ Create `~/.config/robot_lab/to.yml` to set your own defaults — for example, to
 always use a local model:
 
 ```yaml
-provider: openai          # routes to Ollama's OpenAI-compatible endpoint
-model: gpt-oss:20b
+provider: lms             # LM Studio via the ruby_llm-providers-lms gem
+model: qwen/qwen3.8-27b
 local_guards: true
-stream: false
 max_consecutive_failures: 4
 ```
 

data/docs/configuration/settings.md

@@ -13,8 +13,9 @@ CLI flag, or a `RobotLab::To.run` keyword argument (see
 - **CLI:** `--provider NAME`
 
 The LLM provider, passed through to RobotLab / RubyLLM. Use `anthropic`,
-`openai`, etc. For **local Ollama models**, set this to `openai` and point
-RubyLLM at Ollama's OpenAI-compatible endpoint — see [Ollama Setup](../local-models/ollama.md).
+`openai`, etc. For **local LM Studio models**, require the
+ruby_llm-providers-lms gem and set this to `lms` — see
+[LM Studio Setup](../local-models/lm-studio.md).
 
 ### `model`
 
@@ -22,7 +23,7 @@ RubyLLM at Ollama's OpenAI-compatible endpoint — see [Ollama Setup](../local-m
 - **CLI:** `--model MODEL`
 
 The model identifier for the chosen provider (e.g. `claude-sonnet-4-6`,
-`gpt-5.5`, `gpt-oss:20b`).
+`gpt-5.5`, `qwen/qwen3.8-27b`).
 
 ### `stream`
 
@@ -30,10 +31,9 @@ The model identifier for the chosen provider (e.g. `claude-sonnet-4-6`,
 - **CLI:** `--no-stream` to disable
 
 Whether to stream the model response. Streaming enables per-chunk token
-accounting and mid-iteration token-budget enforcement. **Local Ollama models must
-run with `--no-stream`** — Ollama suppresses tool calls when streaming. With
-streaming off, tokens are accounted from each iteration's result instead. See
-[Streaming and tool calls](../local-models/ollama.md#streaming-and-tool-calls).
+accounting and mid-iteration token-budget enforcement. With streaming off,
+tokens are accounted from each iteration's result instead. See
+[LM Studio Setup](../local-models/lm-studio.md).
 
 ## Loop control
 

data/docs/getting-started/installation.md

@@ -7,7 +7,7 @@
 | Ruby **>= 3.2** | Set in the gemspec `required_ruby_version`. |
 | Git | A repository with at least one commit. The loop creates a branch and commits there. |
 | `robot_lab` | The core framework `robot_lab-to` builds on. |
-| An LLM provider | A cloud API key, **or** a local [Ollama](https://ollama.com) server (see [Local Models](../local-models/index.md)). |
+| An LLM provider | A cloud API key, **or** a local [LM Studio](https://lmstudio.ai) server (see [Local Models](../local-models/index.md)). |
 
 ## Install the gem
 
@@ -46,11 +46,11 @@ RobotLab / RubyLLM. Provide credentials the usual way for your provider:
     robot-to "..." --provider openai --model gpt-5.5
     ```
 
-=== "Local (Ollama)"
+=== "Local (LM Studio)"
 
-    No API key required. See [Ollama Setup](../local-models/ollama.md) for the
-    full configuration — local models need `--provider openai` against Ollama's
-    OpenAI-compatible endpoint plus `--no-stream` and `--local-guards`.
+    No API key required. See [LM Studio Setup](../local-models/lm-studio.md)
+    for the full configuration — require the ruby_llm-providers-lms gem, then
+    run with `--provider lms` and `--local-guards`.
 
 The default provider/model is `openai` / `gpt-5.5` (see
 [Settings Reference](../configuration/settings.md)).

data/docs/index.md

@@ -68,7 +68,7 @@ See [The Iteration Loop](concepts/iteration-loop.md) for the full lifecycle.
   `robot-to --resume <run_id>` continues a stopped run and an external scheduler
   can drive it one commit per tick.
 - **Runs on local models.** With `--local-guards` it ships built-in file tools and
-  small-model guardrails, so it can drive a local Ollama model offline. See
+  small-model guardrails, so it can drive a local LM Studio model offline. See
   [Local Models](local-models/index.md).
 
