scaleapi-vero 0.5.0__py3-none-any.whl

scaleapi_vero-0.5.0.dist-info/METADATA

@@ -0,0 +1,219 @@
+Metadata-Version: 2.5
+Name: scaleapi-vero
+Version: 0.5.0
+Summary: A harness for agents to optimize programs.
+Author-email: Varun Ursekar <oss@scale.com>
+License: MIT
+Requires-Python: <3.14,>=3.11
+Requires-Dist: click>=8.0.0
+Requires-Dist: pydantic>=2.11.7
+Requires-Dist: wcmatch>=10.1
+Provides-Extra: claude
+Requires-Dist: claude-agent-sdk>=0.1.56; extra == 'claude'
+Provides-Extra: harbor
+Requires-Dist: fastapi>=0.110; extra == 'harbor'
+Requires-Dist: httpx>=0.28.1; extra == 'harbor'
+Requires-Dist: jinja2>=3.1.6; extra == 'harbor'
+Requires-Dist: pyyaml>=6.0.2; extra == 'harbor'
+Requires-Dist: uvicorn>=0.27; extra == 'harbor'
+Provides-Extra: interpret
+Requires-Dist: openai>=1.0; extra == 'interpret'
+Provides-Extra: optimize
+Requires-Dist: async-lru>=2.0.5; extra == 'optimize'
+Requires-Dist: beautifulsoup4>=4.14.2; extra == 'optimize'
+Requires-Dist: httpx>=0.28.1; extra == 'optimize'
+Requires-Dist: lxml>=6.0.2; extra == 'optimize'
+Requires-Dist: openai-agents[litellm]<0.19,>=0.18.3; extra == 'optimize'
+Requires-Dist: orjson>=3.10; extra == 'optimize'
+Requires-Dist: pypdf>=6.2.0; extra == 'optimize'
+Requires-Dist: trafilatura>=2.0.0; extra == 'optimize'
+Provides-Extra: wandb
+Requires-Dist: wandb>=0.19.10; extra == 'wandb'
+Description-Content-Type: text/markdown
+
+# VeRO: a harness for agents to optimize programs, text, and agents
+
+[![Paper](https://img.shields.io/badge/arXiv-2602.22480-b31b1b.svg)](https://arxiv.org/abs/2602.22480)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](../LICENSE)
+[![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org/)
+
+VeRO gives an optimizer something to edit, a controlled way to evaluate it, and
+durable memory of everything it tried. The target is anything you can put under
+Git and score — a **program** (one function to a whole repo), **text** (a prompt,
+spec, or config), or an **agent** (its scaffold, tools, and prompts).
+
+VeRO runs the same **version → evaluate → select** loop over all of them. *Where*
+each candidate is produced and contained is a swappable backend, and **Harbor is
+the recommended one**: it runs the whole coding agent inside a reproducible,
+credential-isolated container and scores it against a trusted evaluation sidecar.
+That is the right default for optimizing agents and for any untrusted or
+reproducibility-critical run. Lighter local backends exist for trusted work that
+does not need containment.
+
+```
+  ┌─────────────────────────┐   submit candidate    ┌─────────────────────────┐
+  │  candidate production   ├──────────────────────►│  evaluation service     │
+  │                         │                       │                         │
+  │  coding agent, command, │◄──────────────────────┤  owns cases + scoring   │
+  │  or custom strategy;    │  score + diagnostics  │                         │
+  │  edits its own Git      │                       │  development: may ask   │
+  │  worktree per candidate │                       │  validation:  aggregate │
+  └───────────┬─────────────┘                       │  test:        withheld  │
+              │ commit                              └───────────┬─────────────┘
+              ▼                                                 │ report
+  ┌─────────────────────────┐    next round     ┌───────────────▼─────────────┐
+  │  candidate history:     │◄──────────────────┤  selection: keep the best   │
+  │  every version kept,    │                   │  feasible candidate         │
+  │  each one re-selectable │                   └─────────────────────────────┘
+  └─────────────────────────┘
+
+  Every model call on both sides goes through the inference gateway, which holds
+  the provider key and meters spend in tokens against a per-scope budget.
