model-task-executionlisted

# Model Task Execution Execute exactly what the user approved. A valid plan is necessary but not sufficient: explicit user consent must appear in the current conversation. ## Preflight 1. Validate the plan against the model-task plan schema. 2. Compute a SHA-256 plan hash over canonical JSON and show it with the consent summary. 3. Confirm `consent.required` and `consent.status` match the operation. 4. Show provider, model, operation, transmitted inputs, retention evidence, cost estimate status, maximum approved cost, and fallbacks. 5. Check whether the selected provider/model requires a credential. If it does, verify only that provider-native login or the named host environment variable is available; never print or persist its value. If missing, stop and route to `setup-ai-operations`. 6. Ask for explicit user consent. Do not invoke a paid, externally visible, state-changing, or data-transmitting provider tool before approval. 7. Store the approved plan hash in memory for this execution only. Do not write credentials, raw secrets, or private inputs to an execution manifest. ## Material-Change Gate Any change to the **provider, model, data boundary, or cost ceiling** invalidates the plan hash and requires **renewed consent**. The same applies when a fallback adds a new provider, transmits additional data, or changes output visibility. ## Dispatch 1. Mark the next step `approved`. 2. Invoke only the provider tool named in the step. 3. Capture the pr