verifiers 0.2.2.dev7__py3-none-any.whl → 0.2.2.dev9__py3-none-any.whl

verifiers/v1/agent.py

@@ -221,19 +221,19 @@ class Agent:
         task: Task,
         *,
         runtime: Runtime | None = None,
-        shared_tools: Mapping[str, SharedToolServer] | None = None,
+        tools: Mapping[str, SharedToolServer] | None = None,
         on_trace: Callable[[Trace], None] | None = None,
     ) -> Trace:
         """Run this agent on `task` once and return the trace: `runtime` places it
-        into a live borrowed box instead of provisioning one; `shared_tools` are
-        live servers borrowed from their owner, counted in the pairing check;
+        into a live borrowed box instead of provisioning one; `tools` are live
+        servers borrowed from their owner, counted in the pairing check;
         `on_trace` observes the trace the moment it's minted, before any I/O.
         Retries whole while the trace ends with a retryable error (`config.retries`)
         — never into a borrowed box; the final trace keeps earlier attempts' errors."""
         retry = self.config.retries
         history: list = []
         for attempt in range(retry.max_retries + 1):
-            trace = await self._run_once(task, runtime, shared_tools, on_trace)
+            trace = await self._run_once(task, runtime, tools, on_trace)
             if attempt == retry.max_retries or not trace_should_retry(trace, retry):
                 break
             if runtime is not None:
@@ -356,7 +356,7 @@ class _EpisodeAgent(Agent):
     they're created, finished ones land in `completed` (the episode's traces),
     each run takes the eval's gate. The taskset's shared tool servers ride only
     its own tasks — on an env-minted task they'd wrongly put MCP in play
-    (`shared_tools=` overrides)."""
+    (`tools=` overrides)."""
 
     def __init__(
         self,
@@ -392,7 +392,7 @@ class _EpisodeAgent(Agent):
         task: Task,
         *,
         runtime: Runtime | None = None,
-        shared_tools: Mapping[str, SharedToolServer] | None = None,
+        tools: Mapping[str, SharedToolServer] | None = None,
         on_trace: Callable[[Trace], None] | None = None,
     ) -> Trace:
         last: Trace | None = None
@@ -416,9 +416,7 @@ class _EpisodeAgent(Agent):
             trace = await super().run(
                 task,
                 runtime=runtime,
-                shared_tools=shared_tools
-                if shared_tools is not None
-                else self._shared_for(task),
+                tools=tools if tools is not None else self._shared_for(task),
                 on_trace=watch,
             )
         self._completed.append(trace)

{verifiers-0.2.2.dev7.dist-info → verifiers-0.2.2.dev9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: verifiers
-Version: 0.2.2.dev7
+Version: 0.2.2.dev9
 Summary: Verifiers: Environments for LLM Reinforcement Learning
 Project-URL: Homepage, https://github.com/primeintellect-ai/verifiers
 Project-URL: Documentation, https://github.com/primeintellect-ai/verifiers

