feat(eval): add lifecycle extensions and agent rules

[christso]

Recovery

Recovers closed PR #1605 after its stacked base branch feat/av-kfik-4-templating was deleted following #1597 squash-merge.

• Original preserved head: b7af94a60ca4a153aec6baf57baf6705d6f05600
• Recovered head on main: ca0019330e76101e94ea422d4a5fcca2a32f64e8
• git range-diff 61bcec47..recover/pr1605-pre-rebase origin/main..HEAD reports both lifecycle commits as patch-equivalent.
• Attempted to reopen feat(eval): add lifecycle extensions and agent rules #1605, but GitHub rejected it because the deleted base branch prevents changing PR state.

Summary

• Adds promptfoo-compatible AgentV lifecycle extensions: beforeAll, beforeEach, afterEach, and afterAll.
• Adds file://...:<hook> extension execution and the built-in agentv:agent-rules staging extension.
• Keeps workspace.repos first-class: repos are materialized before extension hooks, and repo acquisition is not moved into extension semantics.
• Exposes staged agent_rules_paths through provider context, result metadata, prepare manifests, generated schema, docs, and examples.
• Preserves the feat(eval): add lifecycle extensions and agent rules #1605 review fixes from b7af94a6: conversation-mode teardown/result metadata, slot-scoped pooled beforeAll extension state, and beforeEach baseline refresh when hooks mutate files without returning state.

Validation

• bun test packages/core/test/evaluation/extensions.test.ts packages/core/test/evaluation/orchestrator.test.ts packages/core/test/evaluation/workspace/setup.test.ts packages/core/test/evaluation/workspace/file-changes.test.ts packages/core/test/evaluation/suite-level-input.test.ts packages/core/test/evaluation/validation/eval-file-schema.test.ts packages/core/test/evaluation/validation/eval-validator.test.ts apps/cli/test/commands/prepare/prepare.test.ts (262 passing)
• bun run --cwd packages/core typecheck
• bun run --cwd packages/core lint
• bun run --cwd packages/core build
• bun run --cwd apps/cli build

Prior #1605 validation preserved for review context:

• bun run lint
• bun run typecheck
• Manual CI for original stacked PR: https://github.com/EntityProcess/agentv/actions/runs/28590245378
• Manual CI for original review-fix commit b7af94a6: https://github.com/EntityProcess/agentv/actions/runs/28592955569
• Live dogfood with local OpenAI-compatible target and live LLM grader via http://127.0.0.1:10531/v1: PASS, 1/1, mean score 100%.
• Review-fix dogfood with model gpt-5.3-codex-spark: PASS, 1/1, mean 100%.

Private evidence:

• agentv-private branch: evidence/av-kfik-14-extensions
• Original evidence commit: 36424ef
• Review-fix evidence commit: 1c16dc4, folder review-fix-dogfood/

Scope Notes

• Legacy workspace.hooks command execution remains available for existing suites and reset policy; new docs and migrated examples route executable setup through top-level extensions.
• Hard removal of remaining legacy command hooks is left out of this slice because examples and tests still exercise existing behavior.

Post-Deploy Monitoring & Validation

• Watch CI for eval schema generation, core/CLI typecheck, and CLI prepare tests.
• For early adopters, inspect run index.jsonl metadata for agent_rules_paths and provider request metadata in failed evals involving extensions.
• Healthy signal: evals using workspace.repos plus agentv:agent-rules show staged paths under .agentv/agent-rules/** after workspace materialization.
• Failure signal: setup failures mentioning agentv:agent-rules requires a materialized workspace, stale prepared agent_rules_paths, or missing file:// export functions.
• Rollback trigger: extension-enabled evals fail before provider invocation despite valid workspace materialization.
• Validation window: first CI run and first manual extension-enabled eval after merge; owner: AgentV maintainers.