aid-runtime-python 0.1.39__tar.gz

aid_runtime_python-0.1.39/PKG-INFO

@@ -0,0 +1,268 @@
+Metadata-Version: 2.4
+Name: aid-runtime-python
+Version: 0.1.39
+Summary: The AID Framework Python runtime: model gateway with pinning and cost budgets, prompt registry, tool executor, OTel GenAI tracing, plain-async pipeline, and an eval harness that gates on statistical regression against a stored baseline.
+Author: The AID Framework authors
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/aid-framework/aid-framework
+Project-URL: Documentation, https://github.com/aid-framework/aid-framework/blob/main/docs/design.md
+Project-URL: Issues, https://github.com/aid-framework/aid-framework/issues
+Keywords: ai,codegen,llm,evals,opentelemetry,pydantic
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+Requires-Dist: httpx<1,>=0.27
+Requires-Dist: opentelemetry-api<2,>=1.24
+Requires-Dist: pydantic<3,>=2.7
+Requires-Dist: pydantic-ai-slim<3,>=2
+Provides-Extra: pgvector
+Requires-Dist: psycopg[binary]<4,>=3.1; extra == "pgvector"
+Provides-Extra: deepagents
+Requires-Dist: deepagents==0.7.32; extra == "deepagents"
+Provides-Extra: dev
+Requires-Dist: mypy<3,>=1.11; extra == "dev"
+Requires-Dist: opentelemetry-sdk<2,>=1.24; extra == "dev"
+Requires-Dist: pytest<10,>=8; extra == "dev"
+Requires-Dist: pytest-asyncio<2,>=0.24; extra == "dev"
+Requires-Dist: ruff<1,>=0.6; extra == "dev"
+
+# AID runtime — Python
+
+The Python runtime library: the behavior layer imported by apps generated by the
+[`py-fastapi`](../../packages/generators/py-fastapi/) generator. Generated code is thin glue; this is where
+the behavior lives ([`docs/design.md` §4](../../docs/design.md), principle 1).
+
+Distribution name **`aid-runtime-python`**, import package **`aid_runtime`**. The two differ deliberately: a
+distribution name is conventionally hyphenated, and a Python import package cannot be. That asymmetry is
+asserted in `tests/test_package.py` so it cannot drift.
+
+Requires Python 3.11+.
+
+```sh
+pip install -e ".[dev]"        # the runtime plus its test/lint/type tooling
+pytest -q
+pip install -e ".[pgvector]"   # only if you want the pgvector store adapter
+```
+
+## What it provides
+
+| Module | Provides |
+| --- | --- |
+| `gateway.py` | `ModelGateway` — alias resolution, capability negotiation, ordered fallback, cost accounting, GenAI spans |
+| `providers/` | The `Provider` protocol, one HTTP adapter (`OpenAICompatibleProvider`), and one deterministic fake (`FakeProvider`) |
+| `prompts.py` | `PromptTemplate` / `PromptRegistry` — versioned prompts, typed rendering, few-shot assembly |
+| `structured.py` | `build_agent` — structured output via Pydantic AI only |
+| `tools.py` | `Tool` / `ToolExecutor` — declared definitions, argument validation, structured results |
+| `pipeline.py` | `Pipeline` / `PipelineContext` — plain-async named steps over a frozen context |
+| `agents/` | The native agent runtime: `AgentRuntime` — the loop, transfer vs. delegate, step/token/cost budgets with bounded degrade, memory, and a checkpointed human-in-the-loop pause |
+| `retrieval/` | Retrieval: connectors, chunkers, the `Embedder` / `Reranker` / `VectorStore` protocols, hybrid fusion, citations, and retrieval metrics |
+| `evals/` | Datasets, metrics, and the statistical baseline gate |
+| `tracing.py` | OTel GenAI spans: `llm_span`, `agent_span`, `record_usage`, `record_cost`, `record_attributes`, `record_hitl`, `record_exception` |
+| `cost.py` | `Budget`, `CostLedger`, `estimate_cost_usd`, `estimate_tokens` |
+| `types.py` | The request/response/usage/spec models everything else is typed against |
+
+194 names are exported from `aid_runtime`. The layering is acyclic and one-directional: `errors` and `types` import
+nothing else in the package, `gateway` is imported only by the package `__init__` and the eval runner, and no
+core module imports a higher layer back.
+
+## Model pinning
+
+An **alias resolves to an exact provider model id**, including a pinned version. That is not cosmetic: a
+baseline recorded against `gpt-4o` means nothing if the alias floats to `gpt-4o-2026-…` on the next run, so an
+**unknown alias is an error** (`UnknownModelAliasError`) rather than a silent fall-through to a provider
+default.
