agent-tokenops 0.2.1__tar.gz → 0.4.0__tar.gz

{agent_tokenops-0.2.1/src/agent_tokenops.egg-info → agent_tokenops-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-tokenops
-Version: 0.2.1
+Version: 0.4.0
 Summary: TokenOps control plane and SDK for run-aware agent token governance
 Author: Susheem Koul, Tisha Chawla
 License-Expression: MIT
@@ -20,7 +20,7 @@ Classifier: Topic :: System :: Systems Administration
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
-Requires-Dist: agent-chronicle>=0.3.0
+Requires-Dist: agent-chronicle<0.6,>=0.5.0
 Requires-Dist: openai>=1.0
 Requires-Dist: anthropic>=0.40
 Requires-Dist: pyyaml>=6.0
@@ -38,6 +38,8 @@ Requires-Dist: ruff>=0.8; extra == "dev"
 Requires-Dist: mypy>=1.13; extra == "dev"
 Requires-Dist: pre-commit>=4.0; extra == "dev"
 Requires-Dist: types-PyYAML>=6.0; extra == "dev"
+Provides-Extra: contract
+Requires-Dist: agentplane-control-plane>=0.2.0; extra == "contract"
 Provides-Extra: examples
 Requires-Dist: ddgs>=9.0; extra == "examples"
 Requires-Dist: langchain-core>=0.3; extra == "examples"
@@ -100,7 +102,10 @@ add your own.
 
 ## 🚀 Quickstart
 
-Requires Python 3.10+.
+Requires Python 3.10+ and a running control plane — TokenOps has no ledger of its
+own, so every agent (even a single process) governs against one. Zero-setup taste:
+`python -m tokenops.demo` launches a throwaway plane for you automatically. For your
+own agent, start one first (see [Quickdeploy](#-quickdeploy) below), then:
 
 ### 1. Put it in your agent
 
@@ -123,14 +128,16 @@ Anywhere else (Cursor, Copilot, ...), paste this:
 <details>
 <summary><b>Manual</b>, about ten lines</summary>
 
-Wrap your model call once, then hand the wrapped version to your agent.
+Wrap your model call once, then hand the wrapped version to your agent. Needs
+`CONTROL_PLANE_URL` (or `TOKENOPS_URL`) pointing at a running control plane —
+see [Quickdeploy](#-quickdeploy).
 
 ```python
 from tokenops import ControlPlaneClient, tokenops_run
 from tokenops.control import Halt, wrap_complete
 from tokenops.providers import complete
 
-client = ControlPlaneClient.from_env()
+client = ControlPlaneClient.from_env()  # raises if CONTROL_PLANE_URL isn't set
 
 with tokenops_run(client=client, service="my-agent", intent="research",
                   provider="openai", model="gpt-4o") as bound:
@@ -178,9 +185,9 @@ run is out, even from another process.
 ## 🐳 Quickdeploy
 
 > [!TIP]
-> The control plane (`python -m tokenops.server`) shares one budget across
-> processes and powers the dashboard. A single-process agent doesn't need it
-> running at all.
+> Every agent needs a control plane running — TokenOps has no ledger of its own.
+> A single-process agent still needs one, just not the multi-process sharing this
+> section is about. `python -m tokenops.server` powers the dashboard too.
 
 One command, plane + dashboard:
 
@@ -231,8 +238,8 @@ export TOKENOPS_URL=http://localhost:7700
 export TOKENOPS_DB=tokenops.db   # plane and every agent read the same file
 ```
 
-> `TOKENOPS_EMBEDDED=1` overrides `TOKENOPS_URL`. Leave it unset here, or each
-> process silently falls back to its own local ledger and gets the full budget.
+> tokenops has no ledger of its own — every process governs against the plane at
+> `TOKENOPS_URL`. There is no local-fallback env var to accidentally leave unset.
 
