Support Kimi Code CLI as a builder (PIR #1201)

[mohidmakhdoomi]

PIR Review: Support Kimi Code CLI as a builder

Fixes #1201

Re-integration notice (2026-08-09). This PR was parked on two upstream blockers, both now merged (#1317/#1267, #1356/PIR #1233), and main moved 900+ commits — including Spec 1313, which made afx send mailbox-first. kimi itself moved 0.27.0 → 0.34.0. The branch has been merged up and the feature substantially redesigned against what changed underneath it. The delivery mechanism, the resume mechanism, and the pacing seam are all different from what earlier reviewers saw; the summary below describes the current design, and "What changed since your last review" near the end lists the deltas. Re-review from scratch rather than from memory.

Summary

Adds the Kimi Code CLI (kimi, ≥ 0.33.0) as a supported builder harness — shell.builder: "kimi" / builderHarness: "kimi" / --builder-cmd kimi now produce a working builder instead of the #1062 false-Claude fallthrough (which appended --append-system-prompt and a positional prompt, both rejected by kimi, and could route a stale Claude --resume <uuid> into it).

Kimi has no system-prompt flag and takes no positional prompt, so role and task travel on two different channels:

• Role → --agent-file (kimi 0.31.0+). getWorktreeFiles writes an agent-definition file into the worktree whose body wraps the role around ${base_prompt} — the token that interpolates kimi's own default system prompt, so the role extends rather than replaces it. This is the claude --append-system-prompt analogue.
• Task → the Spec 1313 mailbox. The generated launch script queues the task with afx send, and the render gate delivers it onto a verified-empty composer. Never a direct PTY write, so a boot screen, a busy line, or kimi's folder-trust dialog holds the message rather than corrupting or losing it.

Crash restarts resume with the documented, cwd-scoped kimi -c — no session id is ever baked into generated bash. Kimi as an architect remains out of scope (stage 2); buildRoleInjection throws and doctor warns, so misconfiguration fails loudly rather than falling through to claude flags.

The finding that shaped the design

kimi -c does not fail when there is nothing to continue. It prints No sessions to continue under "<cwd>"; starting a fresh session. and starts one anyway — and that session never saw --agent-file, so it runs silently roleless. That is the #929 hazard class, arriving through a documented flag.

So the launch loop only takes -c after an inlined node -e store probe proves a conversation exists for this cwd, and the probe fails closed: any error (no store, unreadable dir, malformed JSON) exits non-zero and the loop relaunches fresh with the role, which is always safe. Tests execute that probe against fixture stores and cross-check its verdict against the TypeScript discovery it mirrors, so the hand-written snippet cannot silently drift from findLatestKimiSessionId.

The probe asks "would kimi -c continue this?", not "does a directory exist" — a distinction review had to teach me (see below). Kimi lists a cwd's sessions before continuing one, and that listing drops archived sessions and ids it does not recognize, so a session we call resumable but kimi skips lands right back on the roleless path. Both filters now apply on both sides of the mirror.

The same probe makes the script's entry self-configuring, so afx spawn --resume and a Tower-side terminal re-create need no second script shape — and a re-run never re-queues the task into a live conversation.

⚠️ Please look here first: two edits to shared, just-merged gate logic

servers/render-gate.ts is Spec 1313 code that landed recently. This PR touches its classifier in two places. Both are opt-in per profile, and neither can change behaviour for claude, codex or agy — argued below and pinned by tests.

1. The marker exemption follows the matched span instead of column 0

-      if (row === markerRow && col === 0) continue; // the marker glyph itself
+      if (col < markerEnd) continue; // the marker glyph itself

Why: kimi draws its composer inside a rounded box, so its prompt marker sits at column 3 (│ > ), not the row start. Under the column-0 rule the > glyph counts as user text, so a genuinely empty Kimi composer classifies user-text forever — i.e. holds all of its mail, permanently.

2. A profile may declare an upper bound for the composer region

GateProfile gains an optional regionStartPatterns. Kimi sets it to the box top; every other profile leaves it unset and keeps scanning from the marker row exactly as before.

This one fixes a false CLEAN, and it was found by review, not by me. KIMI_MARKER matches │ >, findMarkerRow takes the last match, and the scan started at that row. So a draft whose final line begins with > — a pasted quote, a markdown blockquote — puts the marker on the continuation row, leaving the real draft text above the scanned region. Measured on real kimi 0.34.0:

 ╭──────────────────────────────
 │ > implement the whole feature
 │   >
 ╰──────────────────────────────

→ classified {clean: true, detail: "empty"}. A queued message would then have been typed on top of unsent user input — the exact corruption Spec 1313 removes by construction. Committed as the kimi-multiline-bare fixture, captured rather than constructed.