+
+```python
+from aid_runtime import (
+    Budget,
+    CompletionRequest,
+    CostProfile,
+    ModelGateway,
+    ModelSpec,
+    OpenAICompatibleProvider,
+    PinnedModel,
+)
+
+spec = ModelSpec(
+    name="gpt-4o-2024-08-06",
+    provider="openai-compatible",
+    cost=CostProfile(input_per_1k_usd=0.0025, output_per_1k_usd=0.01),
+    context_window=128_000,
+    max_output_tokens=4096,
+)
+
+gateway = ModelGateway(
+    providers={"openai-compatible": OpenAICompatibleProvider(api_key=...)},
+    aliases={"small": PinnedModel(alias="small", spec=spec)},
+    budget=Budget(max_usd=5.0, scope="nightly"),
+)
+
+result = await gateway.generate("small", CompletionRequest.prompt("hello"))
+result.text, result.usage, result.cost_usd, result.alias, result.attempts, result.fell_back
+```
+
+- `resolve(alias)` returns the `PinnedModel` (alias + `spec`); `provider_for(alias)` its provider. `require(alias,
+  capabilities)` asserts the capabilities *and* returns the pinned model, checking **both** sides — a model that
+  supports tool calling behind an adapter that does not serialise tool definitions cannot tool-call — and raises
+  `CapabilityMismatchError` naming what is missing.
+- `generate(alias, request, *, fallbacks=(), budget=None)` tries the alias then each fallback **in the order
+  given**, and reports the aliases actually attempted on the result. Fallbacks are ordered, not conditional.
+- Every charged call opens a span and updates the ledger. `CostLedger` tracks per-call `LedgerEntry` records
+  and yields a `SpendSummary`; `Budget` (`max_usd`, `max_total_tokens`, `scope`) is enforced before the call,
+  and `estimate_usage` / `estimate_cost_usd` price a request from a model's `CostProfile` when a caller wants
+  to check before spending.
+
+## The eval harness gates on statistics, not equality
+
+Phase 0 ratifies sampling-based gating: a model is **expected** to vary between runs, so a metric that
+compares two runs for equality is either always red or measuring nothing. Non-determinism here is not a bug to
+be fixed; it is the property the gate has to be robust against.
+
+- `Dataset` — versioned cases with inputs, expectations, tags and metadata; `from_records` / `from_json` /
+  `from_path`, `to_json`, and lookups by id (`case`) and by tag (`by_tag`).
+- Metrics — `ExactMatch`, `NormalizedContains`, `JsonSchemaValid`, and `LlmJudge`. `metric_names` and
+  `default_metrics` cover the common set.
+- `run_evaluation(dataset, runner, metrics, runs=5)` samples the runner **N times** and produces an `EvalRun`
+  of per-run metric means, so a single unlucky run does not decide the verdict. `evaluate_once` is the
+  single-pass primitive; a `DatasetRun` gives per-case outcomes and a rendered `summary()`.
+- `EvalBaseline.from_run(run, model=..., note=...)` stores a baseline as JSON: per metric the sample count,
+  mean and spread. `runtimes/python/tests/fixtures/capitals-baseline.json` is a committed example.
+- `BaselineGate(thresholds).evaluate(run, baseline)` compares the current sample against the baseline using a
+  one-sided normal test, with each `Threshold` carrying `metric`, an optional absolute `min_mean`, a
+  `max_regression` allowance, and an `alpha` significance level. A metric passes by clearing `min_mean`, by
+  being within `max_regression` of the baseline, or by regressing only within sampling noise.
+
+Two deliberate limits:
+
+- **`LlmJudge` is implemented and never CI-required.** A judge is itself a model call, and a gate that
+  depends on one non-deterministic call inside the gate you are trying to trust is the problem this design
+  avoids. `gateway_judge(gateway, alias)` builds the judge call when a caller wants it.
+- **`GateConfigurationError` refuses a threshold on a model-derived metric**, because an N-run sample of a
+  probabilistic judge cannot carry a fixed threshold honestly.
+
+`cost` is the enforced budget; a latency p95 budget belongs with Phase 2 dashboards, not here.
+
+## Retrieval
+
+`retrieval/` is an IR-driven layer: `binding_from_spec(retriever, embedding=..., store=...)` folds the IR's
+`retrievers`, `embeddings` and `stores` entries into one `RetrieverBinding`, which a `Retriever` then ingests
+and searches through. The runtime consumes the names the IR emits, field for field.