+```
+
+## Install
+
+```bash
+uv sync --extra optimize        # or --all-extras for the full toolchain
+uv run vero --help
+```
+
+> The published distribution is **`scaleapi-vero`** (`pip install scaleapi-vero`);
+> it imports as `vero`. Do **not** install `scale-vero` from PyPI — that name is
+> an unrelated placeholder squatted in July 2026, not VeRO.
+
+Python 3.11–3.13. 3.14 is excluded because litellm does not build there.
+
+## Quickstart — no credentials needed
+
+The C matrix-multiplication example is deterministic and runs with **no model
+credentials at all**. Its editable target contains only C; a trusted external
+harness compiles it, checks correctness, and measures latency.
+
+```bash
+cd examples/c-matmul/target
+git init -b main && git add .
+git -c user.name=vero -c user.email=vero@localhost commit -m baseline
+cd ..
+
+uv run vero evaluate --config vero.toml     # score the baseline
+uv run vero run --config vero.toml          # optimize
+```
+
+VeRO evaluates the baseline, gives an isolated worktree to the configured
+producer, evaluates its commit, selects the faster feasible result, and leaves
+the original target untouched.
+
+## Examples
+
+Each is a complete, checked-in target plus harness — clone-and-run, not a sketch.
+
+| Example | Optimizes | Needs |
+| --- | --- | --- |
+| [`c-matmul`](examples/c-matmul/) | a C matmul kernel, for latency under a correctness constraint | **nothing** — deterministic, no credentials |
+| [`circle-packing`](examples/circle-packing/) | a packing algorithm: 26 circles in a unit square, maximizing the sum of radii | a model, via `LITELLM_BASE_URL`/`LITELLM_API_KEY` or `OPENAI_BASE_URL`/`OPENAI_API_KEY` |
+| [`harbor-circle-packing`](examples/harbor-circle-packing/) | the same target, but with the agent contained and scored by a sidecar | Docker + credentials |
+| [`harness-conformance`](examples/harness-conformance/) | nothing — it checks the *stack*: whether a new agent or model can actually drive a run | credentials for the pair under test |
+
+Run `harness-conformance` before spending a real benchmark on a new harness or
+model. Every harness addresses its provider differently, and it costs minutes to
+find that out instead of hours.
+
+### A real run, end to end
+
+`harbor-circle-packing` runs a coding agent in a container, scores each candidate
+through a trusted sidecar, and finalizes on a `test` partition the agent never
+touches. One run with `mini-swe-agent` and `claude-sonnet-5`:
+
+![circle-packing search progress](examples/harbor-circle-packing/results/progress.svg)
+
+**0.9598 → 2.5766 on the held-out partition**, `shipped: true`, in about an hour.
+The best published result for 26 circles is ~2.635. The agent wrote a 15 KB
+Lubachevsky–Stillinger-style growth algorithm with LP refinement — no hardcoded
+coordinates.
+
+Two details worth reading off the left panel. The red point is an **infeasible**
+candidate: it scored 2.5341 but overlapped, the harness rejected it on the
+`valid == 1` constraint, and the agent's next commit was "Add safety margin to
+guarantee strict feasibility". And the last five evaluations are flat — it found
+the idea early, then polished.
+
+**The cautionary half.** The same task run with `codex` and no prohibition on
+hardcoding scored **2.6360 in eight minutes** — higher than the honest run — by
+copying the published Packomania table into 26 coordinate literals. It satisfies
+the objective exactly and held-out scoring cannot catch it, because every
+partition here holds one deterministic case, so a memorized answer transfers
+perfectly. The instruction now forbids it. The general lesson is the one this
+suite is built around: a fixed single-instance objective measures lookup and
+problem-solving identically, and only varying the instance across partitions
+separates them.
+
+Regenerate the figure from any session directory:
+
+```bash
+python examples/circle-packing/make_figure.py <session-dir> -o results/progress.svg
+```
+
+## Which backend
+
+| Backend | Best for | Entry point |
+| --- | --- | --- |
+| **Harbor** — recommended | optimizing agents; untrusted or reproducibility-critical runs | `vero harbor run` |
+| [Command harness](docs/guide.md#optimize-a-program-with-a-command-harness) | any language; a trusted local evaluator driven over versioned JSON | `vero run` |
+| [Python tasks](docs/guide.md#python-benchmark-tasks) | Python evaluators via `scale-vero-tasks`, no JSON contract to write | `PythonTaskBackend` |
+| [Native in-process](docs/guide.md#python-api) | fast trusted local runs; a coding agent editing a host-bound sandbox | `vero optimize` |
+
+The target and evaluator do not have to be Python: external evaluators and
+producers connect over command protocols.
