feat!: Add ManagedResult, RunnerResult, and Runner protocol; rename invoke() to run()

[jsonbailey]

Summary

Introduces the new managed-layer return type `ManagedResult`, the unified `Runner` protocol, and extends `LDAIMetricSummary` with `tool_calls`, `duration_ms` (renamed from `duration`), and `resumption_token`.

• `ManagedModel.run()` is the new primary API; returns `ManagedResult`. `ManagedModel.invoke()` is removed — use `run()` instead.
• `ManagedAgent.run()` now returns `ManagedResult`.
• `RunnerResult` added (no `evaluations` field — judge dispatch lives on the managed layer).
• `ManagedModel` and `ManagedAgent` now accept only `Runner`; the `ModelRunner`/`AgentRunner` compat branches are removed from the managed layer.
• `RunnerFactory.create_model()` and `create_agent()` return `Optional[Runner]`.
• `LDAIConfigTracker.init` seeds `LDAIMetricSummary._resumption_token` at instantiation so it's available on `get_summary()`.
• `ModelResponse`, `StructuredResponse`, `AgentResult`, `ModelRunner`, `AgentRunner` type definitions are kept in place so OpenAI and LangChain provider packages continue to pass CI until the follow-up PRs migrate them to the unified `Runner` protocol.

Stack

This is part of the AIC-2388 stacked PR series. Targets `main` (PR #147 merged).

Order: PR 7 ✅ → PR 8 (this) → PR 8-openai → PR 8-langchain → Cleanup → PR 9 → PR 10 → PR 11 → PR 11-openai → PR 11-langchain → PR 12

Test plan

• `make test` — all tests pass
• `make lint` — mypy clean across all 3 packages

🤖 Generated with Claude Code

---

Note

Medium Risk
Medium risk due to a breaking API surface change (invoke() removed/renamed to run()) and refactors across managed model/agent and judge evaluation paths that could impact integrations and metrics tracking.

Overview
Introduces a unified runner interface and new result types. Adds a Runner protocol with a single run() method returning RunnerResult, plus a managed-layer ManagedResult that bundles content, aggregated LDAIMetricSummary, optional parsed structured output, and optional async judge evaluations.

Updates managed and judge APIs to the new runner/result model. ManagedModel.invoke() is replaced by ManagedModel.run() (and the client examples updated), ManagedAgent.run() now returns ManagedResult, and Judge switches from invoke_structured_model/StructuredResponse to Runner.run(..., output_type=...) and reads structured output from RunnerResult.parsed.

Expands tracking/metrics payloads. LDAIMetrics gains tool_calls and duration_ms (included in to_dict()), LDAIMetricSummary adds tool_calls, duration_ms (with deprecated duration alias), and eagerly captures resumption_token; LDAIConfigTracker.track_metrics_of(_async) now supports optional metrics extraction, prefers metrics.duration_ms over wall-clock time, and tracks tool-call events once per execution.

^{Reviewed by Cursor Bugbot for commit 5925da6. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, have a team admin enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit e2e2b6e. Configure here.}