feat(missions): add a "Compare two models" Mission template (#1026)

## Summary

Adds a fifth Mission template, **Compare two models** (`compare`). It
runs the same bounded task on two different models and ends with a blind
verdict.

- **Creation:** the user picks **model A** and **model B** in the main
creation form. Both are required and must name different models
(provider + model id; a reasoning variant alone is not a different
model). This is enforced on every creation path: HTTP, prepare,
recurrence create and agent-started missions.
- **Roles:** `model-a`, `model-b` and `comparator`.
  - A and B share one instruction text and report contract.
- The coordinator writes the task, inputs and criteria once, and gives
both byte-identical briefs.
- The server refuses a run task whose brief differs from its sibling's,
or whose per-task execution would change its role's model.
- **Blind judge, always on:** the comparator works on neutral X/Y
labels.
- It reports one versioned `comparison` artifact: the A/B task
references, per-criterion scores for both runs, sourced observations,
and a verdict `a | b | equivalent | inconclusive`.
  - Completion requires both runs and that comparison.
- **Judge model:** frozen once at creation, like every other role.
- An explicit judge is kept; otherwise the judge copies the
coordinator's effective model. When that model is unknown, both stay on
the native default.
  - Replays and retries therefore reuse the stored profile.
  - The editor warns when the judge's model equals A or B.
- **Readers:** the verdict, both model names, a score table and evidence
by path. Hashes stay under Technical details, for current and archived
recurring passages.

The template came out of evaluating Harness2's comparison loop. It
deliberately has **no** lesson, human approval, budget or duration
handling, and leaves the Wayfinder human gate unchanged. Up to five
models, per-run worktrees and launching from the composer's model picker
(OpenChamber-style multi-run) are left for later.

`AGENTS.md` records the single editor exception: the A/B selectors sit
outside the collapsed Options disclosure. All ten locales are updated.

## Size and upkeep

62 files, +837/-96:

| Part | Lines |
|---|---|
| Product code (about 16 files are one-line template-list hooks) |
+280/-57 |
| Locales (13 keys × 10) | +131 |
| Tests | +409 |
| Docs | +17 |

`missions/control.ts` stays oversized (~1,500 lines).

## Validation

- Full server suite: 2,426 tests pass, 7 existing skips. Root and server
typechecks, the server build and the plugin build pass.
- UI: 45 unit tests and 36 browser tests pass.
- The native trajectory fixture, extended with a compare case, passes on
OpenCode 2.0.31. It checks two distinct models, a one-newline brief
difference refused with the journal unchanged, a real blind judgment and
a completed mission. The native contract and recurring Q fixtures also
pass.
- Regressions cover:
  - distinct-model refusals on every creation path;
  - brief and override refusals;
  - artifact validation and the completion policy;
- judge freezing at creation, revision replay, and retry after a
coordinator model change;
  - editor inheritance and readable evidence.
- Independent review rounds ended with no P0-P3 findings.
- The editor and reader were checked from screenshots of the real Solid
components in the browser harness, not in a packaged app.

.opencode/skills/codenomad-missions/SKILL.md

@@ -7,7 +7,7 @@ description: Coordinate bounded native tasks through the CodeNomad mission map,
 
 Prefer ordinary native delegation for bounded work. Use a mission only when the user needs a durable shared task map, evidence gates, and explicit coordinator decisions; a mission is not required for an ordinary helper.
 
-1. Call `mission.inspect` with `start.objective` and one template: `custom`, `debug`, `wayfinder`, or `delivery`.
+1. Call `mission.inspect` with `start.objective` and one template: `custom`, `debug`, `wayfinder`, `delivery`, or `compare` (two required different model profiles: `model-a` and `model-b`; coordinator-written protocol, identical briefs, always a blind `comparator`, verdict only).
 2. Read the returned playbook. The starting session is the coordinator and is the only session allowed to call `mission.delegate`.
 3. Give every task a stable lowercase `taskKey`. Declare its role, real `blockedBy` dependencies, and execution mode separately from execution. Native is the default for new declarations; blocked declarations do not dispatch or require completed prerequisite reports yet.
 4. Prefer a fresh native child for independent work; reuse an exact specialist only when its context helps and continuation is eligible. Use an independent root only for a concrete `location`, `lifetime`, `existing-root`, or `playbook` reason and explanation. Native continuation names the exact live native `reuseFromTaskKey` with the same parent, never an arbitrary root or a guessed session. This selects context, not a `blockedBy` dependency; do not add a dependency just to reuse a session. Debugging resolvers still require dependency-connected implementer and review evidence. Admission must prove the exact current native execution ended/returned and the actual bound session is idle; a report alone proves neither. Historical tasks without an execution mode retain their root-only behavior: omit `targetSessionID` to create a root, or supply a same-project root to reuse it. Do not automatically convert them.