 PyPI name is `agent-tokenops`; the import is `tokenops`. Extras:
 `pip install "agent-tokenops[examples]"` for the LangChain benches,
@@ -289,7 +296,7 @@ flowchart LR
 | **Control plane** (`python -m tokenops.server`) | `POST /v1/runs`, shared SQLite, Admin/Dashboard | Agent loops, LLM calls, tools |
 | **SDK (in agents)** | `tokenops_run`, `wrap_complete`, ledger/policies, Chronicle crossing hook | Ad-hoc run IDs; mounting `/v1/runs` when `TOKENOPS_URL` is set |
 
-Chronicle records decision boundaries; TokenOps attaches as the cost/governance observer on live crossings. See [Chronicle](https://github.com/theagentplane/chronicle) for record-and-replay.
+Chronicle records decision boundaries; TokenOps attaches as the cost/governance observer on live crossings. See [Chronicle](https://github.com/theagentplane/chronicle) for record-and-replay, accepted at [REALM](https://realm-workshop.github.io/) (Research on Agent Language Models), a workshop at EMNLP 2026.
 
 </details>
 
@@ -298,22 +305,15 @@ Chronicle records decision boundaries; TokenOps attaches as the cost/governance
 
 | Variable | Purpose |
 |---|---|
-| `TOKENOPS_URL` | Remote plane base URL (e.g. `http://localhost:7700`) → HTTP `register_run` |
-| `TOKENOPS_EMBEDDED` | Set to `1` to force in-process `Store` (tests / single-process) |
-| `TOKENOPS_DB` | SQLite path shared by plane + agents |
+| `TOKENOPS_URL` (or `CONTROL_PLANE_URL`) | The control plane's base URL (e.g. `http://localhost:8800`) — **required** |
 | `TOKENOPS_CONFIG` | YAML for governance seed (core: `src/tokenops/config/default.yaml`) |
 
-`TOKENOPS_URL` also accepts the aliases `CONTROL_PLANE_URL` and
+tokenops has no ledger or run registry of its own — `ControlPlaneClient.from_env()`
+raises if `TOKENOPS_URL`/`CONTROL_PLANE_URL` isn't set, rather than silently falling
+back to anything local. Every process talks to the same plane, so they share one
+budget by construction. `TOKENOPS_URL` also accepts the alias
 `TOKENOPS_CONTROL_PLANE_URL`.
 
-Production / multi-process: set `TOKENOPS_URL`; agents must **not** mount `/v1/runs`. Tests: `TOKENOPS_EMBEDDED=1` (or omit URL).
-
-> **Precedence.** `ControlPlaneClient.from_env` takes the HTTP path only when a
-> URL is set **and** `TOKENOPS_EMBEDDED` is not `1`. Setting both falls back to a
-> local SQLite file with no warning, and every process then gets its own full
-> budget. Check with
-> `print("embedded" if client.embedded else client.url)`.
-
 </details>
 
 <details>
@@ -372,6 +372,7 @@ tests/                     # unit + e2e
   [LinkedIn](https://www.linkedin.com/posts/microsoft-developers_who-spent-all-the-tokens-tokenops-gives-activity-7499191980715982848-224b) and [X](https://x.com/msdev/status/2093425027500978292).
 - **[Who spent all the tokens? Real-time, run-scoped cost control for AI agents](https://commandline.microsoft.com/tokenops-real-time-run-scoped-cost-control-ai-agents/)**: *Command Line*, a Microsoft publication.
 - **[FinOps for AI Agents: Who Spent All the Tokens?](https://www.youtube.com/watch?v=GJX19pNhmSw)**: talk at the **AI Engineer World's Fair**, San Francisco.
+- **Selected to participate in the [GitHub Secure Open Source Fund](https://github.com/open-source/github-secure-open-source-fund)** (Session 5), GitHub Security Lab's open source security program.
 
 ## 🛟 Support
 

{agent_tokenops-0.2.1 → agent_tokenops-0.4.0}/README.md

@@ -53,7 +53,10 @@ add your own.
 
