cleveragents-core/tools/controller/state_machine.py

"""Controller state machine — TRANSITIONS table + invariants.

Plan v9 simplified scope: ship the 6 LOAD-BEARING property invariants
for v1; add the other 15 as bugs surface.

States (per plan v6+v9, with v8 metadata-only-no-bypass + v6
CONFLICT_RESOLVING + v6 MERGING + v6 CREATED_PR):

    DISCOVERED
        → ANALYZING (estimator picks tier OR routes to metadata_only)
        → STUCK (estimator failed twice)

    ANALYZING
        → IMPLEMENTING(tier) (normal path)
        → REVIEWING (metadata-only path; per v8 Hard Rule #1 still
                     goes through reviewer with lightweight profile)
        → STUCK (estimator output schema violation)

    IMPLEMENTING
        → AWAITING_CI (worker pushed; head_sha advanced)
        → ESCALATING (worker emitted competence-failure; no push)
        → CONFLICT_RESOLVING (worker emitted rebase-failed)
        → STUCK (worker emitted blocked)

    AWAITING_CI
        → REVIEWING (CI green)
        → IMPLEMENTING(tier) (CI red, attempts-per-tier remaining)
        → ESCALATING (CI red, attempts-per-tier exhausted)
        → AWAITING_CI (flake retry; one retry per flake-classifier
                       per gate; same state)

    CONFLICT_RESOLVING
        → IMPLEMENTING(same tier) (1st conflict resolved)
        → ESCALATING (2nd conflict at same tier)
        → STUCK (3rd conflict; or resolver outcome=irreconcilable)

    ESCALATING
        → IMPLEMENTING(tier+1) (next tier available)
        → ABANDONED (max tier exhausted)

    REVIEWING
        → MERGING (verdict=approve)
        → IMPLEMENTING(tier) (verdict=request-changes,
                              attempts-per-tier remaining)
        → ESCALATING (verdict=request-changes, attempts-per-tier
                      exhausted)
        → STUCK (verdict=abstain; retry-once-then-stuck handled
                 in v9 retry policy)

    MERGING
        → MERGED (Forgejo 200)
        → IMPLEMENTING(tier_last_succeeded) (Forgejo 409; post-
                                              approval base conflict)
        → AWAITING_CI (Forgejo 422; CI status expired race)
        → STUCK (Forgejo 403 branch protection; or retry_count>=5)
        → MERGED OR ABANDONED (Forgejo 404; check external state)

Terminal states:
    MERGED, ABANDONED, STUCK, CREATED_PR

CREATED_PR is reachable only from issue-kind workflows (IMPLEMENTING
on an issue successfully creates a PR + spawns a new pr-kind workflow
with parent_workflow_id; the issue workflow terminates at CREATED_PR).
For v1 simplicity, this module models only the PR-kind state machine;
issue-kind handling lands in Phase 4.
"""
from __future__ import annotations

from dataclasses import dataclass, field
from typing import Iterable


# ─── states ──────────────────────────────────────────────────────────


KNOWN_STATES: frozenset[str] = frozenset({
    "DISCOVERED",
    "ANALYZING",
    "IMPLEMENTING",
    "AWAITING_CI",
    "CONFLICT_RESOLVING",
    "ESCALATING",
    "REVIEWING",
    "MERGING",
    "MERGED",
    "ABANDONED",
    "STUCK",
    "CREATED_PR",
})

TERMINAL_STATES: frozenset[str] = frozenset({
    "MERGED", "ABANDONED", "STUCK", "CREATED_PR",
})

NON_TERMINAL_STATES: frozenset[str] = KNOWN_STATES - TERMINAL_STATES


# Events that drive transitions. The event name captures "what the
# controller observed" so the transition table reads as data, not
# code.
@dataclass(frozen=True)
class Event:
    name: str
    description: str = ""

    def __repr__(self) -> str:
        return f"Event({self.name!r})"