+
+## What you get
+
+| | |
+| --- | --- |
+| **Any target** | a program, text, or an agent — anything Git-versioned and scoreable |
+| **Any producer** | a coding agent (any provider via LiteLLM), an external command, or a custom strategy |
+| **Durable and inspectable** | every candidate is versioned and re-selectable; tool calls and evaluations stream to an event log |
+| **Population search** | `EvolutionaryStrategy` fans out N offspring per round with tournament selection |
+| **Metered** | per-scope token accounting through the gateway, with per-case cost and latency distributions |
+
+## Where things are
+
+| Path | What |
+| --- | --- |
+| [`docs/guide.md`](docs/guide.md) | the full guide: Harbor, command harness, Python API, tasks, sessions, concepts, safety boundaries |
+| [`docs/harbor-architecture.md`](docs/harbor-architecture.md) | how the contained run is assembled, module by module |
+| [`docs/agent-setup-guide.md`](docs/agent-setup-guide.md) | getting a coding agent wired up |
+| [`examples/`](examples/) | c-matmul (no credentials), circle-packing, harbor-circle-packing, harness-conformance |
+| [`src/vero/`](src/vero/) | the library: optimization kernel, runtime, gateway, sidecar, CLI, agent adapters |
+
+For end-to-end agent-optimization benchmarks, see
+[`../harness-engineering-bench/`](../harness-engineering-bench/), which also
+documents how each coding agent must be pointed at the gateway — the one thing
+that reliably costs a run when it is wrong.
+
+## Paper and reproduction
+
+VeRO was introduced in [*VeRO: A Harness for Agents to Optimize
+Agents*](https://arxiv.org/abs/2602.22480), accepted at ICML 2026. The paper
+studies agent-harness optimization; the current library generalizes the same
+version/evaluate/select loop to programs more broadly.
+
+The frozen code for reproducing the paper is preserved on the `paper/v1` branch
+and at the `paper-v1` tag:
+
+```bash
+git checkout paper-v1
+```
+
+The same pre-v0.5 tree is also readable in place under
+[`../legacy/`](../legacy/). Note that it is `scale-vero` 0.4.7 and this is 0.5.0,
+both importing as `vero`, so they cannot share a virtualenv.
+
+## Development
+
+```bash
+uv sync --all-extras
+uv run pytest tests/test_v05_*.py
+```
+
+VeRO is licensed under the MIT License.

scaleapi_vero-0.5.0.dist-info/RECORD

@@ -0,0 +1,130 @@
+vero/__init__.py,sha256=91Qf1606S0Edki9savsTcV7UXqLmH29fVmOX1YYn_iE,887
+vero/candidate.py,sha256=TqmKGkoRg-KqPDQ5xVpYd0IBEkTIs5QWlzJuERDhWbM,2415
+vero/cli.py,sha256=PoL9CR4Jhh7vMAt2urO0KKBhLCMgH5mpD3ScheRMVUs,33822