 ---
@@ -80,7 +80,7 @@ See [The Iteration Loop](concepts/iteration-loop.md) for the full lifecycle.
 - :material-rocket-launch: **[Installation](getting-started/installation.md)** — install the gem and the `robot-to` CLI.
 - :material-play: **[Quick Start](getting-started/quick-start.md)** — your first overnight run in five minutes.
 - :material-cog: **[Configuration](configuration/index.md)** — every setting, the config cascade, and the CLI.
-- :material-laptop: **[Local Models](local-models/index.md)** — drive a local Ollama model with guardrails.
+- :material-laptop: **[Local Models](local-models/index.md)** — drive a local LM Studio model with guardrails.
 - :material-sitemap: **[Architecture](reference/architecture.md)** — how the pieces fit together.
 
 </div>
@@ -93,4 +93,4 @@ See [The Iteration Loop](concepts/iteration-loop.md) for the full lifecycle.
 - A git repository with at least one commit (the loop branches and commits there)
 - The [`robot_lab`](https://github.com/MadBomber/robot_lab) gem and an LLM provider
   (a cloud key such as `ANTHROPIC_API_KEY` / `OPENAI_API_KEY`, **or** a local
-  [Ollama](https://ollama.com) server)
+  [LM Studio](https://lmstudio.ai) server via ruby_llm-providers-lms)

data/docs/local-models/index.md

@@ -1,7 +1,7 @@
 # Local Models
 
 `robot_lab-to` can drive a **local** model — running entirely offline against an
-[Ollama](https://ollama.com) server — instead of a cloud API. This is the
+[LM Studio](https://lmstudio.ai) server via the `:lms` provider — instead of a cloud API. This is the
 "local assistant" mode: no API keys, no per-token cost, no data leaving your
 machine.
 
@@ -19,33 +19,31 @@ Both are enabled together with `--local-guards`.
 
 ```bash
 # 1. Serve a tool-capable model
-ollama pull gpt-oss:20b
+lms server start
+lms get qwen/qwen3.8-27b
 
 # 2. Run robot-to against it
 robot-to "Add a greet(name) method in greeter.rb" \
-  --provider openai \
-  --model gpt-oss:20b \
+  --provider lms \
+  --model qwen/qwen3.8-27b \
   --local-guards \
-  --no-stream \
   --max-iterations 5
 ```
 
-The full setup — including the RubyLLM configuration that points `:openai` at
-Ollama — is on the [Ollama Setup](ollama.md) page.
+The full setup — including requiring the ruby_llm-providers-lms gem — is on
+the [LM Studio Setup](lm-studio.md) page.
 
 ## Why these flags
 
-Driving a local model end-to-end requires three non-obvious settings. Each exists
-because of a concrete limitation discovered in testing:
+Driving a local model end-to-end takes two settings. Each exists because of a
+concrete limitation discovered in testing:
 
 | Flag / setting | Why |
 |----------------|-----|
-| `--provider openai` (+ Ollama base URL) | RubyLLM's native `:ollama` provider doesn't reliably get these models to emit tool calls. Routing through the `:openai` provider against Ollama's OpenAI-compatible `/v1` endpoint does. |
-| `--no-stream` | Ollama suppresses tool calls when the response is streamed. With streaming off, tool calls come through. |
+| `--provider lms` | The ruby_llm-providers-lms gem's LM Studio provider — no API key, and local model ids are assumed to exist. Its default `:chat_completions` protocol supports client tools, structured output, and streaming. |
 | `--local-guards` | Attaches the file tools the model needs to do work, plus guardrails that make those tools safe for a small model. |
 
-See [Ollama Setup → Streaming and tool calls](ollama.md#streaming-and-tool-calls)
-for the details.
+See [LM Studio Setup](lm-studio.md) for the details.
 
