Parent: #64227
Refs #62854
Refs #47213

Summary

Add an opt-in embedded Pi execution contract that keeps GPT-5-style runs acting through plan-only turns, and revise update_plan so it behaves like a structured progress tool instead of a chatty completion surface.

PR 1 is intentionally GPT-5-first: it only activates the strict-agentic contract for embedded Pi openai and openai-codex GPT-5-family runs.

Scope

• add agents.defaults.embeddedPi.executionContract: default | strict-agentic
• add matching per-agent override
• stop default OpenAI/Codex auto-enable of update_plan
• auto-enable update_plan only for explicit tools.experimental.planTool or supported strict-agentic GPT-5 runs
• make update_plan non-chatty and tolerant of extra step fields
• treat update_plan as non-progress in strict-agentic retry logic
• resolve strict-agentic behavior through explicit-agent-aware lookup so no-session-key contexts use the right agent config
• retry plan-only / filler-only GPT-5 turns under strict-agentic
• surface an explicit blocked state after retry cap

Non-goals

• does not supersede runtime: fail closed on plan stalls and retry session-delta sync #62989
• does not implement feat: context-pressure-aware continuation (CONTINUE_WORK / CONTINUE_DELEGATE) #38780
• does not address harness/plugin scope from Refactor agent harness into plugin extension #63452
• embedded-Pi-only slice

Acceptance

• config schema accepts executionContract
• update_plan gating semantics match the contract and precedence rules
• update_plan emits no filler text and tolerates extra step fields
• strict-agentic only auto-enables on supported OpenAI/OpenAI Codex GPT-5-family runs unless planTool is explicitly set
• explicit agentId / no-session-key flows resolve the correct contract
• strict-agentic retries plan-only turns and fail-closes after the retry cap