// compiler-driven-edit — the observe-then-bounce loop for a
// behaviour-preserving type/signature edit, as a Workflow script.
//
// This is the executor for the `compiler-driven` selector arm (see
// boss/SKILL.md "Entry-path reflection"). The arm is entered on an
// OBSERVABLE/syntactic trigger — "a type or signature edit at a definition
// site that propagates mechanically across the sites the type checker
// enumerates" — NOT on a prediction that the change is behaviour-preserving.
// A real build + suite run then settles the verdict:
//
//   an edit landed AND clean build AND suite green unchanged -> DONE  (edits unstaged; orchestrator commits)
//   the edit phase produced NO change (clean tree)           -> BLOCKED (no-op-edit) — never DONE
//   a hole the edit cannot resolve          -> BOUNCE up, per the straddle rule:
//        forces a design choice                 -> specify
//        is test-specifiable new behaviour      -> tdd  (RED-first)
//   the suite is not green / not unchanged  -> BOUNCE to debug  (RED-first)
//
// "An edit landed" is load-bearing: the done-signal `build_clean &&
// suite_green_unchanged` is vacuously true on an EMPTY tree, so doing nothing
// would otherwise read as DONE. DONE requires positive evidence the tree
// differs from HEAD — checked twice: the edit agent's applied_changes self-
// report (cheap, pre-suite) and the verify agent's independent working_tree_
// dirty observation (authoritative backstop).
//
// The fallible ex-ante guess ("this is behaviour-preserving") is replaced by
// a cheap ex-post detection: a mis-routed behaviour change fails the
// post-condition and bounces instead of shipping green-but-wrong. This
// generalises the plugin's RED-first philosophy — observe, do not predict.
//
// "Suite green UNCHANGED" is load-bearing: the suite must pass with NO test
// added, removed, or weakened to make it pass. A new test would mean the
// edit encoded new behaviour — which is the tdd/spec arm, not this one.
//
// The `verify` step below (build + suite-green-unchanged) is the single
// phase the implement loop's pure-refactor case could never invoke on its
// own; here it is a standalone, independently-invokable agent call.
//
// Discipline: the script never commits and never moves main HEAD; all edits
// stay unstaged for the orchestrator. The script has no shell of its own —
// the edit and the verify both run inside agent() calls.
//
// Model policy: every agent() call pins an explicit model — never the
// session-model inherit (which could route to an unintended tier, e.g. fable —
// banned for all plugin agents and workflows). Both phases here are mechanical
// (compiler-enumerated propagation, build/suite re-run), so both run sonnet.
// Effort policy mirrors it: every call pins an explicit effort — the edit
// (real code work) runs high, the build/suite verify (schema-bound check)
// runs medium. See docs/agent-template.md § effort.
//
// Carrier — Workflow `args`:
//   edit_description: what type/signature change to make
//   def_site:         the definition site (file + symbol) it originates from

export const meta = {
  name: 'compiler-driven-edit',
  description:
    'Execute a behaviour-preserving type/signature edit at a definition site, propagate it mechanically across the sites the build enumerates, then let a real build + suite run settle the verdict: clean build AND suite green unchanged -> done (edits unstaged for the orchestrator to commit); a hole the edit cannot resolve -> bounce up per the straddle rule (specify for a design choice, tdd for test-specifiable new behaviour); suite not green-unchanged -> bounce to debug (RED-first). Never commits, never moves main HEAD.',
  phases: [{ title: 'Edit + propagate' }, { title: 'Verify' }, { title: 'Verdict' }],
}

const { edit_description, def_site } = args || {}

const STANDING =
  "Standing reading first (the plugin convention): read the project's CLAUDE.md " +
  '(its "## Skills plugin: project facts" name the build and test commands) and ' +
  '`git log -10 --format=full`. Resolve the build/test commands from those facts.'