 ## 🚀 Quickstart
 
-Requires Python 3.10+.
+Requires Python 3.10+ and a running control plane — TokenOps has no ledger of its
+own, so every agent (even a single process) governs against one. Zero-setup taste:
+`python -m tokenops.demo` launches a throwaway plane for you automatically. For your
+own agent, start one first (see [Quickdeploy](#-quickdeploy) below), then:
 
 ### 1. Put it in your agent
 
@@ -76,14 +79,16 @@ Anywhere else (Cursor, Copilot, ...), paste this:
 <details>
 <summary><b>Manual</b>, about ten lines</summary>
 
-Wrap your model call once, then hand the wrapped version to your agent.
+Wrap your model call once, then hand the wrapped version to your agent. Needs
+`CONTROL_PLANE_URL` (or `TOKENOPS_URL`) pointing at a running control plane —
+see [Quickdeploy](#-quickdeploy).
 
 ```python
 from tokenops import ControlPlaneClient, tokenops_run
 from tokenops.control import Halt, wrap_complete
 from tokenops.providers import complete
 
-client = ControlPlaneClient.from_env()
+client = ControlPlaneClient.from_env()  # raises if CONTROL_PLANE_URL isn't set
 
 with tokenops_run(client=client, service="my-agent", intent="research",
                   provider="openai", model="gpt-4o") as bound:
@@ -131,9 +136,9 @@ run is out, even from another process.
 ## 🐳 Quickdeploy
 
 > [!TIP]
-> The control plane (`python -m tokenops.server`) shares one budget across
-> processes and powers the dashboard. A single-process agent doesn't need it
-> running at all.
+> Every agent needs a control plane running — TokenOps has no ledger of its own.
+> A single-process agent still needs one, just not the multi-process sharing this
+> section is about. `python -m tokenops.server` powers the dashboard too.
 
 One command, plane + dashboard:
 
@@ -184,8 +189,8 @@ export TOKENOPS_URL=http://localhost:7700
 export TOKENOPS_DB=tokenops.db   # plane and every agent read the same file
 ```
 
-> `TOKENOPS_EMBEDDED=1` overrides `TOKENOPS_URL`. Leave it unset here, or each
-> process silently falls back to its own local ledger and gets the full budget.
+> tokenops has no ledger of its own — every process governs against the plane at
+> `TOKENOPS_URL`. There is no local-fallback env var to accidentally leave unset.
 
 PyPI name is `agent-tokenops`; the import is `tokenops`. Extras:
 `pip install "agent-tokenops[examples]"` for the LangChain benches,
@@ -242,7 +247,7 @@ flowchart LR
 | **Control plane** (`python -m tokenops.server`) | `POST /v1/runs`, shared SQLite, Admin/Dashboard | Agent loops, LLM calls, tools |
 | **SDK (in agents)** | `tokenops_run`, `wrap_complete`, ledger/policies, Chronicle crossing hook | Ad-hoc run IDs; mounting `/v1/runs` when `TOKENOPS_URL` is set |
 
-Chronicle records decision boundaries; TokenOps attaches as the cost/governance observer on live crossings. See [Chronicle](https://github.com/theagentplane/chronicle) for record-and-replay.
+Chronicle records decision boundaries; TokenOps attaches as the cost/governance observer on live crossings. See [Chronicle](https://github.com/theagentplane/chronicle) for record-and-replay, accepted at [REALM](https://realm-workshop.github.io/) (Research on Agent Language Models), a workshop at EMNLP 2026.
 
 </details>
 
@@ -251,22 +256,15 @@ Chronicle records decision boundaries; TokenOps attaches as the cost/governance
 
 | Variable | Purpose |
 |---|---|
-| `TOKENOPS_URL` | Remote plane base URL (e.g. `http://localhost:7700`) → HTTP `register_run` |
-| `TOKENOPS_EMBEDDED` | Set to `1` to force in-process `Store` (tests / single-process) |
-| `TOKENOPS_DB` | SQLite path shared by plane + agents |
+| `TOKENOPS_URL` (or `CONTROL_PLANE_URL`) | The control plane's base URL (e.g. `http://localhost:8800`) — **required** |
 | `TOKENOPS_CONFIG` | YAML for governance seed (core: `src/tokenops/config/default.yaml`) |
 
-`TOKENOPS_URL` also accepts the aliases `CONTROL_PLANE_URL` and
+tokenops has no ledger or run registry of its own — `ControlPlaneClient.from_env()`
+raises if `TOKENOPS_URL`/`CONTROL_PLANE_URL` isn't set, rather than silently falling
+back to anything local. Every process talks to the same plane, so they share one
+budget by construction. `TOKENOPS_URL` also accepts the alias
 `TOKENOPS_CONTROL_PLANE_URL`.
 