+
+- Three protocols, in the same style as `providers.Provider`: `Embedder`, `Reranker`, `VectorStore`. Phase 1
+  ships the implementations listed below and no others.
+- `FakeDeterministicEmbedder` maps text to a stable unit vector with a hash — keyless and offline, which is
+  what lets a retrieval gate run in CI. `OpenAICompatibleEmbedder` is the one hosted adapter: a single POST to
+  `/embeddings` over `httpx`, with the retry, timeout and error-chaining behaviour of the HTTP provider.
+- `LexicalReranker` is the only reranker. It is deterministic and lexical; there is no hosted rerank adapter.
+- Chunk ids are **content hashes**, so re-ingesting the same input produces the same ids and a no-op diff.
+  Ingest is therefore held to idempotence rather than to the byte-identical codegen guarantee.
+- **Pinning.** `embedModel` names an IR `embeddings` entry and resolves at codegen time to an exact `modelId`
+  plus its recorded width; the resolved id, width and store `kind` travel into the generated code. An alias is
+  never resolved at runtime, because a baseline recorded against a floating model means nothing.
+- **Cost.** Embedding calls charge the existing `CostLedger` through the existing `Budget`, using the catalog's
+  `CostProfile` for the pinned model. There is no retrieval-specific budgeting machinery.
+
+`RetrievalMetric` (`RecallAtK`, `MeanReciprocalRank`, `CitationGrounding`) is deliberately a **separate
+protocol** from the shipped `Metric`, which scores a single string prediction. Retrieval scores a *retrieved
+set*: recall@k and MRR need the ranked ids, and citation-grounding needs the passages behind the citations.
+Widening `Metric` would have changed an interface the existing gate already threshold-checks, for every
+existing implementation — so retrieval is sampled through `RetrievalGate.sample(...)` instead, producing a
+standard `EvalRun`, and then judged by the **unchanged** `BaselineGate`. Retrieval metrics are deterministic,
+so they pass the gate's own eligibility check.
+
+### pgvector
+
+`PgVectorStore` is a thin adapter over `psycopg` and the `vector` extension. Two consequences worth stating:
+
+- It is **locally provisioned and not covered by any gate.** No CI job starts a database, and no required
+  check touches one; the in-memory adapter carries the store gates, and the two adapters share the same
+  `VectorStore` protocol and the same `similarity` semantics. `compose.pgvector.yml` beside this README brings
+  up a database for local use.
+- The `[pgvector]` extra is **import-safe when absent**: importing `aid_runtime` or `aid_runtime.retrieval`
+  never imports the driver, and the adapter loading it raises a `ConfigurationError` naming the extra.
+
+## Control flow is plain async
+
+`Pipeline` is a list of named async (or plain) steps over a `PipelineContext` that is **frozen**, so a step
+cannot mutate what an earlier step observed — it returns a new context, which keeps a failed run's state
+inspectable. A step may return a context, a mapping, or `None`. Each step runs in its own span, a step raising
+anything aborts the run with the original exception chained (`PipelineError.__cause__`), and `StopPipeline` is
+the supported early exit.
+
+**Pydantic AI is used for structured output and nothing else** (`structured.build_agent`). The orchestration
+library stays out of the control-flow path deliberately, so it remains swappable, and **no graph/orchestration
+dependency is taken at all**: the agent loop in `agents/` is this package's own, and escalation routing and
+third-party orchestration frameworks remain out of scope ([`docs/design.md` §14](../../docs/design.md)).
+
+Tracing follows the OTel GenAI semantic conventions: `gen_ai.*` attributes for the operation, model, provider,
+request parameters and usage, with AID-specific values namespaced `aid.*` so the two never collide. A failing
+call records its exception exactly once.
+
+## The agent runtime
+
+`AgentRuntime.from_ir(document, providers=..., ...)` reads the emitted IR and runs an agent to a stop
+condition: model call, tool calls, observations, until a terminal answer, `maxSteps`, or a budget breach.
+Model calls go through `ModelGateway`, so fallback, cost accounting and tracing apply without a second
+implementation.
+
+**Transfer and delegation are different, and the API says which.** `_transfer` (`handoffs`) hands the
+conversation to the target and never resumes the caller, so `RunResult.agent_id` is the target and `path`
+grows. `_delegate` (`delegates`) runs the target in an isolated `[system, user]` context and returns its answer
+as a single tool observation, so `RunResult.agent_id` is the caller and `path` is unchanged. Both refuse to
+re-enter an agent already on the path.