const EDIT_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['build_clean', 'hole_needs_decision', 'applied_changes'],
  properties: {
    build_clean: { type: 'boolean', description: 'the project build is clean after the edit + mechanical propagation' },
    applied_changes: {
      type: 'boolean',
      description:
        'GROUND TRUTH, not intent: the working tree actually differs from HEAD after the edit. Determine it by running ' +
        '`git status --porcelain` (any line) or `git diff HEAD --stat` (non-empty) — true only if at least one file changed. ' +
        'false means a no-op edit (you touched nothing); report it as false rather than guessing true.',
    },
    hole_needs_decision: {
      type: 'boolean',
      description:
        'a site could not be resolved mechanically: it either forces a design choice, or resolving it would encode new behaviour — so the change was not purely behaviour-preserving after all',
    },
    bounce_to: {
      type: 'string',
      enum: ['specify', 'tdd'],
      description:
        'on hole_needs_decision, per the straddle rule: `specify` if the hole forces a genuine design choice; `tdd` if the discovered work is new behaviour pinnable as one falsifiable assertion. When unsure, `specify` (the conservative heavy path, which itself bounces onward).',
    },
    hole_detail: { type: 'string', description: 'on hole_needs_decision: what the hole forces (the decision, or the new behaviour discovered)' },
    sites: { type: 'integer', description: 'number of sites the build flagged and the edit touched' },
  },
}
const VERIFY_SCHEMA = {
  type: 'object',
  additionalProperties: false,
  required: ['build_clean', 'suite_green_unchanged', 'working_tree_dirty'],
  properties: {
    build_clean: { type: 'boolean' },
    suite_green_unchanged: {
      type: 'boolean',
      description: 'the full suite passes with NO test added, removed, or weakened to make it pass',
    },
    working_tree_dirty: {
      type: 'boolean',
      description:
        'GROUND TRUTH: the working tree differs from HEAD — i.e. an edit actually landed. Run `git status --porcelain` ' +
        '(any line) or `git diff HEAD --stat` (non-empty). false means a clean tree / no-op edit, which is NOT a ' +
        'behaviour-preserving success no matter how green the build and suite are.',
    },
    detail: { type: 'string', description: 'on failure: which tests went red, or which test was changed' },
  },
}

// ---- Phase 1 — make the edit and let the compiler enumerate the sites ----
phase('Edit + propagate')
const edit = await agent(
  `${STANDING}\n\nMake this behaviour-preserving type/signature edit at its definition site, then propagate it ` +
    'MECHANICALLY across every site the build flags — let the type checker enumerate the edit sites. Introduce NO ' +
    'new behaviour, add NO new test, change NO existing test. If a flagged site cannot be resolved without making a ' +
    'design decision, OR resolving it would encode new behaviour, STOP and report it as a hole rather than guessing. ' +
    'When you report a hole, CLASSIFY it (straddle rule): set bounce_to = "specify" if it forces a genuine design ' +
    'choice, or "tdd" if the discovered work is new behaviour pinnable as one falsifiable assertion. When unsure, ' +
    '"specify". Leave all edits UNSTAGED; never commit.\n\n' +
    `EDIT: ${edit_description}\nDEFINITION SITE: ${def_site}\n\n` +
    'Then run the project build and report: is the build clean, does any hole need a decision (with detail + bounce_to), ' +
    'how many sites were touched, and — checked against `git status --porcelain` / `git diff HEAD`, NOT from memory — ' +
    'whether the working tree actually changed (applied_changes).',
  { agentType: 'implementer', model: 'sonnet', effort: 'high', label: 'edit+propagate', phase: 'Edit + propagate', schema: EDIT_SCHEMA },
)
if (!edit) return { status: 'BLOCKED', reason: 'edit agent did not return' }
if (edit.hole_needs_decision) {
  // The change was not purely mechanical after all. Per the straddle rule,
  // route UP: a genuine design choice -> specify; test-specifiable new
  // behaviour -> tdd (RED-first). Default to specify when unclassified —
  // the conservative heavy path, which itself bounces onward.
  const to = edit.bounce_to === 'tdd' ? 'tdd' : 'specify'
  return {
    status: 'BOUNCE',
    to,
    reason: to === 'tdd' ? 'discovered test-specifiable new behaviour' : 'a hole forces a design decision',
    detail: edit.hole_detail || '',
  }
}
// No-op guard (cheap, first line of defence): the done-signal must not be
// satisfiable by doing nothing. If the edit phase reports no hole yet left the
// working tree clean, no edit landed — a no-op is not a behaviour-preserving
// success, and running the suite against a clean tree would only manufacture a
// vacuous green. Stop here with a distinct infra-style BLOCKED rather than
// proceeding toward DONE. (`sites` is the wrong signal: a legitimate edit can
// touch only the definition site, sites 0, and still dirty the tree.)
if (!edit.applied_changes) {
  return {
    status: 'BLOCKED',
    kind: 'no-op-edit',
    reason:
      'the edit phase produced no changes — the working tree is clean against HEAD, so no edit landed. ' +
      'A no-op edit is not a behaviour-preserving success. Likely the task fell outside the shape this arm ' +
      'handles (a type/signature edit the compiler enumerates), e.g. a crate scaffold/extraction; re-route it.',
  }
}