-Production / multi-process: set `TOKENOPS_URL`; agents must **not** mount `/v1/runs`. Tests: `TOKENOPS_EMBEDDED=1` (or omit URL).
-
-> **Precedence.** `ControlPlaneClient.from_env` takes the HTTP path only when a
-> URL is set **and** `TOKENOPS_EMBEDDED` is not `1`. Setting both falls back to a
-> local SQLite file with no warning, and every process then gets its own full
-> budget. Check with
-> `print("embedded" if client.embedded else client.url)`.
-
 </details>
 
 <details>
@@ -325,6 +323,7 @@ tests/                     # unit + e2e
   [LinkedIn](https://www.linkedin.com/posts/microsoft-developers_who-spent-all-the-tokens-tokenops-gives-activity-7499191980715982848-224b) and [X](https://x.com/msdev/status/2093425027500978292).
 - **[Who spent all the tokens? Real-time, run-scoped cost control for AI agents](https://commandline.microsoft.com/tokenops-real-time-run-scoped-cost-control-ai-agents/)**: *Command Line*, a Microsoft publication.
 - **[FinOps for AI Agents: Who Spent All the Tokens?](https://www.youtube.com/watch?v=GJX19pNhmSw)**: talk at the **AI Engineer World's Fair**, San Francisco.
+- **Selected to participate in the [GitHub Secure Open Source Fund](https://github.com/open-source/github-secure-open-source-fund)** (Session 5), GitHub Security Lab's open source security program.
 
 ## 🛟 Support
 

{agent_tokenops-0.2.1 → agent_tokenops-0.4.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agent-tokenops"
-version = "0.2.1"
+version = "0.4.0"
 description = "TokenOps control plane and SDK for run-aware agent token governance"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -34,7 +34,7 @@ classifiers = [
   "Topic :: System :: Systems Administration",
 ]
 dependencies = [
-  "agent-chronicle>=0.3.0",
+  "agent-chronicle>=0.5.0,<0.6",
   "openai>=1.0",
   "anthropic>=0.40",
   "pyyaml>=6.0",
@@ -56,6 +56,14 @@ dev = [
   "pre-commit>=4.0",
   "types-PyYAML>=6.0",
 ]
+# The verified-fake contract suite + e2e run against a real control plane in-process.
+# Not in `dev` because the 0.2.0 line is not on PyPI yet — the tests that need it
+# `pytest.importorskip("control_plane")`, so `[dev]` alone stays green. To run them:
+#   pip install -e ".[dev,contract]"      # once 0.2.0 is released, or
+#   pip install "agentplane-control-plane @ git+https://github.com/theagentplane/control-plane@main"
+contract = [
+  "agentplane-control-plane>=0.2.0",
+]
 examples = [
   "ddgs>=9.0",
   "langchain-core>=0.3",
@@ -74,10 +82,13 @@ testpaths = ["tests"]
 pythonpath = ["src", "."]
 asyncio_mode = "strict"
 markers = [
-  "e2e: example / bench end-to-end tests (not run in default CI)",
-  "live: requires API keys or vendored frameworks",
+  "e2e: example / bench end-to-end tests — real servers, real Governor/policy",
+  "     enforcement, faked model+network only. Part of the default suite (see",
+  "     addopts) precisely so real run+policy regressions are caught.",
+  "live: requires real API keys or vendored frameworks — self-skips without them,",
+  "      excluded from the default run since it needs secrets to do anything.",
 ]
-addopts = "-m 'not e2e and not live'"
+addopts = "-m 'not live'"
 
 [tool.ruff]
 target-version = "py310"