# ─── canonical events ────────────────────────────────────────────────


EVENTS = {
    # ANALYZING
    "estimator_done": Event("estimator_done", "Estimator returned tier"),
    "estimator_metadata_only": Event(
        "estimator_metadata_only",
        "Estimator flagged is_metadata_only=true",
    ),
    "estimator_failed_twice": Event(
        "estimator_failed_twice",
        "Estimator strict-parse failed twice (v6 retry policy)",
    ),
    # IMPLEMENTING
    "implementer_pushed": Event(
        "implementer_pushed",
        "Worker emitted outcome=resolved; head_sha advanced",
    ),
    "implementer_competence_failure": Event(
        "implementer_competence_failure",
        "Worker emitted outcome=competence-failure",
    ),
    "implementer_rebase_failed": Event(
        "implementer_rebase_failed",
        "Worker emitted outcome=rebase-failed",
    ),
    "implementer_blocked": Event(
        "implementer_blocked",
        "Worker emitted outcome=blocked",
    ),
    # AWAITING_CI
    "ci_green": Event("ci_green", "CI overall_state=success"),
    "ci_red_retry_same_tier": Event(
        "ci_red_retry_same_tier",
        "CI failed; attempts-per-tier remaining",
    ),
    "ci_red_escalate": Event(
        "ci_red_escalate",
        "CI failed; attempts-per-tier exhausted",
    ),
    "ci_flake_retry": Event(
        "ci_flake_retry",
        "CI failed but classified as flake; retry once",
    ),
    # CONFLICT_RESOLVING
    "conflict_resolved_first": Event(
        "conflict_resolved_first",
        "Resolver returned outcome=resolved (1st conflict at tier)",
    ),
    "conflict_resolved_second_same_tier": Event(
        "conflict_resolved_second_same_tier",
        "Resolver returned outcome=resolved (2nd conflict at tier)",
    ),
    "conflict_repeated_three_plus": Event(
        "conflict_repeated_three_plus",
        "3rd or later conflict — likely structural; STUCK",
    ),
    "conflict_irreconcilable": Event(
        "conflict_irreconcilable",
        "Resolver returned outcome=irreconcilable",
    ),
    # ESCALATING
    "escalate_next_tier_available": Event(
        "escalate_next_tier_available",
        "Tier+1 ≤ MAX_TIER; transition to IMPLEMENTING(tier+1)",
    ),
    "escalate_max_tier_exhausted": Event(
        "escalate_max_tier_exhausted",
        "Tier was MAX_TIER; ABANDONED",
    ),
    # REVIEWING
    "reviewer_approve": Event(
        "reviewer_approve",
        "Reviewer verdict=approve",
    ),
    "reviewer_request_changes_retry": Event(
        "reviewer_request_changes_retry",
        "Reviewer verdict=request-changes; attempts-per-tier remaining",
    ),
    "reviewer_request_changes_escalate": Event(
        "reviewer_request_changes_escalate",
        "Reviewer verdict=request-changes; attempts-per-tier exhausted",
    ),
    "reviewer_abstain": Event(
        "reviewer_abstain",
        "Reviewer verdict=abstain (rare); per v6 retry-once-then-STUCK",
    ),
    # MERGING
    "merge_ok": Event("merge_ok", "Forgejo merge returned 200"),
    "merge_base_conflict": Event(
        "merge_base_conflict",
        "Forgejo merge returned 409; base advanced post-approval",
    ),
    "merge_ci_required_missing": Event(
        "merge_ci_required_missing",
        "Forgejo merge returned 422; race with CI status",
    ),
    "merge_branch_protection_blocked": Event(
        "merge_branch_protection_blocked",
        "Forgejo merge returned 403; operator must intervene",
    ),
    "merge_retry_exhausted": Event(
        "merge_retry_exhausted",
        "merging_retry_count >= 5; STUCK",
    ),
    "merge_external_action": Event(
        "merge_external_action",
        "Forgejo merge returned 404; reconcile via PR state",
    ),
    # DISCOVERED → ANALYZING
    "discovery_picked_up": Event(
        "discovery_picked_up",
        "Master saw DISCOVERED workflow; queue estimator attempt",
    ),
    # Operator escape hatch (reachable from every non-terminal state)
    "operator_unstick": Event(
        "operator_unstick",
        "Operator manually unstucking; back to DISCOVERED",
    ),
    "pickup_exhausted": Event(
        "pickup_exhausted",
        "Attempt picked up MAX_PICKUPS times w/o success; STUCK",
    ),
}


