[Phase 10] Paper Plan → Tasks

[jeremymanning]

Summary

Produce paper plan + tasks.md where every task carries a [kind:...] token for sub-agent dispatch.

What this phase does

paper_planner produces plan.md/research.md/data-model.md/quickstart.md/contracts/. paper_tasker emits a tasks.md where every line has a [kind:prose|figure|statistics|lit-search|reference-verification|proofread|latex-build|latex-fix] token. The Mode-A → Mode-B analyze loop runs as in Phase 4.

Project lifecycle stages handled

• paper_planned
• paper_tasked
• paper_analyzed

Dependencies

• Depends on: [Phase 9] Paper Spec → Clarify #53
• Blocks: [Phase 11] Paper Implement (dispatcher + sub-agents) #55

Agents in this phase

• sub-issue: paper_planner ([Agent · Phase 10] paper_planner #80)
• sub-issue: paper_tasker ([Agent · Phase 10] paper_tasker #81)

Manual test plan (phase-level smoke test)

1. Stage a project at the entry stage of this phase (see "stages handled" above)
2. python -m llmxive run --project <PROJ-ID> --max-tasks N (N = number of agents in this phase)
3. Verify the project transitions through every stage listed above
4. Run each agent's manual test plan (linked via the sub-issue checklist)
5. Verify state ends at the entry stage of the next phase, or human_input_needed/blocked on legitimate failure (never silently stuck)

Acceptance criteria (phase-level)

• Every agent sub-issue passes its acceptance criteria
• Phase-level smoke test passes end-to-end on a fresh project
• No silent shortcuts — agents that can't do their work MUST fail loudly (write human_input_needed.yaml or emit verdict: failed), not mark tasks [X] with placeholder content
• All artifacts written by this phase pass schema validation (where applicable)
• Run-log entries record outcome, started_at, ended_at for every agent invocation