 ## The design philosophy
 
@@ -74,15 +72,14 @@ The model **must support tool calling**. In testing on an M2 Max:
 
 | Model | Size | Tool calls? | Notes |
 |-------|------|-------------|-------|
-| `gpt-oss:20b` | 20B | ✅ reliable | Called tools *and* `submit_iteration_result`; completed full runs cleanly. **Recommended.** |
-| `qwen3` | 8B | ✅ tools work | Created files via the write tool, but didn't reliably call `submit_iteration_result` (the final-report step). |
-| `phi4-mini` | 3.8B | ❌ | Explains instead of calling tools. |
+| `qwen/qwen3.8-27b` | 27B | ✅ reliable | Honors `tool_choice` and structured output; the right pick for the autonomous loop. **Recommended.** |
+| `openai/gpt-oss-20b` | 20B | ⚠️ partial | Accepts tool definitions but ignores `tool_choice: required`, and its structured output parses without meaning anything. Fine for simple chat, not for the loop. |
 
 Prefer a larger, instruction-following model for the autonomous loop — it has to
 both use tools *and* remember to submit its result every iteration.
 
 ---
 
-- [Ollama Setup](ollama.md) — install, serve, and configure.
+- [LM Studio Setup](lm-studio.md) — install, serve, and configure.
 - [Built-in Tools](tools.md) — what `read`/`write`/`edit`/`bash` do.
 - [Guardrails](guardrails.md) — the small-model safety policies.

data/docs/local-models/lm-studio.md

@@ -0,0 +1,92 @@
+# LM Studio Setup
+
+This page covers running `robot_lab-to` against a local
+[LM Studio](https://lmstudio.ai) server end-to-end, through the
+[ruby_llm-providers-lms](https://github.com/madbomber/ruby_llm-providers-lms)
+gem, which registers the `:lms` provider with RubyLLM.
+
+## 1. Install and start LM Studio
+
+Install LM Studio, then bootstrap its CLI and start the server:
+
+```bash
+lms bootstrap        # puts the `lms` CLI on your PATH
+lms server start     # serves on http://localhost:1234
+```
+
+## 2. Download a tool-capable model
+
+The model **must** support tool calling *and honor it*. `qwen/qwen3.8-27b` is
+the recommended choice — it obeys `tool_choice` and returns meaningful
+structured output, where `gpt-oss` models accept the request shape but ignore
+it (see [model selection](index.md#choosing-a-model)):
+
+```bash
+lms get qwen/qwen3.8-27b
+```
+
+## 3. Point RubyLLM at LM Studio
+
+`robot_lab-to` reaches the model through RobotLab / RubyLLM. Require the
+provider gem and, only if your server is not on the default endpoint,
+configure the base URL:
+
+```ruby
+require "ruby_llm"
+require "ruby_llm/providers/lms"
+require "robot_lab"
+require "robot_lab/to"
+
+RubyLLM.configure do |c|
+  c.lms_api_base    = "http://localhost:1234/v1"  # the default; override if needed
+  c.request_timeout = 600
+end
+
+RobotLab::To.run(
+  "Add a greet(name) method in greeter.rb",
+  provider: :lms,
+  model: "qwen/qwen3.8-27b",
+  local_guards: true,
+  max_iterations: 5
+)
+```
+
+No API key is needed — LM Studio's local server does not require one.
+
+## 4. Run
+
+From the launcher above, or from the CLI:
+
+```bash
+robot-to "Add a greet(name) method in greeter.rb" \
+  --provider lms \
+  --model qwen/qwen3.8-27b \
+  --local-guards \
+  --max-iterations 5
+```
+
+Because LM Studio is a local provider, RubyLLM assumes any model id you pass
+exists — LM Studio just-in-time loads the model if it isn't loaded yet. No
+registry refresh is needed.
+
+## Protocols
+
+LM Studio serves several API protocols on one port; the `:lms` provider
+defaults to `:chat_completions`, which is the most capable one here — client
+tools, structured output, streaming, and reasoning control all work. Stay on
+the default for `robot_lab-to`. See the
+[ruby_llm-providers-lms README](https://github.com/madbomber/ruby_llm-providers-lms)
+for the full protocol matrix.
+
+## Troubleshooting
+
+| Symptom | Cause | Fix |
+|---------|-------|-----|
+| Connection error naming `lms server start` | Server not running | `lms server start`. |
+| Tool calls accepted but ignored, or `{"name":"analysis","age":0}`-style junk from schemas | Model doesn't honor `tool_choice` / grammar output (e.g. `gpt-oss`) | Use `qwen/qwen3.8-27b`. |
+| Every iteration "did not submit" | Model too small to follow the final-report step | Use a larger model (e.g. `qwen/qwen3.8-27b`). |
+| No tool calls at all, model only explains | Model lacks tool support | Pick a tool-capable model. |
+
+---
+
+Next: [Built-in Tools](tools.md).

data/docs/reference/architecture.md

@@ -103,10 +103,10 @@ robot actually exposes the submit tool, guarding against that class of mistake.
 