{verifiers-0.2.2.dev7.dist-info → verifiers-0.2.2.dev9.dist-info}/RECORD

@@ -22,7 +22,6 @@ verifiers/clients/openai_chat_completions_token_client.py,sha256=EGOF9LNW9hgfnpy
 verifiers/clients/openai_completions_client.py,sha256=bMyI87oXMWNMGqbCixF2091GhsJSoPEG_9L0cv8QKk0,7200
 verifiers/clients/openai_responses_client.py,sha256=D3k3NW_7vEpeT6_zrimIHJNcwlVmrp44PSXsZmIv28Y,18090
 verifiers/clients/renderer_client.py,sha256=C3lUoBZO24usJwDFkD-4URHz0s1q4Q-kG1rJDjzGBsc,26800
-verifiers/envs/AGENTS.md,sha256=IFPCx9msgDc8yjLN2pwag09MP0zmE-1C7wlV6xGN3Kk,3695
 verifiers/envs/__init__.py,sha256=OXkw2QcypssNW5BJmIzw7IpBs9uRMyYQSjlXDHpjIIE,86
 verifiers/envs/env_group.py,sha256=kxL8YyENBPbis4AmboilIDmy6d_u3zqkG86_kBNEnZQ,16446
 verifiers/envs/environment.py,sha256=DjYR7KxJZCTSoFcTHJVNjQieXOl39ftAnKxjUryGBpc,53921
@@ -169,7 +168,7 @@ verifiers/utils/tool_utils.py,sha256=gInWZODWQUZN4TyEMuuITyOUm9qlHJxtcvr1zZl_zJs
 verifiers/utils/usage_utils.py,sha256=GPLC0xGY_Obrr8X7huWY-2iODZ7tgX-MtO8WSDN4rXI,3904
 verifiers/utils/version_utils.py,sha256=am3hZLnlaUWTFdllGZR1VMN91hEhiiE8FDmPf1cOG1k,2642
 verifiers/v1/__init__.py,sha256=r8khgi7_KSY4AfevEefSslyxytScmMzzCBA6kjqvd1I,6653
-verifiers/v1/agent.py,sha256=RSBHKw-vUnXiEQk04G6HKg854p88YAQ4Kmxaeml-TlY,19472
+verifiers/v1/agent.py,sha256=k6BBNSgwPkqLe5klzlRLQaNJfSFS1xwwgf_HWa8vaXI,19384
 verifiers/v1/decorators.py,sha256=XRMkUQSyvXCYP5fOwzBYV5qEOlxLg6rzYhnhrHHHTIQ,3838
 verifiers/v1/env.py,sha256=WAShpDP4m1i25CcR7KS4u50s3efynT6LOn2EbF8eId8,24788
 verifiers/v1/episode.py,sha256=XgcStr5k0N4CQ8NXvJzlwZ0y4RNp9cBsE27N47h3750,2307
@@ -316,8 +315,8 @@ verifiers/v1/utils/logging.py,sha256=OcMHA6NsYux3oIzjPuI95rDWmFBHNcHDjZeNIhXTX-Y
 verifiers/v1/utils/memory.py,sha256=ZkIvGk6uITAH5sKon65LifKPbvZr8mJ__PVc23FZpOQ,1835
 verifiers/v1/utils/sampling.py,sha256=JczGzBn6s3wsIrSY2Hy3hE8m6NreNgsNzhSjDikQqX0,1037
 verifiers/v1/utils/version.py,sha256=75ZtI2NHBmlb52KpcKLUpiSXp8q4bASr7uKeXoCKlT8,1582
-verifiers-0.2.2.dev7.dist-info/METADATA,sha256=XGofHtw6moKoR60FkN2wIiOs5Gh0nNh2ttkkALN1A-A,4540
-verifiers-0.2.2.dev7.dist-info/WHEEL,sha256=lCkmxWfQsSc9CfIClYeavTdQeEX2toPqufh9gI35EQA,87
-verifiers-0.2.2.dev7.dist-info/entry_points.txt,sha256=dF82JUYEFslR1AOW8LZfuBWeZeQoyX4wCRrduklg8-I,551
-verifiers-0.2.2.dev7.dist-info/licenses/LICENSE,sha256=v0RrUsdV3IDoZhrRce297IXS3xMHNJ-_LdLpFAUWb9k,1072
-verifiers-0.2.2.dev7.dist-info/RECORD,,
+verifiers-0.2.2.dev9.dist-info/METADATA,sha256=Hodwf1DME43T0xj2O9ZZHTaxn5kmVcbYl75jYEhUjt8,4540
+verifiers-0.2.2.dev9.dist-info/WHEEL,sha256=lCkmxWfQsSc9CfIClYeavTdQeEX2toPqufh9gI35EQA,87
+verifiers-0.2.2.dev9.dist-info/entry_points.txt,sha256=dF82JUYEFslR1AOW8LZfuBWeZeQoyX4wCRrduklg8-I,551
+verifiers-0.2.2.dev9.dist-info/licenses/LICENSE,sha256=v0RrUsdV3IDoZhrRce297IXS3xMHNJ-_LdLpFAUWb9k,1072
+verifiers-0.2.2.dev9.dist-info/RECORD,,