+
+**A budget breach fails hard.** `BudgetExceededError` stops the run; the gateway preflight and the ledger both
+enforce the ceiling. An agent declaring `onBudgetExhausted: 'degrade'` (v0.2) instead steps exactly one rung
+down its declared alias ladder — no retry loop, and the build-time gate rejects the declaration when no
+strictly cheaper alias exists. Each degraded step is recorded in `StepRecord.degraded_from`, and a checkpoint
+carries its current alias so a resumed run re-routes from where it stopped.
+
+**Memory** is in-process plus one store-backed adapter. `thread` scope is the checkpointer unit: trimmed to its
+`tokenBudget`, never written to a store. `user` and `global` scopes read and write the store and render as one
+extra system message, so injection is visible in the request rather than hidden.
+
+**Human-in-the-loop** pauses by returning a checkpoint (completed steps, pending call, current alias), and
+`resume(checkpoint, decision)` continues it. The pause is recorded as an `aid.hitl` span event, not an
+attribute, because a run can pause more than once.
+
+## Development
+
+Four gates, all run by the `python` job in [`.github/workflows/ci.yml`](../../.github/workflows/ci.yml) over
+real content:
+
+```sh
+pytest
+ruff check .
+ruff format --check .
+mypy
+```
+
+`mypy` runs strict over `src` **and** `tests`, so the tests are type-checked too. The `python` job is a real
+gate but is **advisory**: the `main` ruleset requires the `node`, `workflows` and `licenses` contexts only.
+
+`tests/fixtures/capitals-baseline.json` is regenerated from `FakeProvider(accuracy=0.6, seed=0)` over 10 runs
+— the fake is seeded and deterministic per call, so the committed baseline reproduces exactly while a fresh
+sample of it still varies, which is exactly the property the gate has to tolerate.
+
+**Non-responsibility:** no app-specific prompts, tools, or rubrics. Those belong to the generated app's
+`business/` tier ([`docs/design.md` §8.4](../../docs/design.md), the seam).
+
+**Status:** Phase 0 scope implemented, plus the Phase 1 retrieval runtime. One thing deferred and
+undeclared, on purpose: `ModelGateway.stream` raises `FeatureDeferredError`, and no provider advertises
+`Capability.STREAMING` or target declares the capability, because the transport is request/response-only.
+Retrieval likewise fails loudly rather than
+approximating: non-file sources, `semantic` chunking, `incremental` refresh, retriever `filters`, a hosted
+reranker, and the `qdrant` / `pinecone` / `weaviate` / `custom` store kinds all raise `FeatureDeferredError`.
+Also deferred (§14): escalation routing, memory, guardrails, prompt/semantic caching, rate limiting, token
+buckets, and adapters beyond the one HTTP provider and the fake.
+
+Emitting retrieval into a generated app and indexing it from the CLI are later layers, so this package adds no
+entry point for either.
+
+Reference: [`docs/design.md` §9, §12, §14, §17 #2](../../docs/design.md).

aid_runtime_python-0.1.39/README.md

@@ -0,0 +1,234 @@
+# AID runtime — Python
+
+The Python runtime library: the behavior layer imported by apps generated by the
+[`py-fastapi`](../../packages/generators/py-fastapi/) generator. Generated code is thin glue; this is where
+the behavior lives ([`docs/design.md` §4](../../docs/design.md), principle 1).
+
+Distribution name **`aid-runtime-python`**, import package **`aid_runtime`**. The two differ deliberately: a
+distribution name is conventionally hyphenated, and a Python import package cannot be. That asymmetry is
+asserted in `tests/test_package.py` so it cannot drift.
+
+Requires Python 3.11+.
+
+```sh
+pip install -e ".[dev]"        # the runtime plus its test/lint/type tooling
+pytest -q
+pip install -e ".[pgvector]"   # only if you want the pgvector store adapter
+```
+
+## What it provides
+
+| Module | Provides |
+| --- | --- |
+| `gateway.py` | `ModelGateway` — alias resolution, capability negotiation, ordered fallback, cost accounting, GenAI spans |
+| `providers/` | The `Provider` protocol, one HTTP adapter (`OpenAICompatibleProvider`), and one deterministic fake (`FakeProvider`) |
+| `prompts.py` | `PromptTemplate` / `PromptRegistry` — versioned prompts, typed rendering, few-shot assembly |
+| `structured.py` | `build_agent` — structured output via Pydantic AI only |
+| `tools.py` | `Tool` / `ToolExecutor` — declared definitions, argument validation, structured results |
+| `pipeline.py` | `Pipeline` / `PipelineContext` — plain-async named steps over a frozen context |
+| `agents/` | The native agent runtime: `AgentRuntime` — the loop, transfer vs. delegate, step/token/cost budgets with bounded degrade, memory, and a checkpointed human-in-the-loop pause |
+| `retrieval/` | Retrieval: connectors, chunkers, the `Embedder` / `Reranker` / `VectorStore` protocols, hybrid fusion, citations, and retrieval metrics |
+| `evals/` | Datasets, metrics, and the statistical baseline gate |
+| `tracing.py` | OTel GenAI spans: `llm_span`, `agent_span`, `record_usage`, `record_cost`, `record_attributes`, `record_hitl`, `record_exception` |
+| `cost.py` | `Budget`, `CostLedger`, `estimate_cost_usd`, `estimate_tokens` |
+| `types.py` | The request/response/usage/spec models everything else is typed against |
+
+194 names are exported from `aid_runtime`. The layering is acyclic and one-directional: `errors` and `types` import
+nothing else in the package, `gateway` is imported only by the package `__init__` and the eval runner, and no
+core module imports a higher layer back.
