thinkless 0.2.0__tar.gz → 0.4.0__tar.gz

{thinkless-0.2.0 → thinkless-0.4.0}/CHANGELOG.md

@@ -6,6 +6,62 @@ All notable changes are recorded here. The format follows
 
 ## Unreleased
 
+## 0.4.0 - 2026-09-25
+
+The decision benchmark.
+
+### Added
+
+- The decision benchmark 1.0 (`thinkless bench decisions`): eight public
+  tasks across the four question kinds (banking77, clinc150 with out of
+  scope, MASSIVE in five languages, MultiWOZ 2.2 conversations, jailbreaks,
+  Civil Comments toxicity, HelpSteer2 helpfulness ratings and WNUT 2017
+  entities), with frozen rows and published hashes, calibration rows from a
+  separate split, result files that hold every prediction, `verify` that
+  recomputes every metric, a generated leaderboard and open submissions.
+  Baselines for GLiNER 2.5, Laya, Qwen3-1.7B and Qwen 3.7 Flash.
+
+### Changed
+
+- A list of chat messages now renders as `role: text` lines for providers
+  that read text, instead of one `key: value` line per field.
+- README links to the documentation point at the documentation site.
+
+## 0.3.0 - 2026-09-25
+
+Shadow mode, framework adapters, limits, a decision server and MCP tools.
+
+### Added
+
+- Shadow mode (`thinkless.shadow`): run a candidate engine next to existing
+  decision code without changing what it returns, log both answers, and
+  report agreement with a 95% interval, the share settled without an LLM,
+  cost and latency on both sides, thresholds fitted on production traffic,
+  and a verdict per question (`thinkless shadow report`). Disagreements
+  export as labeling rows (`thinkless shadow export`). The same class audits
+  a live engine against an LLM.
+- Framework adapters (`thinkless.integrations`): a LangGraph router, decision
+  node and async decision node; OpenAI Agents SDK input guardrails, tool input
+  guardrails and `route_agent`; and framework-neutral `Router`, `route` and
+  `gate`, tested with LangChain tools and Pydantic AI. Extras `langgraph` and
+  `openai-agents`.
+- Engine deadlines (`deadline_ms` on the engine and per call), spend limits
+  (`SpendLimit`, lifetime or rolling window) and per-run caps
+  (`engine.run(..., max_cost_usd=...)`). Skipped providers are recorded with
+  reason `deadline` or `spend_limit`.
+- A decision server (`thinkless serve`, `thinkless.server.app.create_app`)
+  with `/v1/decide` and a System One compatible `/v1/systemone`, so another
+  engine's `SystemOne` provider, or TypeSafe's SDK, can use it. Extra
+  `server`.
+- MCP tools (`thinkless mcp`, `thinkless.server.mcp.create_mcp_server`): one
+  `decide_<question>` tool per registered question. Extra `mcp`.
+- `thinkless trace export` turns traced decisions into labeling rows, and
+  `thinkless trace drift` compares two periods and exits with 1 when a
+  question drifted.
+- `question_from_spec` rebuilds a question from its spec.
+- Docs: an integrations section, a migration guide, shadow mode, serving,
+  a pilot playbook and a FAQ, published to GitHub Pages by a new workflow.
+
 ## 0.2.0 - 2026-09-25
 
 First release on PyPI.

