-- Goal conditions for mission phases.
--
-- Until now a phase completed when its topology_runs reached a terminal
-- state -- purely structural, with no notion of whether the work was any
-- good. `close_finished_phases` marked a phase `completed` whether the
-- agents produced the artifact or wrote nothing at all.
--
-- `done_when` is a natural-language completion condition, judged after each
-- pass by a model (see crates/cm-api/src/evaluator.rs). It follows the
-- constraint the evaluator operates under: the judge cannot run commands, so
-- the condition must be demonstrable from what the agents surfaced in their
-- turn output.
--
-- NULL `done_when` preserves today's behaviour exactly: terminal runs ->
-- completed, no evaluation, no extra model spend. Existing missions are
-- unaffected.

ALTER TABLE mission_phases
    -- The completion condition. NULL = no evaluation (legacy behaviour).
    ADD COLUMN done_when      TEXT,
    -- Upper bound on passes. 1 = run once, matching current behaviour.
    -- Capped server-side as well; this is a backstop against a runaway loop.
    ADD COLUMN max_iterations INT NOT NULL DEFAULT 1,
    -- Which pass the phase is on, 0-based.
    ADD COLUMN iteration      INT NOT NULL DEFAULT 0;

-- One verdict per (phase, iteration). Modelled on mission_phase_summaries
-- (0060): the model emits structured JSON, we persist it with the model name
-- so a verdict can be attributed, and keep the reason because it is both the
-- explanation shown to the operator AND the guidance fed into the next pass.
CREATE TABLE mission_phase_evaluations (
    id         UUID PRIMARY KEY,
    mission_id UUID NOT NULL REFERENCES missions(id) ON DELETE CASCADE,
    phase_id   UUID NOT NULL REFERENCES mission_phases(id) ON DELETE CASCADE,
    iteration  INT  NOT NULL,
    -- Whether the condition held. Fail-closed: an unparseable or missing
    -- verdict is recorded as false, never as "done".
    met        BOOLEAN NOT NULL,
    reason     TEXT NOT NULL,
    -- The model that judged, e.g. "runtime:coordinator" or "claude-opus-4-8".
    model      TEXT NOT NULL,
    -- Set when the evaluator itself failed (transport, parse). `met` is false
    -- in that case; this distinguishes "judged not done" from "could not judge".
    error      TEXT,
    created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
    UNIQUE (phase_id, iteration)
);

CREATE INDEX mission_phase_evaluations_phase_idx
    ON mission_phase_evaluations (phase_id, iteration DESC);
CREATE INDEX mission_phase_evaluations_mission_idx
    ON mission_phase_evaluations (mission_id, created_at DESC);

-- Which pass produced a run. Without this, "are this phase's runs all
-- finished?" matches pass 1's completed rows forever and a second pass would
-- be declared done the instant it was enqueued.
--
-- (An `iteration` column existed on this table once and was dropped in 0053
-- along with the legacy loops backend. This one is for mission phases.)
ALTER TABLE topology_runs
    ADD COLUMN iteration INT NOT NULL DEFAULT 0;

CREATE INDEX topology_runs_phase_iteration_idx
    ON topology_runs (mission_phase_id, iteration)
    WHERE mission_phase_id IS NOT NULL;