# ─── transitions ─────────────────────────────────────────────────────


# Map of (from_state, event_name) → to_state. Pure data; tests
# enumerate every key to verify invariants.
TRANSITIONS: dict[tuple[str, str], str] = {
    ("DISCOVERED", "discovery_picked_up"): "ANALYZING",

    ("ANALYZING", "estimator_done"): "IMPLEMENTING",
    ("ANALYZING", "estimator_metadata_only"): "REVIEWING",
    ("ANALYZING", "estimator_failed_twice"): "STUCK",

    ("IMPLEMENTING", "implementer_pushed"): "AWAITING_CI",
    ("IMPLEMENTING", "implementer_competence_failure"): "ESCALATING",
    ("IMPLEMENTING", "implementer_rebase_failed"): "CONFLICT_RESOLVING",
    ("IMPLEMENTING", "implementer_blocked"): "STUCK",
    ("IMPLEMENTING", "pickup_exhausted"): "STUCK",

    ("AWAITING_CI", "ci_green"): "REVIEWING",
    ("AWAITING_CI", "ci_red_retry_same_tier"): "IMPLEMENTING",
    ("AWAITING_CI", "ci_red_escalate"): "ESCALATING",
    ("AWAITING_CI", "ci_flake_retry"): "AWAITING_CI",

    ("CONFLICT_RESOLVING", "conflict_resolved_first"): "IMPLEMENTING",
    ("CONFLICT_RESOLVING", "conflict_resolved_second_same_tier"): "ESCALATING",
    ("CONFLICT_RESOLVING", "conflict_repeated_three_plus"): "STUCK",
    ("CONFLICT_RESOLVING", "conflict_irreconcilable"): "STUCK",
    ("CONFLICT_RESOLVING", "pickup_exhausted"): "STUCK",

    ("ESCALATING", "escalate_next_tier_available"): "IMPLEMENTING",
    ("ESCALATING", "escalate_max_tier_exhausted"): "ABANDONED",

    ("REVIEWING", "reviewer_approve"): "MERGING",
    ("REVIEWING", "reviewer_request_changes_retry"): "IMPLEMENTING",
    ("REVIEWING", "reviewer_request_changes_escalate"): "ESCALATING",
    ("REVIEWING", "reviewer_abstain"): "STUCK",
    ("REVIEWING", "pickup_exhausted"): "STUCK",

    ("MERGING", "merge_ok"): "MERGED",
    ("MERGING", "merge_base_conflict"): "IMPLEMENTING",
    ("MERGING", "merge_ci_required_missing"): "AWAITING_CI",
    ("MERGING", "merge_branch_protection_blocked"): "STUCK",
    ("MERGING", "merge_retry_exhausted"): "STUCK",
    ("MERGING", "merge_external_action"): "MERGED",  # reconciliation refines

    # Operator escape hatch from STUCK.
    ("STUCK", "operator_unstick"): "DISCOVERED",
}


# ─── transition lookup ────────────────────────────────────────────────


class IllegalTransitionError(Exception):
    """Raised when ``apply_event`` is called with an event that has no
    mapped transition from the current state. The master catches this
    and transitions the workflow to STUCK with reason='illegal-event'."""


def apply_event(current_state: str, event_name: str) -> str:
    """Return the next state for ``event_name`` from ``current_state``.

    Raises ``ValueError`` if ``current_state`` isn't in ``KNOWN_STATES``
    (callers should validate state at load time per v6 unknown-state
    guard). Raises ``IllegalTransitionError`` if no transition is
    mapped.
    """
    if current_state not in KNOWN_STATES:
        raise ValueError(
            f"unknown state {current_state!r}; not in KNOWN_STATES"
        )
    try:
        return TRANSITIONS[(current_state, event_name)]
    except KeyError:
        raise IllegalTransitionError(
            f"no transition from {current_state!r} on event "
            f"{event_name!r}; known events from this state: "
            f"{sorted(e for (s, e) in TRANSITIONS if s == current_state)}"
        ) from None


def events_from(state: str) -> list[str]:
    """Return the list of event names that have a transition mapped
    from ``state``. Useful for operator CLI 'what can I do from here?'
    queries + property tests."""
    return sorted(e for (s, e) in TRANSITIONS if s == state)


def reachable_from(state: str) -> set[str]:
    """Set of states reachable from ``state`` in one or more transitions.