{thinkless-0.2.0 → thinkless-0.4.0}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.5
 Name: thinkless
-Version: 0.2.0
+Version: 0.4.0
 Summary: The decision plane for AI agents. Rules and small calibrated models make the routine decisions, the LLM is reserved for the steps that need thought, and every step is traced.
 Project-URL: Homepage, https://github.com/inboxpraveen/ThinkLess
-Project-URL: Documentation, https://github.com/inboxpraveen/ThinkLess/tree/main/docs
+Project-URL: Documentation, https://inboxpraveen.github.io/ThinkLess/
 Project-URL: Repository, https://github.com/inboxpraveen/ThinkLess
 Project-URL: Issues, https://github.com/inboxpraveen/ThinkLess/issues
 Project-URL: Changelog, https://github.com/inboxpraveen/ThinkLess/blob/main/CHANGELOG.md
@@ -34,8 +34,12 @@ Provides-Extra: all
 Requires-Dist: accelerate>=1.0; extra == 'all'
 Requires-Dist: anthropic>=1.0; extra == 'all'
 Requires-Dist: datasets>=3.0; extra == 'all'
+Requires-Dist: fastapi>=0.115; extra == 'all'
 Requires-Dist: gliner2[local]<3,>=2.0; extra == 'all'
+Requires-Dist: langgraph>=1.0; extra == 'all'
 Requires-Dist: laya<0.4,>=0.3.20; extra == 'all'
+Requires-Dist: mcp>=1.10; extra == 'all'
+Requires-Dist: openai-agents>=0.22; extra == 'all'
 Requires-Dist: openai>=2.0; extra == 'all'
 Requires-Dist: opentelemetry-api>=1.25; extra == 'all'
 Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.25; extra == 'all'
@@ -44,14 +48,20 @@ Requires-Dist: protobuf>=4.25; extra == 'all'
 Requires-Dist: sentencepiece>=0.2; extra == 'all'
 Requires-Dist: torch>=2.1; extra == 'all'
 Requires-Dist: transformers<5,>=4.48; extra == 'all'
+Requires-Dist: uvicorn>=0.30; extra == 'all'
 Provides-Extra: anthropic
 Requires-Dist: anthropic>=1.0; extra == 'anthropic'
 Provides-Extra: bench
 Requires-Dist: datasets>=3.0; extra == 'bench'
 Provides-Extra: dev
+Requires-Dist: fastapi>=0.115; extra == 'dev'
+Requires-Dist: langgraph>=1.0; extra == 'dev'
+Requires-Dist: mcp>=1.10; extra == 'dev'
 Requires-Dist: mkdocs-material>=9.5; extra == 'dev'
 Requires-Dist: mkdocstrings[python]>=0.26; extra == 'dev'
 Requires-Dist: mypy>=1.10; extra == 'dev'
+Requires-Dist: openai-agents>=0.22; extra == 'dev'
+Requires-Dist: pydantic-ai-slim>=1.0; extra == 'dev'
 Requires-Dist: pytest-cov>=5; extra == 'dev'
 Requires-Dist: pytest>=8; extra == 'dev'
 Requires-Dist: ruff>=0.6; extra == 'dev'
@@ -61,6 +71,8 @@ Requires-Dist: gliner2[local]<3,>=2.0; extra == 'gliner'
 Requires-Dist: protobuf>=4.25; extra == 'gliner'
 Requires-Dist: sentencepiece>=0.2; extra == 'gliner'
 Requires-Dist: transformers<5,>=4.48; extra == 'gliner'
+Provides-Extra: langgraph
+Requires-Dist: langgraph>=1.0; extra == 'langgraph'
 Provides-Extra: laya
 Requires-Dist: laya<0.4,>=0.3.20; extra == 'laya'
 Requires-Dist: transformers<5,>=4.48; extra == 'laya'
@@ -76,12 +88,19 @@ Provides-Extra: local-llm
 Requires-Dist: accelerate>=1.0; extra == 'local-llm'
 Requires-Dist: torch>=2.1; extra == 'local-llm'
 Requires-Dist: transformers<5,>=4.48; extra == 'local-llm'
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.10; extra == 'mcp'
 Provides-Extra: openai
 Requires-Dist: openai>=2.0; extra == 'openai'
+Provides-Extra: openai-agents
+Requires-Dist: openai-agents>=0.22; extra == 'openai-agents'
 Provides-Extra: otel
 Requires-Dist: opentelemetry-api>=1.25; extra == 'otel'
 Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.25; extra == 'otel'
 Requires-Dist: opentelemetry-sdk>=1.25; extra == 'otel'
+Provides-Extra: server
+Requires-Dist: fastapi>=0.115; extra == 'server'
+Requires-Dist: uvicorn>=0.30; extra == 'server'
 Description-Content-Type: text/markdown
 
 <h1 align="center">ThinkLess</h1>
@@ -93,7 +112,7 @@ Description-Content-Type: text/markdown
   <a href="https://github.com/inboxpraveen/ThinkLess/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/inboxpraveen/ThinkLess/actions/workflows/ci.yml/badge.svg"></a>
   <a href="https://github.com/inboxpraveen/ThinkLess/blob/main/LICENSE"><img alt="License: Apache 2.0" src="https://img.shields.io/badge/license-Apache%202.0-blue.svg"></a>
   <img alt="Python 3.10+" src="https://img.shields.io/badge/python-3.10%2B-blue.svg">
-  <a href="https://github.com/inboxpraveen/ThinkLess/blob/main/docs/benchmarks.md"><img alt="Benchmarks" src="https://img.shields.io/badge/benchmarks-reproducible-brightgreen.svg"></a>
+  <a href="https://inboxpraveen.github.io/ThinkLess/benchmarks/"><img alt="Benchmarks" src="https://img.shields.io/badge/benchmarks-reproducible-brightgreen.svg"></a>
 </p>
 