 ### Streaming is optional
 
-By default the robot streams, enabling per-chunk token accounting and mid-stream
-budget enforcement. Local Ollama models run non-streaming (`stream: false`), so
-tokens are accounted from each iteration's result and the budget is enforced at
-iteration boundaries. See [Ollama Setup](../local-models/ollama.md#streaming-and-tool-calls).
+By default the robot streams, enabling per-chunk token accounting and
+mid-stream budget enforcement. Non-streaming runs (`stream: false`) account
+tokens from each iteration's result and enforce the budget at iteration
+boundaries. See [LM Studio Setup](../local-models/lm-studio.md).
 
 ### Interruptible by design
 

data/examples/01_basic_usage/basic_usage.rb

@@ -70,7 +70,7 @@ PROVIDER = ENV.fetch("RLTO_PROVIDER", LOCAL ? "lms" : "anthropic").to_sym
 MODEL    = ENV.fetch("RLTO_MODEL", LOCAL ? "qwen/qwen3.8-27b" : "claude-sonnet-4-6")
 
 # ruby_llm has no native "lms" adapter. "lms" is this example's friendly label for
-# "a local LM Studio model"; setup (common.rb) resolves it to RubyLLM's :openai
+# "a local LM Studio model"; setup (common.rb) resolves it to the :lms provider
 # adapter pointed at LM Studio, starting the server and loading MODEL as needed.
 # Everything passed to RobotLab uses the resolved provider; PROVIDER itself is
 # kept only for display.

data/examples/02_advanced_usage/advanced_usage.rb

@@ -25,7 +25,7 @@
 #       the robot must earn each commit on correctness AND quality.
 #
 # Models (per your request): reasoning on OpenAI gpt-5.5, building on local
-# LM Studio qwen/qwen3.8-27b. Because both use RubyLLM's :openai provider but different
+# LM Studio qwen/qwen3.8-27b. Because the phases use different providers and different
 # endpoints (api.openai.com vs LM Studio's /v1), and openai_api_base is global,
 # we toggle it between the (sequential) phases.
 #
@@ -98,9 +98,9 @@ def use_real_openai!
   RubyLLM.logger.level = Logger::ERROR # keep raw API traffic out of the feed
 end
 
-# Implementation phase routes the :openai provider at the local LM Studio endpoint
+# Implementation phase uses the :lms provider against the local LM Studio endpoint
 # (or whatever BUILD_PROVIDER resolves to). common.rb's setup starts the LM Studio
-# server and loads BUILD_MODEL as needed; the "lms" label resolves to :openai.
+# server and loads BUILD_MODEL as needed; the "lms" label resolves to the :lms provider.
 def use_build_provider!
   setup(provider: BUILD_PROVIDER, model: BUILD_MODEL)
 end

data/examples/03_scored/scored_run.rb

@@ -64,7 +64,7 @@ PROVIDER = ENV.fetch("RLTO_PROVIDER", LOCAL ? "lms" : "anthropic").to_sym
 MODEL    = ENV.fetch("RLTO_MODEL", LOCAL ? "qwen/qwen3.8-27b" : "claude-sonnet-4-6")
 
 # ruby_llm has no native "lms" adapter. "lms" is this example's friendly label for
-# "a local LM Studio model"; setup (common.rb) resolves it to RubyLLM's :openai
+# "a local LM Studio model"; setup (common.rb) resolves it to the :lms provider
 # adapter pointed at LM Studio, starting the server and loading MODEL as needed.
 # Everything passed to RobotLab uses the resolved provider; PROVIDER itself is
 # kept only for display.

data/examples/04_prose/prose_run.rb

@@ -65,7 +65,7 @@ JUDGE_MODEL = ENV.fetch("RLTO_JUDGE_MODEL", LOCAL ? "qwen/qwen3.8-27b" : "claude
 TOPIC       = ENV.fetch("RLTO_TOPIC", "writing good Git commit messages")
 