    Includes the starting state IFF it's part of a cycle (e.g.,
    AWAITING_CI has a self-loop via ``ci_flake_retry``).
    """
    seen: set[str] = set()
    stack = [state]
    cycles_back = False
    while stack:
        s = stack.pop()
        for (frm, _evt), to in TRANSITIONS.items():
            if frm != s:
                continue
            if to == state and s != state:
                # A transition leads back to the start — that's a cycle.
                cycles_back = True
            if to == state and s == state:
                # Self-loop on the start state.
                cycles_back = True
            if to in seen:
                continue
            seen.add(to)
            stack.append(to)
    if not cycles_back:
        seen.discard(state)
    return seen


# ─── property invariants (v9: ship 6 for v1) ──────────────────────────


@dataclass(frozen=True)
class InvariantViolation:
    """Returned by ``check_*`` helpers when an invariant fails. The
    property tests assert ``check_*() == []``."""

    invariant: str
    message: str


def _violation(invariant: str, message: str) -> InvariantViolation:
    return InvariantViolation(invariant=invariant, message=message)


def check_no_path_implementing_to_reviewing_skips_ci(
) -> list[InvariantViolation]:
    """Invariant #1 (v9 load-bearing): REVIEWING is reachable from
    IMPLEMENTING only through AWAITING_CI.

    Closes the no-mans-land race by construction.
    """
    name = "no_path_implementing_to_reviewing_skips_ci"
    # Direct edge IMPLEMENTING → REVIEWING would violate this.
    for (frm, evt), to in TRANSITIONS.items():
        if frm == "IMPLEMENTING" and to == "REVIEWING":
            return [_violation(
                name,
                f"direct IMPLEMENTING → REVIEWING via {evt!r}; must "
                f"route through AWAITING_CI"
            )]
    # AWAITING_CI is the only path; check it's reachable from
    # IMPLEMENTING.
    if "AWAITING_CI" not in reachable_from("IMPLEMENTING"):
        return [_violation(
            name, "IMPLEMENTING cannot reach AWAITING_CI"
        )]
    return []


def check_terminal_states_have_no_exits() -> list[InvariantViolation]:
    """Invariant #2: terminal states are sinks — no outgoing transitions.

    Note: ``STUCK`` has the ``operator_unstick`` exit, which is the
    OPERATOR-driven escape hatch. Treated as "outgoing for
    operator-driven events, but not for controller-driven events" —
    we permit it.
    """
    name = "terminal_states_have_no_exits"
    out: list[InvariantViolation] = []
    for (frm, evt), to in TRANSITIONS.items():
        if frm in {"MERGED", "ABANDONED", "CREATED_PR"}:
            out.append(_violation(
                name,
                f"terminal {frm!r} has transition via {evt!r} → {to!r}"
            ))
        # STUCK's only allowed exit is operator_unstick.
        if frm == "STUCK" and evt != "operator_unstick":
            out.append(_violation(
                name,
                f"STUCK has unauthorized exit via {evt!r} → {to!r}; "
                f"only 'operator_unstick' is allowed"
            ))
    return out


def check_tier_monotonic_non_decreasing() -> list[InvariantViolation]:
    """Invariant #3: when ESCALATING fires, the next tier is strictly
    greater than the previous. Encoded structurally: ESCALATING has
    only two events — escalate_next_tier_available (→ IMPLEMENTING,
    interpreted by master as tier+1) and escalate_max_tier_exhausted
    (→ ABANDONED).
    """
    name = "tier_monotonic_non_decreasing"
    out: list[InvariantViolation] = []
    escalating_events = events_from("ESCALATING")
    if set(escalating_events) != {
        "escalate_next_tier_available", "escalate_max_tier_exhausted",
    }:
        out.append(_violation(
            name,
            f"ESCALATING has unexpected events {escalating_events}; "
            f"expected {{'escalate_next_tier_available', "
            f"'escalate_max_tier_exhausted'}}"
        ))
    return out


def check_every_pr_workflow_includes_reviewing() -> list[InvariantViolation]:
    """Invariant #4: every path from DISCOVERED to MERGED must pass
    through REVIEWING.