 ThinkLess is an open-source decision plane for AI agents. The routine
@@ -140,7 +159,7 @@ if intent.is_("refund_duplicate_charge"):       # only true when the answer is c
 Same agent, same 53 labeled support tickets, two decision planes: `llm` sends
 every decision to the LLM, `hybrid` asks rules, GLiNER and Laya first. Hosted
 models ran through OpenRouter, and the dollar figures are what OpenRouter
-billed ([full results](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/benchmarks.md)):
+billed ([full results](https://inboxpraveen.github.io/ThinkLess/benchmarks/)):
 
 | Fallback LLM | Success, `llm` | Success, `hybrid` | Billed per 1k tickets, `llm` | Billed per 1k tickets, `hybrid` | Decision time |
 |---|---:|---:|---:|---:|---:|
@@ -166,7 +185,7 @@ billed ([full results](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/
   validated on a separate calibration set first. The baseline is the
   strongest form of the LLM design: all six triage questions in one prompt.
 - The support set is 53 synthetic tickets: evidence of the mechanism and its
-  failure modes, not a leaderboard. The [benchmarks page](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/benchmarks.md)
+  failure modes, not a leaderboard. The [benchmarks page](https://inboxpraveen.github.io/ThinkLess/benchmarks/)
   lists the weak areas found and what was done about each.
 
 ## Quick start
@@ -229,6 +248,51 @@ No GPU? `pip install thinkless` and run
 [`examples/01_rules_only.py`](https://github.com/inboxpraveen/ThinkLess/blob/main/examples/01_rules_only.py): the API, the cascade
 and the traces with no model downloads.
 
+## Use it in your agent
+
+ThinkLess sits inside the framework you already use, at the points where the
+agent decides something: which path to take, whether an input is safe,
+whether a tool call is inside policy. Uncertain decisions go to the code you
+run today, so nothing gets worse while the routine ones get cheaper.
+
+```python
+from thinkless.integrations.langgraph import router
+
+intent = router(engine, INTENT, {"order_status": "tracking", "refund": "refunds"},
+                default="agent")          # your existing LLM node
+builder.add_conditional_edges(START, intent, intent.destinations)
+```
+
+- [LangGraph](https://inboxpraveen.github.io/ThinkLess/integrations/langgraph/):
+  routers, decision nodes and gated tools.
+- [OpenAI Agents SDK](https://inboxpraveen.github.io/ThinkLess/integrations/openai-agents/):
+  input guardrails, tool guardrails and routing to a specialist agent.
+- [Any framework](https://inboxpraveen.github.io/ThinkLess/integrations/any-framework/):
+  `route` and `gate` for Pydantic AI, a hand-written loop, or anything else.
+
+Before switching anything, measure it. Shadow mode runs ThinkLess next to your
+current code on live traffic and reports, per decision, the agreement with a
+confidence interval and what it would save:
+
+```python
+from thinkless.shadow import Shadow
+
+shadow = Shadow(engine, log="shadow/intent.jsonl", sample=0.2)
+
+@shadow.watch(INTENT, cost_usd=0.0004)    # today's cost per call
+def classify(message: str) -> str:
+    ...                                    # unchanged, and still what users get
+```
+
+```bash
+thinkless shadow report shadow/intent.jsonl --volume 2000000
+```
+
+The [migration guide](https://inboxpraveen.github.io/ThinkLess/guides/migration/)
+walks through it, and the [FAQ](https://inboxpraveen.github.io/ThinkLess/faq/)
+covers the common questions. To share one engine across services, run it as
+a [decision server or MCP tools](https://inboxpraveen.github.io/ThinkLess/guides/serving/).
+
 ## Try the demo agent
 
 A complete customer support agent ships with the package: a mock store with
@@ -250,31 +314,31 @@ thinkless bench intents --dataset banking77
 **Typed questions.** `Choice`, `Score`, `YesNo` and `Extract` declare what you
 want to know and which answers are allowed. They follow the System One wire
 format, so the same question works on every provider.
-[Questions](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/questions.md)
+[Questions](https://inboxpraveen.github.io/ThinkLess/concepts/questions/)
 
 **A confidence cascade.** Providers are tried cheapest first. Each gets one
 call with every open question it supports; answers that clear their threshold
 close, the rest move on. Unresolved questions come back `uncertain` with the
 best answer seen, and `decision.is_()` never matches an uncertain answer.
-[The cascade](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/cascade.md)
+[The cascade](https://inboxpraveen.github.io/ThinkLess/concepts/cascade/)
 