{agent_tokenops-0.2.1 → agent_tokenops-0.4.0/src/agent_tokenops.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agent-tokenops
-Version: 0.2.1
+Version: 0.4.0
 Summary: TokenOps control plane and SDK for run-aware agent token governance
 Author: Susheem Koul, Tisha Chawla
 License-Expression: MIT
@@ -20,7 +20,7 @@ Classifier: Topic :: System :: Systems Administration
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
-Requires-Dist: agent-chronicle>=0.3.0
+Requires-Dist: agent-chronicle<0.6,>=0.5.0
 Requires-Dist: openai>=1.0
 Requires-Dist: anthropic>=0.40
 Requires-Dist: pyyaml>=6.0
@@ -38,6 +38,8 @@ Requires-Dist: ruff>=0.8; extra == "dev"
 Requires-Dist: mypy>=1.13; extra == "dev"
 Requires-Dist: pre-commit>=4.0; extra == "dev"
 Requires-Dist: types-PyYAML>=6.0; extra == "dev"
+Provides-Extra: contract
+Requires-Dist: agentplane-control-plane>=0.2.0; extra == "contract"
 Provides-Extra: examples
 Requires-Dist: ddgs>=9.0; extra == "examples"
 Requires-Dist: langchain-core>=0.3; extra == "examples"
@@ -100,7 +102,10 @@ add your own.
 
 ## 🚀 Quickstart
 
-Requires Python 3.10+.
+Requires Python 3.10+ and a running control plane — TokenOps has no ledger of its
+own, so every agent (even a single process) governs against one. Zero-setup taste:
+`python -m tokenops.demo` launches a throwaway plane for you automatically. For your
+own agent, start one first (see [Quickdeploy](#-quickdeploy) below), then:
 
 ### 1. Put it in your agent
 
@@ -123,14 +128,16 @@ Anywhere else (Cursor, Copilot, ...), paste this:
 <details>
 <summary><b>Manual</b>, about ten lines</summary>
 
-Wrap your model call once, then hand the wrapped version to your agent.
+Wrap your model call once, then hand the wrapped version to your agent. Needs
+`CONTROL_PLANE_URL` (or `TOKENOPS_URL`) pointing at a running control plane —
+see [Quickdeploy](#-quickdeploy).
 
 ```python
 from tokenops import ControlPlaneClient, tokenops_run
 from tokenops.control import Halt, wrap_complete
 from tokenops.providers import complete
 
-client = ControlPlaneClient.from_env()
+client = ControlPlaneClient.from_env()  # raises if CONTROL_PLANE_URL isn't set
 
 with tokenops_run(client=client, service="my-agent", intent="research",
                   provider="openai", model="gpt-4o") as bound:
@@ -178,9 +185,9 @@ run is out, even from another process.
 ## 🐳 Quickdeploy
 
 > [!TIP]
-> The control plane (`python -m tokenops.server`) shares one budget across
-> processes and powers the dashboard. A single-process agent doesn't need it
-> running at all.
+> Every agent needs a control plane running — TokenOps has no ledger of its own.
+> A single-process agent still needs one, just not the multi-process sharing this
+> section is about. `python -m tokenops.server` powers the dashboard too.
 
 One command, plane + dashboard:
 
@@ -231,8 +238,8 @@ export TOKENOPS_URL=http://localhost:7700
 export TOKENOPS_DB=tokenops.db   # plane and every agent read the same file
 ```
 
-> `TOKENOPS_EMBEDDED=1` overrides `TOKENOPS_URL`. Leave it unset here, or each
-> process silently falls back to its own local ledger and gets the full budget.
+> tokenops has no ledger of its own — every process governs against the plane at
+> `TOKENOPS_URL`. There is no local-fallback env var to accidentally leave unset.
 
 PyPI name is `agent-tokenops`; the import is `tokenops`. Extras:
 `pip install "agent-tokenops[examples]"` for the LangChain benches,
@@ -289,7 +296,7 @@ flowchart LR
 | **Control plane** (`python -m tokenops.server`) | `POST /v1/runs`, shared SQLite, Admin/Dashboard | Agent loops, LLM calls, tools |
 | **SDK (in agents)** | `tokenops_run`, `wrap_complete`, ledger/policies, Chronicle crossing hook | Ad-hoc run IDs; mounting `/v1/runs` when `TOKENOPS_URL` is set |
 
-Chronicle records decision boundaries; TokenOps attaches as the cost/governance observer on live crossings. See [Chronicle](https://github.com/theagentplane/chronicle) for record-and-replay.
+Chronicle records decision boundaries; TokenOps attaches as the cost/governance observer on live crossings. See [Chronicle](https://github.com/theagentplane/chronicle) for record-and-replay, accepted at [REALM](https://realm-workshop.github.io/) (Research on Agent Language Models), a workshop at EMNLP 2026.
 