 # ruby_llm has no native "lms" adapter. "lms" is this example's friendly label for
-# "a local LM Studio model"; setup (common.rb) resolves it to RubyLLM's :openai
+# "a local LM Studio model"; setup (common.rb) resolves it to the :lms provider
 # adapter pointed at LM Studio, starting the server and loading each model as
 # needed -- once for the doer, again for the judge (a no-op if they're the same
 # model, or if it's already loaded). Everything passed to RobotLab uses the

data/examples/common.rb

@@ -12,12 +12,12 @@
 #   actual_provider = setup(provider: PROVIDER, model: MODEL)
 #   RobotLab::To.run(objective, provider: actual_provider, model: MODEL, ...)
 #
-# ruby_llm has no native "lms" adapter -- "lms" is this example suite's own
-# label for "a local LM Studio model". When `provider` is "lms", setup:
-#   1. points RubyLLM's :openai adapter at LMS_BASE_URL
+# "lms" is the ruby_llm-providers-lms gem's native LM Studio provider.
+# When `provider` is "lms", setup:
+#   1. points the :lms provider at LMS_BASE_URL
 #   2. starts the LM Studio server if it isn't already running
 #   3. loads `model` into LM Studio if it isn't already loaded
-# and returns :openai -- the RubyLLM-recognized provider to pass to RobotLab.
+# and returns :lms -- the RubyLLM-recognized provider to pass to RobotLab.
 # Any other provider (a cloud one) passes straight through untouched; setup
 # does nothing else for it (the example configures its own API key as before).
 #
@@ -32,6 +32,7 @@ require "open3"
 require "uri"
 
 require "ruby_llm"
+require "ruby_llm/providers/lms"
 
 LMS_BASE_URL = ENV.fetch("LMS_BASE_URL", "http://localhost:1234/v1")
 
@@ -44,7 +45,7 @@ def setup(provider: ENV.fetch("RLTO_PROVIDER", "lms"), model: ENV.fetch("RLTO_MO
   configure_lms!
   ensure_lms_server_running!
   ensure_lms_model_loaded!(model)
-  :openai
+  :lms
 end
 
 def teardown
@@ -58,18 +59,14 @@ at_exit { teardown }
 
 # --- internals ---------------------------------------------------------------
 
-# Route RubyLLM's :openai provider at LM Studio's OpenAI-compatible endpoint and
-# refresh the registry so tool attachment works.
+# Point the :lms provider at the LM Studio endpoint. Local models are assumed
+# to exist, so no registry refresh is needed.
 def configure_lms!
   RubyLLM.configure do |c|
-    c.openai_api_base = LMS_BASE_URL
-    c.openai_api_key  = "lm-studio" # ignored by LM Studio, but RubyLLM wants a value
+    c.lms_api_base    = LMS_BASE_URL
     c.request_timeout = 600
   end
   RubyLLM.logger.level = Logger::ERROR
-  RubyLLM.models.refresh!
-rescue StandardError => e
-  warn "warning: could not refresh LM Studio models (#{e.class}: #{e.message})"
 end
 
 def lms_server_running?

data/lib/robot_lab/to/orchestrator.rb

@@ -597,10 +597,14 @@ module RobotLab
         tools + [Tools::Read.new, Tools::Write.new, Tools::Edit.new, Tools::Bash.new]
       end
 
+      # :reek:TooManyStatements -- the streaming callback accumulates usage and enforces the stop in one place.
       def token_tracker
         lambda do |chunk|
-          @run.input_tokens  += chunk.input_tokens.to_i
-          @run.output_tokens += chunk.output_tokens.to_i
+          # ruby_llm 2.0 nests counts under chunk.tokens (usually only on the
+          # final chunk of a stream).
+          tokens = chunk.respond_to?(:tokens) ? chunk.tokens : nil
+          @run.input_tokens  += tokens&.input.to_i
+          @run.output_tokens += tokens&.output.to_i
 
           return unless @stop_conditions.token_limit_exceeded?
 

data/lib/robot_lab/to/tools/bash.rb

@@ -17,8 +17,8 @@ module RobotLab
           output and exit status. Use for building, testing, listing, and git.
         DESC
 