 **One meaning of confidence.** Providers disagree about what "confidence"
 means (Laya and TypeSafe compute it differently), so a threshold of 0.8 would
 mean different things per backend. ThinkLess derives a single normalized
 confidence from each provider's probabilities.
-[Confidence](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/confidence.md)
+[Confidence](https://inboxpraveen.github.io/ThinkLess/concepts/confidence/)
 
 **Thresholds from data.** `thinkless calibrate` sweeps thresholds on labeled
 examples and recommends the lowest one that meets your accuracy target, per
 question and per provider (`thresholds={"intent@gliner": 0.9}`).
-[Calibration](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/calibration.md)
+[Calibration](https://inboxpraveen.github.io/ThinkLess/guides/calibration/)
 
 **Traces for everything.** Decisions, provider attempts, generations, tool
 calls and rule checks are spans with W3C-compatible ids. Write JSONL audit
 files, export to any OpenTelemetry backend with GenAI semantic conventions, or
 open the self-contained HTML viewer. Content capture can be switched off
 without losing structure, timings or confidences.
-[Tracing](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/tracing.md)
+[Tracing](https://inboxpraveen.github.io/ThinkLess/concepts/tracing/)
 
 ## Providers and backends
 
@@ -294,32 +358,44 @@ without losing structure, timings or confidences.
 | `OpenAICompatibleLLM` | OpenAI, Ollama, vLLM, LM Studio, llama.cpp, Groq |
 | `AnthropicLLM` | Claude, with server-side refusal fallbacks |
 
-Writing your own provider is one class. [Providers](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/providers.md),
-[LLM backends](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/llm-backends.md)
+Writing your own provider is one class. [Providers](https://inboxpraveen.github.io/ThinkLess/guides/providers/),
+[LLM backends](https://inboxpraveen.github.io/ThinkLess/guides/llm-backends/)
 
 ## Documentation
 
-- [Getting started](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/getting-started.md)
-- Concepts: [the four planes](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/planes.md),
-  [questions](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/questions.md),
-  [confidence](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/confidence.md),
-  [the cascade](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/cascade.md),
-  [tracing](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/tracing.md)
-- Guides: [the support agent](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/support-agent.md),
-  [calibration](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/calibration.md),
-  [providers](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/providers.md),
-  [LLM backends](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/llm-backends.md),
-  [production](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/production.md),
-  [troubleshooting](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/troubleshooting.md)
-- [Benchmarks](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/benchmarks.md), [CLI reference](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/reference/cli.md),
-  [Python API](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/reference/api.md), [roadmap](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/roadmap.md)
+- [Getting started](https://inboxpraveen.github.io/ThinkLess/getting-started/),
+  [installation](https://inboxpraveen.github.io/ThinkLess/guides/installation/)
+- Use it in your agent: [overview](https://inboxpraveen.github.io/ThinkLess/integrations/),
+  [LangGraph](https://inboxpraveen.github.io/ThinkLess/integrations/langgraph/),
+  [OpenAI Agents SDK](https://inboxpraveen.github.io/ThinkLess/integrations/openai-agents/),
+  [any framework](https://inboxpraveen.github.io/ThinkLess/integrations/any-framework/),
+  [migration](https://inboxpraveen.github.io/ThinkLess/guides/migration/),
+  [shadow mode](https://inboxpraveen.github.io/ThinkLess/guides/shadow-mode/),
+  [FAQ](https://inboxpraveen.github.io/ThinkLess/faq/)
+- Concepts: [the four planes](https://inboxpraveen.github.io/ThinkLess/concepts/planes/),
+  [questions](https://inboxpraveen.github.io/ThinkLess/concepts/questions/),
+  [confidence](https://inboxpraveen.github.io/ThinkLess/concepts/confidence/),
+  [the cascade](https://inboxpraveen.github.io/ThinkLess/concepts/cascade/),
+  [tracing](https://inboxpraveen.github.io/ThinkLess/concepts/tracing/)
+- Guides: [the support agent](https://inboxpraveen.github.io/ThinkLess/guides/support-agent/),
+  [calibration](https://inboxpraveen.github.io/ThinkLess/guides/calibration/),
+  [providers](https://inboxpraveen.github.io/ThinkLess/guides/providers/),
+  [LLM backends](https://inboxpraveen.github.io/ThinkLess/guides/llm-backends/),
+  [production](https://inboxpraveen.github.io/ThinkLess/guides/production/),
+  [serving](https://inboxpraveen.github.io/ThinkLess/guides/serving/),
+  [running a pilot](https://inboxpraveen.github.io/ThinkLess/guides/pilot/),
+  [troubleshooting](https://inboxpraveen.github.io/ThinkLess/guides/troubleshooting/)
+- [Benchmarks](https://inboxpraveen.github.io/ThinkLess/benchmarks/), [CLI reference](https://inboxpraveen.github.io/ThinkLess/reference/cli/),
+  [Python API](https://inboxpraveen.github.io/ThinkLess/reference/api/), [roadmap](https://inboxpraveen.github.io/ThinkLess/roadmap/)
 