 </details>
 
@@ -298,22 +305,15 @@ Chronicle records decision boundaries; TokenOps attaches as the cost/governance
 
 | Variable | Purpose |
 |---|---|
-| `TOKENOPS_URL` | Remote plane base URL (e.g. `http://localhost:7700`) → HTTP `register_run` |
-| `TOKENOPS_EMBEDDED` | Set to `1` to force in-process `Store` (tests / single-process) |
-| `TOKENOPS_DB` | SQLite path shared by plane + agents |
+| `TOKENOPS_URL` (or `CONTROL_PLANE_URL`) | The control plane's base URL (e.g. `http://localhost:8800`) — **required** |
 | `TOKENOPS_CONFIG` | YAML for governance seed (core: `src/tokenops/config/default.yaml`) |
 
-`TOKENOPS_URL` also accepts the aliases `CONTROL_PLANE_URL` and
+tokenops has no ledger or run registry of its own — `ControlPlaneClient.from_env()`
+raises if `TOKENOPS_URL`/`CONTROL_PLANE_URL` isn't set, rather than silently falling
+back to anything local. Every process talks to the same plane, so they share one
+budget by construction. `TOKENOPS_URL` also accepts the alias
 `TOKENOPS_CONTROL_PLANE_URL`.
 
-Production / multi-process: set `TOKENOPS_URL`; agents must **not** mount `/v1/runs`. Tests: `TOKENOPS_EMBEDDED=1` (or omit URL).
-
-> **Precedence.** `ControlPlaneClient.from_env` takes the HTTP path only when a
-> URL is set **and** `TOKENOPS_EMBEDDED` is not `1`. Setting both falls back to a
-> local SQLite file with no warning, and every process then gets its own full
-> budget. Check with
-> `print("embedded" if client.embedded else client.url)`.
-
 </details>
 
 <details>
@@ -372,6 +372,7 @@ tests/                     # unit + e2e
   [LinkedIn](https://www.linkedin.com/posts/microsoft-developers_who-spent-all-the-tokens-tokenops-gives-activity-7499191980715982848-224b) and [X](https://x.com/msdev/status/2093425027500978292).
 - **[Who spent all the tokens? Real-time, run-scoped cost control for AI agents](https://commandline.microsoft.com/tokenops-real-time-run-scoped-cost-control-ai-agents/)**: *Command Line*, a Microsoft publication.
 - **[FinOps for AI Agents: Who Spent All the Tokens?](https://www.youtube.com/watch?v=GJX19pNhmSw)**: talk at the **AI Engineer World's Fair**, San Francisco.
+- **Selected to participate in the [GitHub Secure Open Source Fund](https://github.com/open-source/github-secure-open-source-fund)** (Session 5), GitHub Security Lab's open source security program.
 
 ## 🛟 Support
 

{agent_tokenops-0.2.1 → agent_tokenops-0.4.0}/src/agent_tokenops.egg-info/SOURCES.txt