-        param :command, type: "string", desc: "The shell command to run"
-        param :timeout, type: "integer", desc: "Seconds before the command is killed", required: false
+        parameter :command, type: "string", description: "The shell command to run"
+        parameter :timeout, type: "integer", description: "Seconds before the command is killed", required: false
 
         def initialize(robot: nil, timeout: DEFAULT_TIMEOUT)
           super(robot: robot)

data/lib/robot_lab/to/tools/edit.rb

@@ -14,10 +14,10 @@ module RobotLab
           replace_all is true. Read the file first to get the exact text.
         DESC
 
-        param :path, type: "string", desc: "Path of the file to edit"
-        param :old_text, type: "string", desc: "Exact text to replace"
-        param :new_text, type: "string", desc: "Replacement text"
-        param :replace_all, type: "boolean", desc: "Replace every occurrence", required: false
+        parameter :path, type: "string", description: "Path of the file to edit"
+        parameter :old_text, type: "string", description: "Exact text to replace"
+        parameter :new_text, type: "string", description: "Replacement text"
+        parameter :replace_all, type: "boolean", description: "Replace every occurrence", required: false
 
         # :reek:BooleanParameter -- replace_all is a tool param the LLM sets;
         # the `param` declarations above fix this signature.

data/lib/robot_lab/to/tools/read.rb

@@ -14,9 +14,9 @@ module RobotLab
           start line) and limit (max lines). Always read a file before editing it.
         DESC
 
-        param :path, type: "string", desc: "Path to the file to read"
-        param :offset, type: "integer", desc: "1-based first line to return", required: false
-        param :limit, type: "integer", desc: "Maximum number of lines to return", required: false
+        parameter :path, type: "string", description: "Path to the file to read"
+        parameter :offset, type: "integer", description: "1-based first line to return", required: false
+        parameter :limit, type: "integer", description: "Maximum number of lines to return", required: false
 
         def execute(path:, offset: nil, limit: nil, **)
           resolved = File.expand_path(path, Dir.pwd)

data/lib/robot_lab/to/tools/request_decision.rb

@@ -25,20 +25,20 @@ module RobotLab
           for routine engineering choices you are equipped to make yourself.
         DESC
 
-        param :question, type: "string",
-                         desc: "The decision that needs a human answer, phrased as a question"
+        parameter :question, type: "string",
+                         description: "The decision that needs a human answer, phrased as a question"
 
-        param :situation, type: "string",
-                          desc: "Why this needs a human and what is at stake", required: false
+        parameter :situation, type: "string",
+                          description: "Why this needs a human and what is at stake", required: false
 
-        param :options, type: "array",
-                        desc: "The distinct options you see (strings)", required: false
+        parameter :options, type: "array",
+                        description: "The distinct options you see (strings)", required: false
 
-        param :recommendation, type: "string",
-                               desc: "Your recommended option and the reasoning behind it", required: false
+        parameter :recommendation, type: "string",
+                               description: "Your recommended option and the reasoning behind it", required: false
 
-        param :blocking, type: "boolean",
-                         desc: "true if work cannot correctly proceed until this is answered", required: false
+        parameter :blocking, type: "boolean",
+                         description: "true if work cannot correctly proceed until this is answered", required: false
 
         def captured_requests
           @captured_requests ||= []

data/lib/robot_lab/to/tools/submit_result.rb

@@ -13,23 +13,23 @@ module RobotLab
           FINAL action before finishing. Do not call it until your work is complete.
         DESC
 
-        param :success, type: "boolean",
-                        desc: "true if you made meaningful progress toward the objective; " \
-                              "false if you made no meaningful changes AND have no new learnings"
+        parameter :success, type: "boolean",
+                        description: "true if you made meaningful progress toward the objective; " \
+                                     "false if you made no meaningful changes AND have no new learnings"
 
-        param :summary, type: "string",
-                        desc: "Brief one-sentence description of what you accomplished or why you stopped"
+        parameter :summary, type: "string",
+                        description: "Brief one-sentence description of what you accomplished or why you stopped"
 
-        param :key_changes, type: "array",
-                            desc: "List of files or changes made this iteration (empty if none)",
+        parameter :key_changes, type: "array",
+                            description: "List of files or changes made this iteration (empty if none)",
                             required: false
 
-        param :key_learnings, type: "array",
-                              desc: "Insights worth remembering for future iterations (empty if none)",
+        parameter :key_learnings, type: "array",
+                              description: "Insights worth remembering for future iterations (empty if none)",
                               required: false
 