+vero/config.py,sha256=A16ikOFokQ3-1wOq9llVoDn5k_uijUUnEr2es3fIVtk,19312
+vero/evals_cli.py,sha256=PEVrwEpiIfe0VMqln9MI2JGhV9X0ripj-QLLkjB62Jo,26470
+vero/exceptions.py,sha256=MOqTY14yBxNUAXXK4nVSfp80NXXO2YebhBgAVUxJU9o,74
+vero/layout.py,sha256=M1Ge806KmYyuO3CH0yTJjo01-S_5rco2WLRRTULr30c,7368
+vero/models.py,sha256=_en5V2AmQ9cTGK0m6rs3xW4FC16QYRz-7nxjITgLqUE,461
+vero/report.py,sha256=av71aYK2F2LR3TCYmuv1O3_KzuAzEWEYoBf7acXiGNM,18928
+vero/sandbox.py,sha256=jdsGaQsVuhHL9RsMxNosZ4GWqxi38YzNa3lGqD9l_TU,26832
+vero/staging.py,sha256=UjQtgKwWo60x9u7AKqtyeNXYzAs_RUDZjWVB-ILStRk,2678
+vero/agents/__init__.py,sha256=akQDnSBn16k5GCF1z4dABUBqRzSm07VYJisGtMUvm_Q,609
+vero/agents/claude_code.py,sha256=rX-vlzyXcBnSnifKLr1xIkerRIzudt8KQlsSlJdXO5w,13255
+vero/agents/events.py,sha256=oO_hwe6Ux-ZgWh-a2VKEPXvZAkixU2M5sFE0RXrTCI8,886
+vero/agents/producer.py,sha256=MLRMh_rRcUIvKazHUpo3XV-_1hdoFWqnReQNdmAvHCA,5604
+vero/agents/protocol.py,sha256=dQdigmhIQ6YGulNMQiMjWCU6hhnq4b8w8CelMAkQip0,2828
+vero/agents/vero.py,sha256=rKEnlJ-fnTX10P7ZbRB6_QRQIMhv4nY2yPtJd3RoJuE,15430
+vero/candidate_repository/__init__.py,sha256=vOvHaMadGWmXSvjJtTyR-xf_Be7WJA1NFQOHiJkAxVY,310
+vero/candidate_repository/base.py,sha256=8mtzQRRMx8CT7zK6SW5EdMQ82uKLTVghIbnkfxX49T0,2478
+vero/candidate_repository/git.py,sha256=JbPM4SchUC2OoA59O_bfcFaCJGZAUr3Xn3RNzf38Q7I,31857
+vero/evaluation/__init__.py,sha256=1ccdiuRHVXduAvKYVvbRBpeUecNnriFMZUwTgADPkrQ,4602
+vero/evaluation/engine.py,sha256=oAPj80JC7HtORJnIOg0m_B66CibFyssIR-qpZFqOjUA,22116
+vero/evaluation/evaluator.py,sha256=wIx6UqjAnDFdMqHIV8AtOswhI75OHZ6k5B1kPOmCAsw,11029
+vero/evaluation/exceptions.py,sha256=baA5GXfjLZUPQ5ZMU6lNPvWdwQA2kEMSY8PeQVD284g,1814
+vero/evaluation/models.py,sha256=Tdql3fqfRsP39H5JCdKaPmiFFf_DBk-z665A6tdhWdQ,28116
+vero/evaluation/backends/__init__.py,sha256=6b0tyDz2Ek52uh1HdxFLs3ll2hIeqN-pxCnkj3t-drw,368
+vero/evaluation/backends/base.py,sha256=1qe3T41qheIJGfVCmxxePLN_Kqs1Lht6ZOApS0oML1w,3390
+vero/evaluation/backends/command.py,sha256=HfxXwbp7CU6uGjTsd59eaxLpoOKYCLICnM8ftdWI-M0,14449
+vero/evaluation/backends/python_task.py,sha256=O08vFaHZuOKyjFOqq7lNDOiSkuOyAp81gxV5s7f77XA,12384
+vero/evaluation/scoring/__init__.py,sha256=wGkFEuN6MMbH8HSbtaRH166Eab8qFfIPI3mdsptcHJA,276
+vero/evaluation/scoring/error_taxonomy.py,sha256=EyW9gJoBaSoJu9qShT3v7TuiwzOQb62Mo3gS-y7cNvo,12353
+vero/evaluation/scoring/objective.py,sha256=i3-uwwtuzeE5-gwDMUgOkGJUsqyvdRrMlyJ5NunST5I,6584
+vero/evaluation/scoring/security.py,sha256=weAZElrMO9ZrqGtX3kgeA2X0pGPbAROf0fyVTQXajMU,3555
+vero/evaluation/store/__init__.py,sha256=arM-Q0KeTsfPdWf7NXLxg_vRy3LYhs_1XlKj2j0tQB4,269