+
+## Model pinning
+
+An **alias resolves to an exact provider model id**, including a pinned version. That is not cosmetic: a
+baseline recorded against `gpt-4o` means nothing if the alias floats to `gpt-4o-2026-…` on the next run, so an
+**unknown alias is an error** (`UnknownModelAliasError`) rather than a silent fall-through to a provider
+default.
+
+```python
+from aid_runtime import (
+    Budget,
+    CompletionRequest,
+    CostProfile,
+    ModelGateway,
+    ModelSpec,
+    OpenAICompatibleProvider,
+    PinnedModel,
+)
+
+spec = ModelSpec(
+    name="gpt-4o-2024-08-06",
+    provider="openai-compatible",
+    cost=CostProfile(input_per_1k_usd=0.0025, output_per_1k_usd=0.01),
+    context_window=128_000,
+    max_output_tokens=4096,
+)
+
+gateway = ModelGateway(
+    providers={"openai-compatible": OpenAICompatibleProvider(api_key=...)},
+    aliases={"small": PinnedModel(alias="small", spec=spec)},
+    budget=Budget(max_usd=5.0, scope="nightly"),
+)
+
+result = await gateway.generate("small", CompletionRequest.prompt("hello"))
+result.text, result.usage, result.cost_usd, result.alias, result.attempts, result.fell_back
+```
+
+- `resolve(alias)` returns the `PinnedModel` (alias + `spec`); `provider_for(alias)` its provider. `require(alias,
+  capabilities)` asserts the capabilities *and* returns the pinned model, checking **both** sides — a model that
+  supports tool calling behind an adapter that does not serialise tool definitions cannot tool-call — and raises
+  `CapabilityMismatchError` naming what is missing.
+- `generate(alias, request, *, fallbacks=(), budget=None)` tries the alias then each fallback **in the order
+  given**, and reports the aliases actually attempted on the result. Fallbacks are ordered, not conditional.
+- Every charged call opens a span and updates the ledger. `CostLedger` tracks per-call `LedgerEntry` records
+  and yields a `SpendSummary`; `Budget` (`max_usd`, `max_total_tokens`, `scope`) is enforced before the call,
+  and `estimate_usage` / `estimate_cost_usd` price a request from a model's `CostProfile` when a caller wants
+  to check before spending.
+
+## The eval harness gates on statistics, not equality
+
+Phase 0 ratifies sampling-based gating: a model is **expected** to vary between runs, so a metric that
+compares two runs for equality is either always red or measuring nothing. Non-determinism here is not a bug to
+be fixed; it is the property the gate has to be robust against.
+
+- `Dataset` — versioned cases with inputs, expectations, tags and metadata; `from_records` / `from_json` /
+  `from_path`, `to_json`, and lookups by id (`case`) and by tag (`by_tag`).
+- Metrics — `ExactMatch`, `NormalizedContains`, `JsonSchemaValid`, and `LlmJudge`. `metric_names` and
+  `default_metrics` cover the common set.
+- `run_evaluation(dataset, runner, metrics, runs=5)` samples the runner **N times** and produces an `EvalRun`
+  of per-run metric means, so a single unlucky run does not decide the verdict. `evaluate_once` is the
+  single-pass primitive; a `DatasetRun` gives per-case outcomes and a rendered `summary()`.
+- `EvalBaseline.from_run(run, model=..., note=...)` stores a baseline as JSON: per metric the sample count,
+  mean and spread. `runtimes/python/tests/fixtures/capitals-baseline.json` is a committed example.
+- `BaselineGate(thresholds).evaluate(run, baseline)` compares the current sample against the baseline using a
+  one-sided normal test, with each `Threshold` carrying `metric`, an optional absolute `min_mean`, a
+  `max_regression` allowance, and an `alpha` significance level. A metric passes by clearing `min_mean`, by
+  being within `max_regression` of the baseline, or by regressing only within sampling noise.