-        param :should_fully_stop, type: "boolean",
-                                  desc: "Set to true only when instructed by a stop condition",
+        parameter :should_fully_stop, type: "boolean",
+                                  description: "Set to true only when instructed by a stop condition",
                                   required: false
 
         attr_reader :captured_result

data/lib/robot_lab/to/tools/write.rb

@@ -15,8 +15,8 @@ module RobotLab
           do not exist yet; to change an existing file, use Edit.
         DESC
 
-        param :path, type: "string", desc: "Path of the file to create"
-        param :content, type: "string", desc: "Full text content to write"
+        parameter :path, type: "string", description: "Path of the file to create"
+        parameter :content, type: "string", description: "Full text content to write"
 
         def execute(path:, content:, **)
           resolved = File.expand_path(path, Dir.pwd)

data/lib/robot_lab/to/version.rb

@@ -2,6 +2,6 @@
 
 module RobotLab
   module To
-    VERSION = "0.2.8"
+    VERSION = "0.3.0"
   end
 end

data/lib/robot_lab/to.rb

@@ -44,6 +44,7 @@ module RobotLab
       # @return [void]
       def run(objective, **)
         config = Config.new(**)
+        ensure_provider_loaded(config.provider)
         suppress_llm_logging unless config.debug?
         Orchestrator.new(objective, config).run
       end
@@ -52,6 +53,7 @@ module RobotLab
       # objective and prior state are loaded from the run's run.json.
       def resume(run_id, **)
         config = Config.new(**)
+        ensure_provider_loaded(config.provider)
         suppress_llm_logging unless config.debug?
         Orchestrator.new(nil, config, resume_run_id: run_id).run
       end
@@ -66,6 +68,26 @@ module RobotLab
 
       private
 
+      # Provider gems register themselves on require by convention
+      # (ruby_llm-providers-<name> defines ruby_llm/providers/<name>). When the
+      # configured provider isn't registered yet — e.g. `robot-to --provider
+      # lms` from the CLI — try that conventional require so the user doesn't
+      # need a wrapper script. A miss falls through to RubyLLM's own "Unknown
+      # provider" error at request time.
+      def ensure_provider_loaded(provider)
+        return unless provider
+        return unless defined?(RubyLLM::Provider)
+
+        name = provider.to_s
+        return if RubyLLM::Provider.resolve(name)
+
+        begin
+          require "ruby_llm/providers/#{name}"
+        rescue LoadError
+          # Not a provider-gem provider; RubyLLM will report it if truly unknown.
+        end
+      end
+
       def suppress_llm_logging
         require "logger"
         null = Logger.new(File::NULL)

data/mkdocs.yml

@@ -136,7 +136,7 @@ nav:
       - CLI Reference: configuration/cli.md
   - Local Models:
       - Overview: local-models/index.md
-      - Ollama Setup: local-models/ollama.md
+      - LM Studio Setup: local-models/lm-studio.md
       - Built-in Tools: local-models/tools.md
       - Guardrails: local-models/guardrails.md
   - Reference:

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: robot_lab-to
 version: !ruby/object:Gem::Version
-  version: 0.2.8
+  version: 0.3.0
 platform: ruby
 authors:
 - Dewayne VanHoozer
@@ -13,16 +13,16 @@ dependencies:
   name: robot_lab
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.1'
+        version: 0.3.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.1'
+        version: 0.3.0
 - !ruby/object:Gem::Dependency
   name: myway_config
   requirement: !ruby/object:Gem::Requirement
@@ -83,7 +83,7 @@ files:
 - docs/index.md
 - docs/local-models/guardrails.md
 - docs/local-models/index.md
-- docs/local-models/ollama.md
+- docs/local-models/lm-studio.md
 - docs/local-models/tools.md
 - docs/reference/architecture.md
 - examples/.envrc
@@ -172,7 +172,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.20
+rubygems_version: 4.0.21
 specification_version: 4
 summary: Autonomous overnight agent loop for RobotLab — run robots while you sleep.
 test_files: []