+vero/evaluation/store/budget.py,sha256=VQqAGrK3eZmYbu4HNHELHJ3zYhsEjnHFUgGT_4Jxm6o,9962
+vero/evaluation/store/persistence.py,sha256=UeTjBUbbU7GvrZfETyES4Xlk0jPqr_RB-f7GYnqOPMc,17878
+vero/gateway/__init__.py,sha256=VKQa9rTW-fMBN6ZW2bpYvBlscLuM3Hy6ETGimlXNmeI,662
+vero/gateway/inference.py,sha256=gQgWoSDIOODTVQURUq3XBqjNC-FMsJX_zu5eir0y_Gw,50195
+vero/harbor/__init__.py,sha256=tg0Gff6WUxUa6eJ32-vkK3bfgIRsdFAxv6dzWM-iefk,1500
+vero/harbor/backend.py,sha256=cik0Ru48BSna1ANaB0UMfobhyfoEdfAVQzQCT-Lzxp8,77430
+vero/harbor/cli.py,sha256=5z_OK_A0qxalcwX5mwwCC3ZEDJJG6l7S23L4Lmk6L8k,50691
+vero/harbor/deployment.py,sha256=d1C5DwwWLSOMF_V-MxnvW2ZX_wt6SIYKn65Dwe3pCXU,18701
+vero/harbor/generation.py,sha256=CXDHzNidYcGutauexQshlCCBLONCnnrvoUv6n4A2OnQ,2279
+vero/harbor/build/__init__.py,sha256=tWY4wKxPwzlLb3V93Wm8JrciFY8tA07SiJzEJSqM_5g,1020
+vero/harbor/build/compiler.py,sha256=RwGyx3p9IzF3lO7ynRseSPQoTnUIDDvQIi3JcZaXo9k,37116
+vero/harbor/build/config.py,sha256=RpkyuWDPuEbxlfLmjJz-ygxjSJhtKb1G9fpNlbqwVWY,34411
+vero/harbor/build/loader.py,sha256=9II0bgv3MIyOgBbD5MuR2iswrlyBDTZ5RilvBG_3Syg,6863
+vero/harbor/build/specs.py,sha256=hb-uy_rA-xnShjTndKdiWt8kmBKxUvc9KP0euhCeGTg,16102
+vero/harbor/build/templates/Dockerfile.gateway.j2,sha256=w5-xSFblrsR_AUW6crf-TR37rbpbVe_PY2S4IyT3si0,485
+vero/harbor/build/templates/Dockerfile.main.j2,sha256=LXEkRaRHbKD5kkZb_o0ihrINzEJm-raJKxuAek8ZSMM,668
+vero/harbor/build/templates/Dockerfile.sidecar.j2,sha256=3yutXn8MvHewRcJV9KYXPTBXeK5aCFlTotxXrXDvjGg,2436
+vero/harbor/build/templates/docker-compose.yaml.j2,sha256=gzFVfkfhLYzAuM_tUiwXBPwZsLt8MiqKRP9ljd9i6jA,3410
+vero/harbor/build/templates/instruction.md.j2,sha256=MvKDjPcbgr2O5ugi9EOKQuE5IVrwFL4JrJDv5O6rVyo,6274
+vero/harbor/build/templates/seed.sh.j2,sha256=qW65TzlAuq9PTZwZ5M6U_to8PfVEYn3gNK-Al9bWG30,1403
+vero/harbor/build/templates/solve.sh.j2,sha256=3fBSPDQ-tpxxh-eLm9i4UzDpxZjCJuF95zDF1qcjnsM,454
+vero/harbor/build/templates/task.toml.j2,sha256=98EAGrbC-igIEcwXljc2dxR_3S52RpPobqMiYFavmYo,1603
+vero/harbor/build/templates/test.sh.j2,sha256=tjuO_i8ziMW8t4gzQ5A-IArVdizJW32zH5I6ue6hDUI,244
+vero/interpret/__init__.py,sha256=pQFvmOQ6VNClbagOVewCZL8uMz65bf233AqWzDcquKQ,549
+vero/interpret/cache.py,sha256=Ra37w4ouZYJ7jUJbzkZFHdyt20JzRggiJmupPjSzWGw,3292
+vero/interpret/cli.py,sha256=KerPeWkcuGHrBACcIm779Y0MQvST0SY06cWH2tCJ6EA,10753
+vero/interpret/config.py,sha256=LdLWnDh2fp6Z1F4yKuUz4tj0ObsGUfznaQxR_AT0TEg,2543
+vero/interpret/models.py,sha256=IJNsUL_irS1aEpm0fodm8lLQb5jItT24-QEjmFSAcZQ,6794