 ## Status
 
-ThinkLess is at 0.1: the core API (questions, the engine, decisions and
-traces) is meant to stay stable, and providers and benchmarks will grow.
-Next up are shadow mode, calibration from traces, calibrated LLM confidence
-from log probabilities, and live Jev runs. See the [roadmap](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/roadmap.md).
+ThinkLess is pre-1.0: the core API (questions, the engine, decisions and
+traces) is meant to stay stable, and providers, adapters and benchmarks will
+grow. The [decision benchmark](https://inboxpraveen.github.io/ThinkLess/decision-benchmark/)
+compares decision models on eight public tasks and is open to submissions.
+Next up are more models on it, cross-request batching in the server, and
+calibrated LLM confidence from log probabilities. See the [roadmap](https://inboxpraveen.github.io/ThinkLess/roadmap/).
 
 ## Contributing
 
@@ -332,8 +408,12 @@ and after from `thinkless bench` or `thinkless calibrate`.
 
 If ThinkLess saves your team time or money, consider
 [sponsoring its development](https://github.com/sponsors/inboxpraveen).
-Sponsorship funds frontier-model benchmark runs, more providers and more
-demos.
+
+Model vendors can sponsor runs of their models on the
+[decision benchmark](https://inboxpraveen.github.io/ThinkLess/decision-benchmark/).
+Sponsored runs are done by the maintainers and published as verified,
+whatever the result: sponsorship buys runs, not rankings. Sponsorship also
+funds more providers and more demos.
 
 ## Citing
 

{thinkless-0.2.0 → thinkless-0.4.0}/README.md

@@ -7,7 +7,7 @@
   <a href="https://github.com/inboxpraveen/ThinkLess/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/inboxpraveen/ThinkLess/actions/workflows/ci.yml/badge.svg"></a>
   <a href="https://github.com/inboxpraveen/ThinkLess/blob/main/LICENSE"><img alt="License: Apache 2.0" src="https://img.shields.io/badge/license-Apache%202.0-blue.svg"></a>
   <img alt="Python 3.10+" src="https://img.shields.io/badge/python-3.10%2B-blue.svg">
-  <a href="https://github.com/inboxpraveen/ThinkLess/blob/main/docs/benchmarks.md"><img alt="Benchmarks" src="https://img.shields.io/badge/benchmarks-reproducible-brightgreen.svg"></a>
+  <a href="https://inboxpraveen.github.io/ThinkLess/benchmarks/"><img alt="Benchmarks" src="https://img.shields.io/badge/benchmarks-reproducible-brightgreen.svg"></a>
 </p>
 
 ThinkLess is an open-source decision plane for AI agents. The routine
@@ -54,7 +54,7 @@ if intent.is_("refund_duplicate_charge"):       # only true when the answer is c
 Same agent, same 53 labeled support tickets, two decision planes: `llm` sends
 every decision to the LLM, `hybrid` asks rules, GLiNER and Laya first. Hosted
 models ran through OpenRouter, and the dollar figures are what OpenRouter
-billed ([full results](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/benchmarks.md)):
+billed ([full results](https://inboxpraveen.github.io/ThinkLess/benchmarks/)):
 
 | Fallback LLM | Success, `llm` | Success, `hybrid` | Billed per 1k tickets, `llm` | Billed per 1k tickets, `hybrid` | Decision time |
 |---|---:|---:|---:|---:|---:|
@@ -80,7 +80,7 @@ billed ([full results](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/
   validated on a separate calibration set first. The baseline is the
   strongest form of the LLM design: all six triage questions in one prompt.
 - The support set is 53 synthetic tickets: evidence of the mechanism and its
-  failure modes, not a leaderboard. The [benchmarks page](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/benchmarks.md)
+  failure modes, not a leaderboard. The [benchmarks page](https://inboxpraveen.github.io/ThinkLess/benchmarks/)
   lists the weak areas found and what was done about each.
 