    Per Hard Rule #1: every PR receives a fresh LLM review.
    """
    name = "every_pr_workflow_includes_reviewing"
    out: list[InvariantViolation] = []
    # Check: no transition lands in MERGED from anything but MERGING.
    for (frm, evt), to in TRANSITIONS.items():
        if to == "MERGED" and frm != "MERGING":
            out.append(_violation(
                name,
                f"MERGED reachable from {frm!r} via {evt!r} (not MERGING)"
            ))
    # Check: MERGING is reachable only via REVIEWING.
    for (frm, evt), to in TRANSITIONS.items():
        if to == "MERGING" and frm != "REVIEWING":
            out.append(_violation(
                name,
                f"MERGING reachable from {frm!r} via {evt!r} (not REVIEWING)"
            ))
    return out


def check_conflict_resolving_bounded() -> list[InvariantViolation]:
    """Invariant #5: CONFLICT_RESOLVING transitions for 1st-time
    resolution go to IMPLEMENTING; 2nd same-tier resolution goes to
    ESCALATING; 3rd-or-later goes to STUCK. Structurally enforced
    via exactly these named events.
    """
    name = "conflict_resolving_bounded"
    out: list[InvariantViolation] = []
    expected_events = {
        "conflict_resolved_first": "IMPLEMENTING",
        "conflict_resolved_second_same_tier": "ESCALATING",
        "conflict_repeated_three_plus": "STUCK",
        "conflict_irreconcilable": "STUCK",
        "pickup_exhausted": "STUCK",
    }
    actual = {
        evt: to for (frm, evt), to in TRANSITIONS.items()
        if frm == "CONFLICT_RESOLVING"
    }
    for evt, expected_to in expected_events.items():
        got_to = actual.get(evt)
        if got_to != expected_to:
            out.append(_violation(
                name,
                f"CONFLICT_RESOLVING + {evt!r}: expected → {expected_to!r}; "
                f"got → {got_to!r}"
            ))
    unexpected = set(actual) - set(expected_events)
    if unexpected:
        out.append(_violation(
            name,
            f"CONFLICT_RESOLVING has unexpected event(s) {sorted(unexpected)}"
        ))
    return out


def check_escalation_deterministic() -> list[InvariantViolation]:
    """Invariant #6: ESCALATING has exactly two transitions, both
    deterministic. Combined with tier-monotonic-non-decreasing, this
    means the escalation policy is static (min(tier+1, MAX_TIER)).
    """
    name = "escalation_deterministic"
    out: list[InvariantViolation] = []
    actual = {
        evt: to for (frm, evt), to in TRANSITIONS.items()
        if frm == "ESCALATING"
    }
    if actual != {
        "escalate_next_tier_available": "IMPLEMENTING",
        "escalate_max_tier_exhausted": "ABANDONED",
    }:
        out.append(_violation(
            name,
            f"ESCALATING transitions are non-deterministic: {actual}"
        ))
    return out


# Registry of all v1 load-bearing invariants. Tests iterate this.
LOAD_BEARING_INVARIANTS: dict[str, callable] = {  # type: ignore[type-arg]
    "no_path_implementing_to_reviewing_skips_ci":
        check_no_path_implementing_to_reviewing_skips_ci,
    "terminal_states_have_no_exits":
        check_terminal_states_have_no_exits,
    "tier_monotonic_non_decreasing":
        check_tier_monotonic_non_decreasing,
    "every_pr_workflow_includes_reviewing":
        check_every_pr_workflow_includes_reviewing,
    "conflict_resolving_bounded":
        check_conflict_resolving_bounded,
    "escalation_deterministic":
        check_escalation_deterministic,
}


def check_all_invariants() -> list[InvariantViolation]:
    """Run every load-bearing invariant; return concatenated violations."""
    out: list[InvariantViolation] = []
    for check in LOAD_BEARING_INVARIANTS.values():
        out.extend(check())
    return out


__all__ = [
    "EVENTS",
    "Event",
    "IllegalTransitionError",
    "InvariantViolation",
    "KNOWN_STATES",
    "LOAD_BEARING_INVARIANTS",
    "NON_TERMINAL_STATES",
    "TERMINAL_STATES",
    "TRANSITIONS",
    "apply_event",
    "check_all_invariants",
    "events_from",
    "reachable_from",
]