+vero/interpret/analysis/__init__.py,sha256=PCma2L_NTsOk6UBX_fFgRqS-VoySUKj-6WSJiZis-P0,135
+vero/interpret/analysis/display.py,sha256=Zl0TyNPduGr8wQdmZJuR7skvXolx0rymiV2r2WPS5Sk,2729
+vero/interpret/analysis/figures.py,sha256=RALN49fheHxVUbK3OGGPPsm8P67LzcyXnHTm2fSA2gs,19627
+vero/interpret/analysis/paper_figures.py,sha256=DIsVcHGZuUACbqu0tZNZXQCkNMW9Ye9hUhc76NPXGp0,11150
+vero/interpret/analysis/preamble.py,sha256=37CAMpBXDwb4hE0W7MlbQdcpe9HyHbt-zYwkqLh561I,9494
+vero/interpret/analysis/stats.py,sha256=4BMMhwyq4tuOPPFiPloD_kOr4IIh60NGnZ8XFzVnxac,9268
+vero/interpret/analysis/brand/house_style.py,sha256=HJbf7AcMADoFKtD2DZ5DQD5WK1L0YL4YJNLHDTMmlXo,5381
+vero/interpret/analysis/brand/fonts/GeistMono.ttf,sha256=0A5ZC46zpZrMMpstBE_RQ66TUJC32jMZnr7ifMfegZY,171948
+vero/interpret/analysis/brand/fonts/HostGrotesk.ttf,sha256=dMd7joUNWN09iyLjkRGnO-80UN6ftXAY75kRny1IT10,81784
+vero/interpret/artifacts/__init__.py,sha256=4Fd4CEMWs3aM_cghJ1XnuWgFDjpx6nwHBiCDVjPuZRY,211
+vero/interpret/artifacts/base.py,sha256=TsiR0Zr_SxcKQf-h8V2NJaWVRNhLGkM0DkamwVnYyts,1646
+vero/interpret/artifacts/harbor/__init__.py,sha256=knFUH-H4NK75mw9mpBCG_8E2SScMXr1Et2dxp21__Z0,159
+vero/interpret/artifacts/harbor/adapter.py,sha256=Appa3hNR1Og31ZvIfBnAKpRT2UHbWdxsvBLL5NN8LJg,6969
+vero/interpret/artifacts/harbor/repo.py,sha256=URRPxeOnKRbizq4jcMKy2Xmiqs0MtkINJRBgtgxTMCc,3468
+vero/interpret/artifacts/harbor/session.py,sha256=qna55orJIh051bOHPNdZ1ZUCSkfn9kvoqFGWGX2WGB4,3556
+vero/interpret/edits/__init__.py,sha256=KT_IElZ3iH2lA_QJyXGSCsaD2eM5rALvntHcfJ6Rm-g,153
+vero/interpret/edits/decompose.py,sha256=9-mIr3l2WEhGydWDE3eMKTb2WDdTacWl0OWKjc1fytw,8213
+vero/interpret/edits/locus.py,sha256=GW6HnYjha2eRljrrwFJnEuucJS3ku3vm1UvXNcijHWs,6416
+vero/interpret/edits/provenance.py,sha256=QELhGfUh_KJUhBQS8HqiKvYw27wQlJwoIaifnOGgD38,2681
+vero/interpret/labeling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+vero/interpret/labeling/client.py,sha256=swS8coSYQ7UwLb7yRpixs8AHEIXC-WLqe5Qe_RYBUEs,3186
+vero/interpret/labeling/labeler.py,sha256=6OSTcmDfJzM3aVdG-rSg6uaKLM5ThYq3ct_gXXCQwpg,8154
+vero/interpret/labeling/taxonomy.py,sha256=aABtPsvkZAKWI9EB3H6rAIjSvs0qOT_MfLZ3XVYpK_c,9322
+vero/optimization/__init__.py,sha256=fLV848g-2Yz4_xTnrCym9DeEalH_ZTfqkQGm4EO89M0,1233
+vero/optimization/command.py,sha256=4H5h4wLNEUNk3Lxa0t6rlZm5l_bXha93JdNQew8Ciak,6435
+vero/optimization/models.py,sha256=AeSEmMd0RYvN5WY5cu52zq-Rk6Bpq7me7cgMo55N9EQ,4262
+vero/optimization/optimizer.py,sha256=q4Hdoc8NshdnLyIMN1l_YSLxISPxrkAM9M1SZnBogdQ,29951
+vero/optimization/protocols.py,sha256=DD0eLYfhHfYAFMKq19rF63L_9KcEgjbahqimEeyJY7s,2581