@@ -22,6 +22,7 @@ src/tokenops/control/config.py
 src/tokenops/control/context.py
 src/tokenops/control/core.py
 src/tokenops/control/crossing.py
+src/tokenops/control/dev_plane.py
 src/tokenops/control/engine.py
 src/tokenops/control/governance_cache.py
 src/tokenops/control/http.py
@@ -29,12 +30,14 @@ src/tokenops/control/http_store.py
 src/tokenops/control/instrument.py
 src/tokenops/control/integration.py
 src/tokenops/control/ledger.py
+src/tokenops/control/ledger_backend.py
 src/tokenops/control/models.py
 src/tokenops/control/pricing.py
 src/tokenops/control/propagate.py
 src/tokenops/control/request_context.py
 src/tokenops/control/run.py
 src/tokenops/control/store.py
+src/tokenops/control/usage.py
 src/tokenops/control/policies/__init__.py
 src/tokenops/control/policies/_util.py
 src/tokenops/control/policies/concurrency_cap.py
@@ -45,6 +48,7 @@ src/tokenops/control/policies/output_runaway.py
 src/tokenops/control/policies/pre_call_worst_case.py
 src/tokenops/control/policies/progress_guard.py
 src/tokenops/control/policies/step_cap.py
+src/tokenops/control/policies/time_budget.py
 src/tokenops/control/policies/tool_fix.py
 src/tokenops/control/policies/tool_output_cap.py
 src/tokenops/control/policies/trajectory_hint.py
@@ -66,6 +70,7 @@ src/tokenops/server/__main__.py
 src/tokenops/server/app.py
 src/tokenops/ui/__init__.py
 src/tokenops/ui/app.py
+src/tokenops/ui/policy_labels.py
 src/tokenops/ui/run_detail.py
 src/tokenops/ui/store_client.py
 src/tokenops/ui/theme.py
@@ -89,28 +94,36 @@ tests/test_cost_guard.py
 tests/test_cross_process_budget_gating.py
 tests/test_crossing_hook.py
 tests/test_demo.py
+tests/test_demo_policy_names.py
 tests/test_governance_config_cache.py
+tests/test_governance_event_names.py
 tests/test_governance_per_agent.py
 tests/test_integration.py
 tests/test_ledger.py
+tests/test_ledger_backend_contract.py
+tests/test_ledger_backend_mode.py
 tests/test_llm_boundary_precall.py
 tests/test_output_runaway.py
 tests/test_policies_wrap_integration.py
 tests/test_policy_coordination.py
+tests/test_policy_names.py
 tests/test_pre_call_worst_case.py
 tests/test_preview_mode.py
 tests/test_pricing.py
 tests/test_progress_guard.py
 tests/test_propagate.py
+tests/test_provider_usage.py
 tests/test_reason_encoding.py
 tests/test_server_enforcement.py
 tests/test_step_cap.py
 tests/test_store.py
 tests/test_thread_safety.py
+tests/test_time_budget.py
 tests/test_tokenops_run.py
 tests/test_tool_fix.py
 tests/test_tool_output_cap.py
 tests/test_trajectory_hint.py
 tests/test_trajectory_hint_e2e.py
+tests/test_ui_policy_names.py
 tests/test_wrap_adapters.py
 tests/test_wrap_complete_chronicle.py

{agent_tokenops-0.2.1 → agent_tokenops-0.4.0}/src/agent_tokenops.egg-info/requires.txt

@@ -1,4 +1,4 @@
-agent-chronicle>=0.3.0
+agent-chronicle<0.6,>=0.5.0
 openai>=1.0
 anthropic>=0.40
 pyyaml>=6.0
@@ -8,6 +8,9 @@ httpx>=0.27
 fastapi>=0.115
 uvicorn>=0.32
 
+[contract]
+agentplane-control-plane>=0.2.0
+
 [dev]
 pytest>=8.0
 pytest-asyncio>=0.24

{agent_tokenops-0.2.1 → agent_tokenops-0.4.0}/src/tokenops/__init__.py

@@ -4,7 +4,7 @@ from tokenops.env import load_env
 
 load_env()
 
-__version__ = "0.2.1"
+__version__ = "0.4.0"
 
 
 def init() -> None:

{agent_tokenops-0.2.1 → agent_tokenops-0.4.0}/src/tokenops/config/default.yaml

@@ -1,5 +1,6 @@
 # TokenOps control plane seed. Consumed by tokenops.control.build_governor / Store auto-seed.
 # Budgets are spend caps bound to a segment; policies are the (detect, fix) templates.
+# Policy keys are canonical IDs, not display labels or instance IDs. See docs/product/policies-index.md.
 governance:
   budgets:
     - id: run_llm_cap
@@ -31,7 +32,6 @@ governance:
       mode: minimize
     context_compaction:
       ctx_max: 100000
-      has_hook: false
     output_runaway:
       repeats: 4
       max_retries: 2

{agent_tokenops-0.2.1 → agent_tokenops-0.4.0}/src/tokenops/control/__init__.py

@@ -3,14 +3,9 @@
 The Account (ledger) + Enforce (policies) half of the control plane. Consumes
 attributed boundary crossings, records them, and decides: steer or stop.
 