verifiers/envs/AGENTS.md

@@ -1,72 +0,0 @@
-# Environments
-
-**WIP** -- subject to change.
-
-## Overview
-
-Environment classes are organized into three categories:
-
-| Category | Location | Description |
-|----------|----------|-------------|
-| **Core** | `verifiers/envs/` | Stable base classes and sandbox environments |
-| **Integrations** | `verifiers/envs/integrations/` | Third-party library wrappers (lazy-loaded, require extras) |
-| **Experimental** | `verifiers/envs/experimental/` | Newer environments with sharper edges |
-
-Avoid storing global state in the environment. Instead, use the state argument to the environment's methods.
-
-## Core Environments
-
-Base classes for building environments:
-
-- `SingleTurnEnv` - Single response Q&A tasks
-- `MultiTurnEnv` - Multi-turn interactions (games, simulations, agents)
-- `ToolEnv` - Stateless, idempotent tools passed as Python functions with all arguments exposed to the model. For managing additional state, use `StatefulToolEnv`.
-- `StatefulToolEnv` - Tools requiring per-rollout state (e.g. sandbox ID). Use `update_tool_args` to inject state into tool calls. See `sandbox_env.py` for an example.
-- `SandboxEnv` - Sandboxed container execution using `prime` sandboxes. All sandbox setup logic should be included in the start command and queued via `setup_state`, but not awaited—await resources only when first needed to overlap provisioning with rollout. See `python_env.py` for an example.
-- `PythonEnv` - Persistent Python REPL in sandbox
-
-## Integrations
-
-Third-party library wrappers that require additional dependencies:
-
-| Environment | Extra | Install Command |
-|-------------|-------|-----------------|
-| `TextArenaEnv` | `ta` | `uv add 'verifiers[ta]'` |
-| `ReasoningGymEnv` | `rg` | `uv add 'verifiers[rg]'` |
-| `BrowserEnv` | `browser` | `uv add 'verifiers[browser]'` |
-
-When developing in the `verifiers` repo:
-```bash
-uv sync --extra ta       # for TextArenaEnv
-uv sync --extra rg       # for ReasoningGymEnv
-uv sync --extra browser  # for BrowserEnv
-```
-
-### TextArenaEnv
-
-Wrapper for text-based TextArena environments (games, simulations). When adding new TextArena environments, investigate the `textarena` source code to determine the observation format. Often you'll want to re-render observations via `feedback_fn`, as `verifiers` doesn't allow overwriting past messages (only concatenation), and many TextArena games return full game state rather than turn-level diffs.
-
-### ReasoningGymEnv
-
-Wrapper for [reasoning-gym](https://github.com/reasoning-gym/reasoning-gym) procedural datasets. Supports single datasets or composite mixtures via `DatasetSpec`.
-
-### BrowserEnv
-
-Browser automation environment using [Browserbase](https://browserbase.com) with two modes:
-
-**DOM mode** (`mode="dom"`): Natural language browser control via Stagehand SDK.
-
-**CUA mode** (`mode="cua"`): Vision-based browser control using coordinate-based primitives.
-
-CUA mode supports automatic sandbox deployment (`use_sandbox=True`, the default), where the CUA server is automatically deployed to a sandbox container. This eliminates the need for manual server setup. The server files are located in `assets/templates/browserbase/cua/` and are uploaded to sandboxes during rollout initialization.
-
-For local development, set `use_sandbox=False` and start the server manually from `assets/templates/browserbase/cua/`.
-
-## Experimental
-
-See `verifiers/envs/experimental/README.md` for documentation on:
-- `GymEnv` - Universal Gym-compatible environment runner
-- `MCPEnv` - MCP server integration
-- `CliAgentEnv` - Agent code in sandboxes with API call interception
-- V1 `vf.Env` / `vf.Taskset` / `vf.Harness` - taskset/harness agent composition
-- `HarborEnv` - Harbor-format task loading