 ## Quick start
@@ -143,6 +143,51 @@ No GPU? `pip install thinkless` and run
 [`examples/01_rules_only.py`](https://github.com/inboxpraveen/ThinkLess/blob/main/examples/01_rules_only.py): the API, the cascade
 and the traces with no model downloads.
 
+## Use it in your agent
+
+ThinkLess sits inside the framework you already use, at the points where the
+agent decides something: which path to take, whether an input is safe,
+whether a tool call is inside policy. Uncertain decisions go to the code you
+run today, so nothing gets worse while the routine ones get cheaper.
+
+```python
+from thinkless.integrations.langgraph import router
+
+intent = router(engine, INTENT, {"order_status": "tracking", "refund": "refunds"},
+                default="agent")          # your existing LLM node
+builder.add_conditional_edges(START, intent, intent.destinations)
+```
+
+- [LangGraph](https://inboxpraveen.github.io/ThinkLess/integrations/langgraph/):
+  routers, decision nodes and gated tools.
+- [OpenAI Agents SDK](https://inboxpraveen.github.io/ThinkLess/integrations/openai-agents/):
+  input guardrails, tool guardrails and routing to a specialist agent.
+- [Any framework](https://inboxpraveen.github.io/ThinkLess/integrations/any-framework/):
+  `route` and `gate` for Pydantic AI, a hand-written loop, or anything else.
+
+Before switching anything, measure it. Shadow mode runs ThinkLess next to your
+current code on live traffic and reports, per decision, the agreement with a
+confidence interval and what it would save:
+
+```python
+from thinkless.shadow import Shadow
+
+shadow = Shadow(engine, log="shadow/intent.jsonl", sample=0.2)
+
+@shadow.watch(INTENT, cost_usd=0.0004)    # today's cost per call
+def classify(message: str) -> str:
+    ...                                    # unchanged, and still what users get
+```
+
+```bash
+thinkless shadow report shadow/intent.jsonl --volume 2000000
+```
+
+The [migration guide](https://inboxpraveen.github.io/ThinkLess/guides/migration/)
+walks through it, and the [FAQ](https://inboxpraveen.github.io/ThinkLess/faq/)
+covers the common questions. To share one engine across services, run it as
+a [decision server or MCP tools](https://inboxpraveen.github.io/ThinkLess/guides/serving/).
+
 ## Try the demo agent
 
 A complete customer support agent ships with the package: a mock store with
@@ -164,31 +209,31 @@ thinkless bench intents --dataset banking77
 **Typed questions.** `Choice`, `Score`, `YesNo` and `Extract` declare what you
 want to know and which answers are allowed. They follow the System One wire
 format, so the same question works on every provider.
-[Questions](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/questions.md)
+[Questions](https://inboxpraveen.github.io/ThinkLess/concepts/questions/)
 
 **A confidence cascade.** Providers are tried cheapest first. Each gets one
 call with every open question it supports; answers that clear their threshold
 close, the rest move on. Unresolved questions come back `uncertain` with the
 best answer seen, and `decision.is_()` never matches an uncertain answer.
-[The cascade](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/cascade.md)
+[The cascade](https://inboxpraveen.github.io/ThinkLess/concepts/cascade/)
 
 **One meaning of confidence.** Providers disagree about what "confidence"
 means (Laya and TypeSafe compute it differently), so a threshold of 0.8 would
 mean different things per backend. ThinkLess derives a single normalized
 confidence from each provider's probabilities.
-[Confidence](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/confidence.md)
+[Confidence](https://inboxpraveen.github.io/ThinkLess/concepts/confidence/)
 
 **Thresholds from data.** `thinkless calibrate` sweeps thresholds on labeled
 examples and recommends the lowest one that meets your accuracy target, per
 question and per provider (`thresholds={"intent@gliner": 0.9}`).
-[Calibration](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/calibration.md)
+[Calibration](https://inboxpraveen.github.io/ThinkLess/guides/calibration/)
 
 **Traces for everything.** Decisions, provider attempts, generations, tool
 calls and rule checks are spans with W3C-compatible ids. Write JSONL audit
 files, export to any OpenTelemetry backend with GenAI semantic conventions, or
 open the self-contained HTML viewer. Content capture can be switched off
 without losing structure, timings or confidences.
-[Tracing](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/tracing.md)
+[Tracing](https://inboxpraveen.github.io/ThinkLess/concepts/tracing/)
 