+vero/optimization/strategy.py,sha256=6z4LIa1NFcB5_-8PKMmvcJpkuWF8_gvx1QXoncjnE2E,13055
+vero/runtime/__init__.py,sha256=Nevay1iTRnCzpwLWm6HQPU9RmZA7rCdNYkOlPIatbr8,1464
+vero/runtime/artifacts.py,sha256=Cg6O5SPh1bw7rZnrX9O78NgzPetleNEBKHSOa3krQnw,1463
+vero/runtime/context.py,sha256=fWhp8ta31BNH0HvSkPhrWAvvx_aqbGMI4IvhMaJQVwc,23100
+vero/runtime/events.py,sha256=JfNimVxIJPJjOYCQkhO6eIE9WyayTX2tJxr3MNLjomk,3802
+vero/runtime/factory.py,sha256=DSmXEcZixPXVef00LFhrtc5sXv_zQUfpS16g5-lWgsE,10082
+vero/runtime/session.py,sha256=QBgd63Uwoha4zWwaAfseAgLbR3V-yznerbfUhKceFW0,20440
+vero/runtime/wandb.py,sha256=zr3MoEp1rqxmffhNDzHpygFZcPHb_KWZMp8l3eq7n_s,22488
+vero/sidecar/__init__.py,sha256=h5Z9AjDgyHkodYl8BBUIcUMlWwwhuTW4CXOoKd1o2jc,2348
+vero/sidecar/app.py,sha256=pnla9ment5W5R8BuOtINU5CO-J6Ycmzlj-ObGca7C9I,7763
+vero/sidecar/auth.py,sha256=T0Z0bsUGHqB4OScMuqbfAv2tVEi37c2zxn1rSMRDE3k,2654
+vero/sidecar/isolation.py,sha256=LmySiA-562TH8hmlNNbCKEDcoynQ3CDqAZNj4Y-OUzg,2006
+vero/sidecar/serve.py,sha256=4J_Dw1QaVDlMLmy2Mz29nbrZKHpATnzPPA0bQ-2Wm6s,2919
+vero/sidecar/session.py,sha256=h6D56Qi57c4zMd8-Vd21T5ES9niUBJfsmJsPs6u8oKs,8323
+vero/sidecar/sidecar.py,sha256=cQC5TdpzFIQSlls3uuLRhyWclsOGaBzoVWZXn5gX5Dk,33862
+vero/sidecar/transport.py,sha256=WKvLt6Aq5znBtj9WXjubznuztVhyLHiLLWAre_GoIm8,6606
+vero/sidecar/verifier.py,sha256=YNgdFLvNHIelds0njObrUOzTw7DyPLj5kSayeyya1fs,25740
+vero/skills/evals/SKILL.md,sha256=Ms1USjcmTUeLAZhfERePZHawk_bGsvaC1ElbQ6FOKMw,6488
+vero/templates/report.html,sha256=oFR9sq6rqZJ9XqOpHgVgGbovGCTOTojUTvEQ933I4cE,24903
+vero/tools/__init__.py,sha256=VmeQHoOkt5ulp5Q9bDNzz0mQIiNGPxt-I5mJp9LvHvk,903
+vero/tools/base.py,sha256=tj-Znw1DKcWA4m0ikYEY6nL8z1OXO2sXjNlJq2LPy2U,530
+vero/tools/evaluation.py,sha256=Y3OFcJfRiqo89Mg84K6H7SHGNgRkXGevf17Yd2NATYQ,3486
+vero/tools/planning.py,sha256=i2bSUX6sVS5a3pxG7-BKlR7ChdgreyWtuPxzm7Cm4wE,3037
+vero/tools/registry.py,sha256=h1HraZGl_hdCnt9hiKkGByw-96oUq6Ez6-dKxBL5rSA,2803
+vero/tools/sandbox_tools.py,sha256=gV_V6kSV8geARHpYfljPS-UfABdkrgbKxU4CKGgaAME,3041
+vero/tools/sub_agent.py,sha256=ckGSxLNhXzbyVT9TJpsysDsuxJ7tQzNtIEtetGkmitw,6520
+vero/tools/web.py,sha256=1TLW1ZMPqRl7-Ha_9thDgKZ_5ixa2kq_mOnhQh4tyCg,10314
+vero/tools/utils/__init__.py,sha256=YHDUkg5b_9U6kM-8o66-6-dzdSPd3VBrqzCZY_IJeOA,928
+vero/tools/utils/openai_agents.py,sha256=MJPZ2lzdBrrWk2PKjLNeIyUqq8PoILOoSBCokOuTnQY,2795
+vero/utils/__init__.py,sha256=aSdw1Oem2-KX9g1PPGUFl65Uhr0TEiRY55xOva0Ot8Q,549
+vero/utils/asyncio.py,sha256=3AgO8CIJWXx7FSnHffAiPMPDtIH-_oyPUx-mzbLAoYA,8214