+
+Two deliberate limits:
+
+- **`LlmJudge` is implemented and never CI-required.** A judge is itself a model call, and a gate that
+  depends on one non-deterministic call inside the gate you are trying to trust is the problem this design
+  avoids. `gateway_judge(gateway, alias)` builds the judge call when a caller wants it.
+- **`GateConfigurationError` refuses a threshold on a model-derived metric**, because an N-run sample of a
+  probabilistic judge cannot carry a fixed threshold honestly.
+
+`cost` is the enforced budget; a latency p95 budget belongs with Phase 2 dashboards, not here.
+
+## Retrieval
+
+`retrieval/` is an IR-driven layer: `binding_from_spec(retriever, embedding=..., store=...)` folds the IR's
+`retrievers`, `embeddings` and `stores` entries into one `RetrieverBinding`, which a `Retriever` then ingests
+and searches through. The runtime consumes the names the IR emits, field for field.
+
+- Three protocols, in the same style as `providers.Provider`: `Embedder`, `Reranker`, `VectorStore`. Phase 1
+  ships the implementations listed below and no others.
+- `FakeDeterministicEmbedder` maps text to a stable unit vector with a hash — keyless and offline, which is
+  what lets a retrieval gate run in CI. `OpenAICompatibleEmbedder` is the one hosted adapter: a single POST to
+  `/embeddings` over `httpx`, with the retry, timeout and error-chaining behaviour of the HTTP provider.
+- `LexicalReranker` is the only reranker. It is deterministic and lexical; there is no hosted rerank adapter.
+- Chunk ids are **content hashes**, so re-ingesting the same input produces the same ids and a no-op diff.
+  Ingest is therefore held to idempotence rather than to the byte-identical codegen guarantee.
+- **Pinning.** `embedModel` names an IR `embeddings` entry and resolves at codegen time to an exact `modelId`
+  plus its recorded width; the resolved id, width and store `kind` travel into the generated code. An alias is
+  never resolved at runtime, because a baseline recorded against a floating model means nothing.
+- **Cost.** Embedding calls charge the existing `CostLedger` through the existing `Budget`, using the catalog's
+  `CostProfile` for the pinned model. There is no retrieval-specific budgeting machinery.
+
+`RetrievalMetric` (`RecallAtK`, `MeanReciprocalRank`, `CitationGrounding`) is deliberately a **separate
+protocol** from the shipped `Metric`, which scores a single string prediction. Retrieval scores a *retrieved
+set*: recall@k and MRR need the ranked ids, and citation-grounding needs the passages behind the citations.
+Widening `Metric` would have changed an interface the existing gate already threshold-checks, for every
+existing implementation — so retrieval is sampled through `RetrievalGate.sample(...)` instead, producing a
+standard `EvalRun`, and then judged by the **unchanged** `BaselineGate`. Retrieval metrics are deterministic,
+so they pass the gate's own eligibility check.
+
+### pgvector
+
+`PgVectorStore` is a thin adapter over `psycopg` and the `vector` extension. Two consequences worth stating:
+
+- It is **locally provisioned and not covered by any gate.** No CI job starts a database, and no required
+  check touches one; the in-memory adapter carries the store gates, and the two adapters share the same
+  `VectorStore` protocol and the same `similarity` semantics. `compose.pgvector.yml` beside this README brings
+  up a database for local use.
+- The `[pgvector]` extra is **import-safe when absent**: importing `aid_runtime` or `aid_runtime.retrieval`
+  never imports the driver, and the adapter loading it raises a `ConfigurationError` naming the extra.
+
+## Control flow is plain async
+
+`Pipeline` is a list of named async (or plain) steps over a `PipelineContext` that is **frozen**, so a step
+cannot mutate what an earlier step observed — it returns a new context, which keeps a failed run's state
+inspectable. A step may return a context, a mapping, or `None`. Each step runs in its own span, a step raising
+anything aborts the run with the original exception chained (`PipelineError.__cause__`), and `StopPipeline` is
+the supported early exit.
+
+**Pydantic AI is used for structured output and nothing else** (`structured.build_agent`). The orchestration
+library stays out of the control-flow path deliberately, so it remains swappable, and **no graph/orchestration
+dependency is taken at all**: the agent loop in `agents/` is this package's own, and escalation routing and
+third-party orchestration frameworks remain out of scope ([`docs/design.md` §14](../../docs/design.md)).