 ## Providers and backends
 
@@ -208,32 +253,44 @@ without losing structure, timings or confidences.
 | `OpenAICompatibleLLM` | OpenAI, Ollama, vLLM, LM Studio, llama.cpp, Groq |
 | `AnthropicLLM` | Claude, with server-side refusal fallbacks |
 
-Writing your own provider is one class. [Providers](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/providers.md),
-[LLM backends](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/llm-backends.md)
+Writing your own provider is one class. [Providers](https://inboxpraveen.github.io/ThinkLess/guides/providers/),
+[LLM backends](https://inboxpraveen.github.io/ThinkLess/guides/llm-backends/)
 
 ## Documentation
 
-- [Getting started](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/getting-started.md)
-- Concepts: [the four planes](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/planes.md),
-  [questions](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/questions.md),
-  [confidence](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/confidence.md),
-  [the cascade](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/cascade.md),
-  [tracing](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/concepts/tracing.md)
-- Guides: [the support agent](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/support-agent.md),
-  [calibration](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/calibration.md),
-  [providers](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/providers.md),
-  [LLM backends](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/llm-backends.md),
-  [production](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/production.md),
-  [troubleshooting](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/guides/troubleshooting.md)
-- [Benchmarks](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/benchmarks.md), [CLI reference](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/reference/cli.md),
-  [Python API](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/reference/api.md), [roadmap](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/roadmap.md)
+- [Getting started](https://inboxpraveen.github.io/ThinkLess/getting-started/),
+  [installation](https://inboxpraveen.github.io/ThinkLess/guides/installation/)
+- Use it in your agent: [overview](https://inboxpraveen.github.io/ThinkLess/integrations/),
+  [LangGraph](https://inboxpraveen.github.io/ThinkLess/integrations/langgraph/),
+  [OpenAI Agents SDK](https://inboxpraveen.github.io/ThinkLess/integrations/openai-agents/),
+  [any framework](https://inboxpraveen.github.io/ThinkLess/integrations/any-framework/),
+  [migration](https://inboxpraveen.github.io/ThinkLess/guides/migration/),
+  [shadow mode](https://inboxpraveen.github.io/ThinkLess/guides/shadow-mode/),
+  [FAQ](https://inboxpraveen.github.io/ThinkLess/faq/)
+- Concepts: [the four planes](https://inboxpraveen.github.io/ThinkLess/concepts/planes/),
+  [questions](https://inboxpraveen.github.io/ThinkLess/concepts/questions/),
+  [confidence](https://inboxpraveen.github.io/ThinkLess/concepts/confidence/),
+  [the cascade](https://inboxpraveen.github.io/ThinkLess/concepts/cascade/),
+  [tracing](https://inboxpraveen.github.io/ThinkLess/concepts/tracing/)
+- Guides: [the support agent](https://inboxpraveen.github.io/ThinkLess/guides/support-agent/),
+  [calibration](https://inboxpraveen.github.io/ThinkLess/guides/calibration/),
+  [providers](https://inboxpraveen.github.io/ThinkLess/guides/providers/),
+  [LLM backends](https://inboxpraveen.github.io/ThinkLess/guides/llm-backends/),
+  [production](https://inboxpraveen.github.io/ThinkLess/guides/production/),
+  [serving](https://inboxpraveen.github.io/ThinkLess/guides/serving/),
+  [running a pilot](https://inboxpraveen.github.io/ThinkLess/guides/pilot/),
+  [troubleshooting](https://inboxpraveen.github.io/ThinkLess/guides/troubleshooting/)
+- [Benchmarks](https://inboxpraveen.github.io/ThinkLess/benchmarks/), [CLI reference](https://inboxpraveen.github.io/ThinkLess/reference/cli/),
+  [Python API](https://inboxpraveen.github.io/ThinkLess/reference/api/), [roadmap](https://inboxpraveen.github.io/ThinkLess/roadmap/)
 
 ## Status
 
-ThinkLess is at 0.1: the core API (questions, the engine, decisions and
-traces) is meant to stay stable, and providers and benchmarks will grow.
-Next up are shadow mode, calibration from traces, calibrated LLM confidence
-from log probabilities, and live Jev runs. See the [roadmap](https://github.com/inboxpraveen/ThinkLess/blob/main/docs/roadmap.md).
+ThinkLess is pre-1.0: the core API (questions, the engine, decisions and
+traces) is meant to stay stable, and providers, adapters and benchmarks will
+grow. The [decision benchmark](https://inboxpraveen.github.io/ThinkLess/decision-benchmark/)
+compares decision models on eight public tasks and is open to submissions.
+Next up are more models on it, cross-request batching in the server, and
+calibrated LLM confidence from log probabilities. See the [roadmap](https://inboxpraveen.github.io/ThinkLess/roadmap/).
 