+vero/utils/general.py,sha256=5WLwz-YtoX4L0IsgxOiwbF9eb2dmUHYIURwcCTXv8fc,2631
+vero/utils/openai_agents.py,sha256=ylv1YzP68aRMjt3Brrn7-hIGhUAVlsk12uwZgA-vtj4,1667
+vero/workspace/__init__.py,sha256=2wd9NpHD1eucCGJp2ebOICvKTR2UYkS8OPwuXetkq4o,177
+vero/workspace/base.py,sha256=b__MYvXPLUquEQl1H8ZeptfVroSBWTdUCmRHx01x16o,5235
+vero/workspace/git.py,sha256=LXM0xLMka4tYBoKequ_2sZUkjlpFgY-ZEiyIx23cpMc,14679
+scaleapi_vero-0.5.0.dist-info/METADATA,sha256=nn3xl0U7EJPR_pUpHTSzRQna5ryG-wLl_7mUsHSOeAw,11348
+scaleapi_vero-0.5.0.dist-info/WHEEL,sha256=zOwg4jB6zX2kU910N-cMawjivD6tO8NEWvE12je1bVk,87
+scaleapi_vero-0.5.0.dist-info/entry_points.txt,sha256=jYSxsX5il21dxt1bqdc82OSNYtseD6b2Irrfe7m2NJI,67
+scaleapi_vero-0.5.0.dist-info/RECORD,,

scaleapi_vero-0.5.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.32.0
+Root-Is-Purelib: true
+Tag: py3-none-any

scaleapi_vero-0.5.0.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+evals = vero.evals_cli:main
+vero = vero.cli:main

vero/__init__.py

@@ -0,0 +1,34 @@
+"""VeRO's public program-optimization API."""
+
+from vero.candidate import Candidate
+from vero.candidate_repository import CandidateRepository, GitCandidateRepository
+from vero.evaluation import (
+    EvaluationBackend,
+    EvaluationRecord,
+    EvaluationReport,
+    EvaluationSet,
+    ObjectiveSpec,
+)
+from vero.optimization import CandidateProducer, OptimizationStrategy, Optimizer
+from vero.runtime import (
+    OptimizationSession,
+    create_local_optimization_session,
+    create_optimization_session,
+)
+
+__all__ = [
+    "Candidate",
+    "CandidateRepository",
+    "CandidateProducer",
+    "EvaluationBackend",
+    "EvaluationRecord",
+    "EvaluationReport",
+    "EvaluationSet",
+    "GitCandidateRepository",
+    "ObjectiveSpec",
+    "OptimizationSession",
+    "OptimizationStrategy",
+    "Optimizer",
+    "create_optimization_session",
+    "create_local_optimization_session",
+]

vero/agents/__init__.py

@@ -0,0 +1,24 @@
+from .producer import AgentCandidateProducer
+from .protocol import AgentContext, AgentRequirements, AgentRunResult, CodingAgent
+
+__all__ = [
+    "AgentCandidateProducer",
+    "AgentContext",
+    "AgentRequirements",
+    "AgentRunResult",
+    "ClaudeCodeAgent",
+    "CodingAgent",
+    "VeroAgent",
+]
+
+
+def __getattr__(name: str):
+    if name == "ClaudeCodeAgent":
+        from .claude_code import ClaudeCodeAgent
+
+        return ClaudeCodeAgent
+    if name == "VeroAgent":
+        from .vero import VeroAgent
+
+        return VeroAgent
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")