+
+Tracing follows the OTel GenAI semantic conventions: `gen_ai.*` attributes for the operation, model, provider,
+request parameters and usage, with AID-specific values namespaced `aid.*` so the two never collide. A failing
+call records its exception exactly once.
+
+## The agent runtime
+
+`AgentRuntime.from_ir(document, providers=..., ...)` reads the emitted IR and runs an agent to a stop
+condition: model call, tool calls, observations, until a terminal answer, `maxSteps`, or a budget breach.
+Model calls go through `ModelGateway`, so fallback, cost accounting and tracing apply without a second
+implementation.
+
+**Transfer and delegation are different, and the API says which.** `_transfer` (`handoffs`) hands the
+conversation to the target and never resumes the caller, so `RunResult.agent_id` is the target and `path`
+grows. `_delegate` (`delegates`) runs the target in an isolated `[system, user]` context and returns its answer
+as a single tool observation, so `RunResult.agent_id` is the caller and `path` is unchanged. Both refuse to
+re-enter an agent already on the path.
+
+**A budget breach fails hard.** `BudgetExceededError` stops the run; the gateway preflight and the ledger both
+enforce the ceiling. An agent declaring `onBudgetExhausted: 'degrade'` (v0.2) instead steps exactly one rung
+down its declared alias ladder — no retry loop, and the build-time gate rejects the declaration when no
+strictly cheaper alias exists. Each degraded step is recorded in `StepRecord.degraded_from`, and a checkpoint
+carries its current alias so a resumed run re-routes from where it stopped.
+
+**Memory** is in-process plus one store-backed adapter. `thread` scope is the checkpointer unit: trimmed to its
+`tokenBudget`, never written to a store. `user` and `global` scopes read and write the store and render as one
+extra system message, so injection is visible in the request rather than hidden.
+
+**Human-in-the-loop** pauses by returning a checkpoint (completed steps, pending call, current alias), and
+`resume(checkpoint, decision)` continues it. The pause is recorded as an `aid.hitl` span event, not an
+attribute, because a run can pause more than once.
+
+## Development
+
+Four gates, all run by the `python` job in [`.github/workflows/ci.yml`](../../.github/workflows/ci.yml) over
+real content:
+
+```sh
+pytest
+ruff check .
+ruff format --check .
+mypy
+```
+
+`mypy` runs strict over `src` **and** `tests`, so the tests are type-checked too. The `python` job is a real
+gate but is **advisory**: the `main` ruleset requires the `node`, `workflows` and `licenses` contexts only.
+
+`tests/fixtures/capitals-baseline.json` is regenerated from `FakeProvider(accuracy=0.6, seed=0)` over 10 runs
+— the fake is seeded and deterministic per call, so the committed baseline reproduces exactly while a fresh
+sample of it still varies, which is exactly the property the gate has to tolerate.
+
+**Non-responsibility:** no app-specific prompts, tools, or rubrics. Those belong to the generated app's
+`business/` tier ([`docs/design.md` §8.4](../../docs/design.md), the seam).
+
+**Status:** Phase 0 scope implemented, plus the Phase 1 retrieval runtime. One thing deferred and
+undeclared, on purpose: `ModelGateway.stream` raises `FeatureDeferredError`, and no provider advertises
+`Capability.STREAMING` or target declares the capability, because the transport is request/response-only.
+Retrieval likewise fails loudly rather than
+approximating: non-file sources, `semantic` chunking, `incremental` refresh, retriever `filters`, a hosted
+reranker, and the `qdrant` / `pinecone` / `weaviate` / `custom` store kinds all raise `FeatureDeferredError`.
+Also deferred (§14): escalation routing, memory, guardrails, prompt/semantic caching, rate limiting, token
+buckets, and adapters beyond the one HTTP provider and the fake.
+
+Emitting retrieval into a generated app and indexing it from the CLI are later layers, so this package adds no
+entry point for either.
+
+Reference: [`docs/design.md` §9, §12, §14, §17 #2](../../docs/design.md).

aid_runtime_python-0.1.39/pyproject.toml

@@ -0,0 +1,147 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "aid-runtime-python"
+version = "0.1.39"
+description = "The AID Framework Python runtime: model gateway with pinning and cost budgets, prompt registry, tool executor, OTel GenAI tracing, plain-async pipeline, and an eval harness that gates on statistical regression against a stored baseline."
+readme = "README.md"
+requires-python = ">=3.11"
+license = "Apache-2.0"
+authors = [{ name = "The AID Framework authors" }]
+keywords = ["ai", "codegen", "llm", "evals", "opentelemetry", "pydantic"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Typing :: Typed",
+]
+# Deliberately narrow. One HTTP provider adapter ships here; provider breadth is
+# out of scope. `pydantic-ai-slim` is used only for structured output, not as an
+# orchestration dependency -- pipeline control flow is plain async.