data/docs/local-models/ollama.md

@@ -1,122 +0,0 @@
-# Ollama Setup
-
-This page covers running `robot_lab-to` against a local
-[Ollama](https://ollama.com) server end-to-end.
-
-## 1. Install and start Ollama
-
-```bash
-# macOS / Linux
-curl -fsSL https://ollama.com/install.sh | sh
-
-# Ollama runs a server on http://localhost:11434
-```
-
-## 2. Pull a tool-capable model
-
-The model **must** support tool calling. `gpt-oss:20b` is the recommended choice
-(see [model selection](index.md#choosing-a-model)):
-
-```bash
-ollama pull gpt-oss:20b
-```
-
-You can confirm a model advertises tool support:
-
-```bash
-curl -s http://localhost:11434/api/tags | jq '.models[] | {name, caps: .capabilities}'
-```
-
-## 3. Point RubyLLM at Ollama
-
-`robot_lab-to` reaches the model through RobotLab / RubyLLM. The robust path is
-the **`:openai` provider** aimed at Ollama's OpenAI-compatible `/v1` endpoint.
-Configure RubyLLM once, before launching the run:
-
-```ruby
-require "ruby_llm"
-require "robot_lab"
-require "robot_lab/to"
-
-RubyLLM.configure do |c|
-  c.openai_api_base = "http://localhost:11434/v1"
-  c.openai_api_key  = "ollama"   # ignored by Ollama, but RubyLLM requires a value
-  c.request_timeout = 600
-end
-
-RobotLab::To.run(
-  "Add a greet(name) method in greeter.rb",
-  provider: :openai,
-  model: "gpt-oss:20b",
-  local_guards: true,
-  stream: false,
-  max_iterations: 5
-)
-```
-
-!!! note "Why a wrapper script"
-    The Ollama base-URL configuration lives in RubyLLM's global config, so it's
-    set in a small Ruby launcher (as above) rather than via a `robot-to` CLI flag.
-    The CLI flags `--provider openai --model gpt-oss:20b --local-guards --no-stream`
-    cover the rest; only the base URL needs the wrapper. You can also set it in
-    your application's RubyLLM initializer.
-
-## 4. Run
-
-From the launcher above, or — once the base URL is configured in your environment
-— from the CLI:
-
-```bash
-robot-to "Add a greet(name) method in greeter.rb" \
-  --provider openai \
-  --model gpt-oss:20b \
-  --local-guards \
-  --no-stream \
-  --max-iterations 5
-```
-
-## Streaming and tool calls
-
-**Local Ollama models must run non-streaming** (`--no-stream` / `stream: false`).
-
-Ollama's OpenAI-compatible endpoint suppresses tool calls when the response is
-streamed — the model "thinks" but never emits a tool call, so the robot can't do
-any work. With streaming disabled, tool calls come through normally.
-
-The trade-off: streaming is what enables per-chunk token accounting and
-mid-iteration token-budget enforcement. With `--no-stream`, tokens are accounted
-from each iteration's *result* instead, and `--max-tokens` is enforced at
-iteration boundaries rather than mid-stream. For overnight local runs this is
-almost always fine.
-
-## Why not the native `:ollama` provider?
-
-RubyLLM ships a native `:ollama` provider, but in testing it did **not** reliably
-get tool-capable models (e.g. qwen3) to emit tool calls — the same model tool-calls
-correctly through the `:openai` provider against Ollama's `/v1` endpoint. Until
-that changes, prefer `provider: :openai` + `openai_api_base` for `robot_lab-to`.
-
-## Registering models (if needed)
-
-RubyLLM validates models against its registry. `robot_lab-to` sets
-`assume_model_exists` when a provider is given, which is enough for a bare chat —
-but attaching tools triggers a capability lookup that can raise
-`ModelNotFoundError` for an unregistered model. If you hit that, refresh the
-registry so your local models are known:
-
-```ruby
-RubyLLM.models.refresh!   # discovers locally-served Ollama models
-```
-
-## Troubleshooting
-
-| Symptom | Cause | Fix |
-|---------|-------|-----|
-| Model thinks but never calls a tool | Streaming is on | Add `--no-stream`. |
-| `RobotLab::ModelNotFoundError` when tools attach | Model not in RubyLLM registry | `RubyLLM.models.refresh!`. |
-| Every iteration "did not submit" | Model too small to follow the final-report step | Use a larger model (e.g. `gpt-oss:20b`). |
-| No tool calls at all, model only explains | Model lacks tool support | Pick a model whose `capabilities` include `tools`. |
-
----
-
-Next: [Built-in Tools](tools.md).