 ## Contributing
 
@@ -246,8 +303,12 @@ and after from `thinkless bench` or `thinkless calibrate`.
 
 If ThinkLess saves your team time or money, consider
 [sponsoring its development](https://github.com/sponsors/inboxpraveen).
-Sponsorship funds frontier-model benchmark runs, more providers and more
-demos.
+
+Model vendors can sponsor runs of their models on the
+[decision benchmark](https://inboxpraveen.github.io/ThinkLess/decision-benchmark/).
+Sponsored runs are done by the maintainers and published as verified,
+whatever the result: sponsorship buys runs, not rankings. Sponsorship also
+funds more providers and more demos.
 
 ## Citing
 

thinkless-0.4.0/benchmarks/decisions/README.md

@@ -0,0 +1,18 @@
+# Decision benchmark
+
+A provider-neutral benchmark for the models that make an agent's routine
+decisions. The method, the leaderboard and the submission guide are in the
+documentation: https://inboxpraveen.github.io/ThinkLess/decision-benchmark/
+
+| Path | |
+|---|---|
+| `tasks/<task>/test.jsonl`, `calibration.jsonl` | the frozen rows of benchmark 1.0 |
+| `tasks/NOTICE.md` | sources, revisions, licenses and changes for every task |
+| `build.py` | how the rows were sampled; maintainers only, and never rerun within a version |
+| `results/verified/` | runs done by the maintainers |
+| `results/submitted/` | runs submitted by others, verified by CI |
+
+```bash
+thinkless bench decisions run --provider gliner --name "GLiNER 2.5 base"
+thinkless bench decisions verify GLiNER-2.5-base.json
+```

{thinkless-0.2.0 → thinkless-0.4.0}/pyproject.toml

@@ -70,7 +70,13 @@ otel = [
 ]
 # Public dataset benchmarks.
 bench = ["datasets>=3.0"]
-all = ["thinkless[local,openai,anthropic,otel,bench]"]
+# Agent framework adapters (thinkless.integrations).
+langgraph = ["langgraph>=1.0"]
+openai-agents = ["openai-agents>=0.22"]
+# The decision server (thinkless serve) and MCP tools (thinkless mcp).
+server = ["fastapi>=0.115", "uvicorn>=0.30"]
+mcp = ["mcp>=1.10"]
+all = ["thinkless[local,openai,anthropic,otel,bench,langgraph,openai-agents,server,mcp]"]
 dev = [
   "pytest>=8",
   "pytest-cov>=5",
@@ -79,11 +85,16 @@ dev = [
   "typesafe-sdk>=0.7",
   "mkdocs-material>=9.5",
   "mkdocstrings[python]>=0.26",
+  "langgraph>=1.0",
+  "openai-agents>=0.22",
+  "pydantic-ai-slim>=1.0",
+  "fastapi>=0.115",
+  "mcp>=1.10",
 ]
 
 [project.urls]
 Homepage = "https://github.com/inboxpraveen/ThinkLess"
-Documentation = "https://github.com/inboxpraveen/ThinkLess/tree/main/docs"
+Documentation = "https://inboxpraveen.github.io/ThinkLess/"
 Repository = "https://github.com/inboxpraveen/ThinkLess"
 Issues = "https://github.com/inboxpraveen/ThinkLess/issues"
 Changelog = "https://github.com/inboxpraveen/ThinkLess/blob/main/CHANGELOG.md"

{thinkless-0.2.0 → thinkless-0.4.0}/src/thinkless/__init__.py

@@ -28,6 +28,7 @@ from ._version import __version__
 from .decision import Answer, Attempt, Decision, Plane, Status, Usage
 from .engine import Engine, Run
 from .errors import ConfigurationError, ThinkLessError
+from .limits import SpendLimit, SpendLimitError
 from .logs import configure_logging
 from .questions import Choice, Extract, Kind, Question, Score, YesNo
 from .settings import load_env
@@ -49,6 +50,8 @@ __all__ = [
     "Question",
     "Run",
     "Score",
+    "SpendLimit",
+    "SpendLimitError",
     "Status",
     "ThinkLessError",
     "TraceSummary",

thinkless-0.4.0/src/thinkless/_version.py

@@ -0,0 +1 @@
+__version__ = "0.4.0"