+dependencies = [
+  "httpx>=0.27,<1",
+  "opentelemetry-api>=1.24,<2",
+  "pydantic>=2.7,<3",
+  "pydantic-ai-slim>=2,<3",
+]
+
+[project.optional-dependencies]
+# pgvector is optional and locally provisioned. The driver is imported lazily inside
+# the adapter, so the default install and the `dev` extra both work with this extra
+# absent -- which is the only state CI is ever in. There is deliberately no CI job
+# for it; the adapter is not gate-covered, and the in-memory store carries the gates.
+pgvector = ["psycopg[binary]>=3.1,<4"]
+# The Deep Agents orchestration backend. Exactly pinned, never a range: the IR gate
+# demands a pinned `engineVersion`, and `aid_runtime.agents.engine.DEEPAGENTS_PIN`
+# is the one authoritative copy of this number that a run is compared against. Both
+# copies must move together, which is why the version is a single literal here and a
+# single literal there rather than a constraint that could silently widen.
+deepagents = ["deepagents==0.7.32"]
+dev = [
+  "mypy>=1.11,<3",
+  "opentelemetry-sdk>=1.24,<2",
+  "pytest>=8,<10",
+  "pytest-asyncio>=0.24,<2",
+  "ruff>=0.6,<1",
+]
+
+[project.urls]
+Homepage = "https://github.com/aid-framework/aid-framework"
+Documentation = "https://github.com/aid-framework/aid-framework/blob/main/docs/design.md"
+Issues = "https://github.com/aid-framework/aid-framework/issues"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+aid_runtime = ["py.typed"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+asyncio_mode = "auto"
+asyncio_default_fixture_loop_scope = "function"
+addopts = "-ra --strict-markers --strict-config"
+filterwarnings = ["error"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = [
+  "A",     # builtins shadowing
+  "ANN",   # annotations
+  "ASYNC", # async correctness
+  "B",     # bugbear
+  "C4",    # comprehensions
+  "DTZ",   # naive datetimes
+  "E",     # pycodestyle errors
+  "ERA",   # commented-out code
+  "F",     # pyflakes
+  "I",     # import sorting
+  "LOG",   # logging
+  "N",     # pep8-naming
+  "PT",    # pytest style
+  "PTH",   # pathlib over os.path
+  "RET",   # return simplification
+  "RUF",   # ruff-specific
+  "S",     # bandit
+  "SIM",   # simplify
+  "T20",   # no print()
+  "TID",   # tidy imports
+  "UP",    # pyupgrade
+  "W",     # pycodestyle warnings
+]
+ignore = [
+  # `Any` is unavoidable at the provider/tool boundary, where the payload is
+  # shaped by the remote model rather than by us.
+  "ANN401",
+]
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**" = [
+  "ANN001", # fixtures and test callables take untyped parameters
+  "ANN201",
+  "ANN202",
+  "S101",   # assert is the point of a test
+]
+# The fake provider is a deterministic simulation, not a source of randomness
+# with security implications; bandit cannot tell the difference.
+"src/aid_runtime/providers/fake.py" = ["S311"]
+
+[tool.ruff.lint.flake8-tidy-imports]
+ban-relative-imports = "all"
+
+[tool.mypy]
+python_version = "3.11"
+mypy_path = "src"
+files = ["src", "tests"]
+strict = true
+warn_unreachable = true
+
+[[tool.mypy.overrides]]
+# pydantic-ai ships type hints but no `py.typed` marker on every release line.
+module = ["pydantic_ai.*"]
+follow_untyped_imports = true
+
+[[tool.mypy.overrides]]
+# The pgvector driver is an optional extra and is absent wherever the gates run, so
+# there is nothing to resolve. Everything read off it is confined to `Any` inside the
+# one adapter that is allowed to touch it.
+module = ["psycopg.*"]
+ignore_missing_imports = true
+
+[[tool.mypy.overrides]]
+# The Deep Agents harness is an optional extra. `deepagents` and `langgraph` are absent
+# from the default install, and `langchain`'s middleware surface is not exported with
+# types we can rely on across minor releases. Everything crossing this boundary is
+# erased at the one adapter in `agents/chat_model.py` and the one engine in
+# `agents/deep_agents.py`; the rest of the runtime never sees these names.
+module = ["deepagents.*", "langgraph.*", "langchain.*", "langchain_core.*"]
+ignore_missing_imports = true

aid_runtime_python-0.1.39/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+