-Ten policies (delegation_cap dropped — fan-out is concurrency_cap, spend is
-cost_budget / pre_call_worst_case), evaluated by moment:
-  pre_call : concurrency_cap, tool_fix, context_compaction, cost_guard, pre_call_worst_case
-  stream   : output_runaway
-  observe  : cost_budget, step_cap, tool_output_cap, progress_guard
-
-Source of truth: docs/policies/ and docs/governance-policy.md. ``core.py`` is the
-canonical vocabulary.
+Built-in IDs and display labels live in ``config.POLICY_TEMPLATES``; see the single
+glossary at ``docs/product/policies-index.md`` and behavior docs at ``docs/policies/``.
+``core.py`` is the canonical runtime vocabulary.
 """
 
 from tokenops.control.attribution import (
@@ -62,7 +57,15 @@ from tokenops.control.integration import (
     wrap_complete,
     wrap_stream,
 )
-from tokenops.control.ledger import Budget, Ledger, RunState, segment_key
+from tokenops.control.ledger import Budget, Ledger, LocalRunState, segment_key
+from tokenops.control.ledger_backend import (
+    AggregateState,
+    ApplyResult,
+    HttpLedgerBackend,
+    LedgerBackend,
+    LedgerEvent,
+    PrecheckRequest,
+)
 
 # Process-wide: re-attach after every reset_session (Chronicle clears on_crossing).
 install_crossing_hook()
@@ -104,8 +107,15 @@ __all__ = [
     # ledger
     "Budget",
     "Ledger",
-    "RunState",
+    "LocalRunState",
     "segment_key",
+    # ledger backend (remote-only)
+    "LedgerBackend",
+    "HttpLedgerBackend",
+    "LedgerEvent",
+    "PrecheckRequest",
+    "AggregateState",
+    "ApplyResult",
     # harness
     "Governor",
     "RaiseControls",

{agent_tokenops-0.2.1 → agent_tokenops-0.4.0}/src/tokenops/control/boundary.py

@@ -15,6 +15,7 @@ from typing import Any
 from tokenops.control.attribution import _build_attribution, require_registration
 from tokenops.control.context import current_governance, current_span
 from tokenops.control.core import NodeType, Observation, Usage
+from tokenops.control.usage import usage_from_counts
 
 _KIND_MAP: dict[str, NodeType] = {
     "llm": "llm",
@@ -55,6 +56,7 @@ def observation_from_crossing(
     model: str = "",
     ts: float | None = None,
     extra_tags: Mapping[str, str] | None = None,
+    compaction: Mapping[str, int] | None = None,
 ) -> Observation:
     reg = require_registration()
     attr = _build_attribution(reg, service=service)
@@ -73,24 +75,9 @@ def observation_from_crossing(
 
     if node_type == "llm":
         usage_obj = getattr(result, "usage", None)
-        if usage_obj is not None:
-            usage = Usage(
-                input=int(
-                    getattr(usage_obj, "prompt_tokens", 0)
-                    or getattr(usage_obj, "input_tokens", 0)
-                    or 0
-                ),
-                output=int(
-                    getattr(usage_obj, "completion_tokens", 0)
-                    or getattr(usage_obj, "output_tokens", 0)
-                    or 0
-                ),
-            )
-        else:
-            usage = Usage(
-                input=int(getattr(result, "input_tokens", 0) or 0),
-                output=int(getattr(result, "output_tokens", 0) or 0),
-            )
+        usage = usage_from_counts(
+            usage_obj if usage_obj is not None else result, native=usage_obj is not None
+        )
         text = getattr(result, "content", None)
         if text is None and hasattr(result, "completion"):
             text = getattr(result, "completion", result)
@@ -116,7 +103,7 @@ def observation_from_crossing(
         raw_roll = getattr(result, "rolled_up_cost_micros", None)
         if raw_roll is None:
             raw_roll = input_state.get("rolled_up_cost_micros", 0)
-        rolled_up = int(raw_roll) if isinstance(raw_roll, (int, float, str)) else 0
+        rolled_up = int(raw_roll) if isinstance(raw_roll, int | float | str) else 0
         output = dict(result) if isinstance(result, dict) else {"result": str(result)}
 
     return Observation(
@@ -133,6 +120,7 @@ def observation_from_crossing(
         result_hash=result_hash,
         rolled_up_cost_micros=rolled_up,
         boundary_tags=tags,
+        compaction=compaction,
         **_span_fields(service),
     )