// ---- Phase 2 — verify (the independently-invokable phase) ---------------
phase('Verify')
const verify = await agent(
  `${STANDING}\n\nVerify the edit is behaviour-preserving WITHOUT changing any code or test. Run the project build ` +
    'and the full test suite. Report whether the build is clean and whether the suite is green AND UNCHANGED — i.e. ' +
    'every test passes and NO test was added, removed, or weakened versus the pre-edit baseline (compare `git diff ' +
    'HEAD` for test-file changes). Also report working_tree_dirty — whether `git status --porcelain` / `git diff HEAD` ' +
    'shows ANY change at all (a clean tree means no edit landed). Do NOT edit anything; do NOT commit.',
  { model: 'sonnet', effort: 'medium', label: 'verify(build+suite)', phase: 'Verify', schema: VERIFY_SCHEMA },
)

// ---- Phase 3 — verdict --------------------------------------------------
phase('Verdict')
if (verify && verify.build_clean && verify.suite_green_unchanged && verify.working_tree_dirty) {
  return {
    status: 'DONE',
    sites: edit.sites ?? null, // ?? not ||: a legitimate sites:0 (def-site-only edit) must report 0, not null
    note: 'behaviour-preserving edit verified; edits unstaged in the working tree for the orchestrator to commit',
  }
}
// Vacuous-green backstop (authoritative, second line of defence): build + suite
// are green but verify INDEPENDENTLY observed a clean tree. A clean tree is not
// a regression, so debug (RED-first) would be the wrong route — there is nothing
// to reproduce. It is a no-op edit the Phase-1 self-report missed; surface it as
// the same distinct BLOCKED, never as DONE.
if (verify && verify.build_clean && verify.suite_green_unchanged && !verify.working_tree_dirty) {
  return {
    status: 'BLOCKED',
    kind: 'no-op-edit',
    reason:
      'verify observed a clean working tree (no diff against HEAD) — no edit landed, so the green build + suite are ' +
      'vacuous. DONE requires positive evidence that an edit actually landed; a no-op edit is not a success.',
  }
}
// observe-then-bounce: the post-condition failed, so the change was NOT
// behaviour-preserving after all. Route RED-first via debug rather than
// shipping a green-but-wrong commit.
return {
  status: 'BOUNCE',
  to: 'debug',
  reason: !verify
    ? 'verify agent did not return'
    : !verify.build_clean
      ? 'build not clean after the edit'
      : 'suite not green-unchanged — a regression surfaced, so the edit was not behaviour-preserving',
  detail: verify ? verify.detail || '' : '',
}