The bound is exclusive, mirroring the region end, and that is load-bearing rather than stylistic: the box-top row's right corner ╮ is not in the classifier's ignorable-glyph set, so an inclusive bound counted it as user text and held every idle kimi composer forever. The fixture suite caught that on the first attempt.

Why other profiles cannot reach it: they declare no regionStartPatterns, so the region starts at markerRow; and since findMarkerRow returns the last match, no row below it can match either. The set of marker-matching rows in their region is exactly {markerRow} — the previous behaviour, by construction. A test asserts all three declare no region start, and that text above the composer still classifies clean for claude and codex.

Why it is a no-op for every other app, argued and then pinned by tests:

profile	marker	span	effect
claude	^[❯›]	1	col < 1 ≡ col === 0 — literally the old rule
codex	^[❯›]	1	same
agy	^>	2	extra cell is the space, already skipped by the whitespace rule that runs before the marker check
kimi	^\s*│\s*>	4	the case this exists for

Guardrail tests (render-gate.test.ts, "marker-span exemption is a no-op…"): the exact span per shipped profile; a tightest-possible 1-char draft in the first cell the exemption could wrongly reach, per profile, all still busy (over-skipping is the only direction that could cause harm — a false CLEAN); proof that agy's span can never over-reach a typed character (>x doesn't match its marker at all); and a direct before/after demonstration that a span-2 kimi profile classifies the real 0.34.0 idle capture user-text while the shipped span-4 one classifies it clean. Every pre-existing claude/codex/agy fixture still passes unchanged.

Undocumented-surface reliance (audited against kimi 0.34.0, 2026-08-09)

Two surfaces, both dated so the reliance can be re-checked on each Kimi major:

1. Session store ~/.kimi-code/sessions/wd_*/session_*/state.json. This has already drifted once: 0.33.0 renamed workDir → cwd, moved timestamps from ISO strings to epoch ms, and dropped lastPrompt. Readers accept both shapes, and codev doctor asserts the load-bearing facts explicitly and names the one that broke rather than reporting "something changed".

2. Workspace-trust record ~/.kimi-code/workspace-trust/wd_<basename>_<sha256(root)[:12]> → {root, trustedAt}. This is the maintainer veto point, so here is the full argument.

   kimi 0.33.0 added a startup "Trust this folder?" dialog. A builder worktree is always a brand-new directory; the dialog renders before any composer, and its only non-trusting option exits kimi — so an unattended builder would sit on it forever. The spawn path therefore pre-writes the trust record.

   • No sanctioned bypass exists. kimi --help has no flag; a full strings sweep of the 0.34.0 binary for KIMI_* env vars and for trust config keys found nothing (every "trust" hit was KaTeX/V8/OpenSSL noise). I looked for a supported knob first, as requested, and there isn't one.
   • What trust actually gates is narrow: whether project-level MCP servers (.mcp.json, .kimi-code/mcp.json) load from the folder. It does not gate tool execution or writes.
   • Scope: written only for a worktree Codev itself created, for a builder the human explicitly spawned, already running --yolo. It grants strictly less than launching the builder already authorized, and never touches a directory the user did not hand us.
   • Fail-soft: on any error the dialog simply appears, the gate holds the task message (no composer marker → busy), and mailbox escalation surfaces it. Never a silent misdelivery.
   • Drift is detected, not silent: codev doctor validates our derivation against kimi's own records (each record carries the root it was written for, so the expected filename is recomputable). A scheme change surfaces as a named warning instead of silently stranding every new builder on the dialog.

   My reviewers split on this one, so you should see both sides rather than just my case. Codex argued it is a real security boundary: --yolo governs approval of the agent's tool calls, whereas workspace trust governs whether repository-controlled MCP configuration is loaded and its processes started at all — so a builder spawned on a fork PR or other untrusted branch could have attacker-controlled MCP config loaded without a human ever seeing the decision. Claude reviewed the same code and reached the opposite conclusion: a --yolo builder in a Codev-created worktree already holds strictly more authority than MCP loading confers. I find Claude's reading more persuasive for the worktrees Codev creates, but Codex's fork-PR scenario is the case where the two arguments genuinely diverge, and that is a policy call I do not think is mine to settle.

   If you'd rather not ship the hash write at all, the fallback is that Kimi builders require one human keypress at first launch; say the word and I'll cut it. A narrower option, if you want the automation but not the blanket: refuse the pre-write when the worktree carries project-level MCP configuration.

Corrections to claims this PR previously made

• "Kimi has no hook seam, so Builder worktree write-guard: prevent writes anchored at the main checkout root #1018 write-guard parity is impossible" — obsolete. Kimi documents blocking PreToolUse hooks ([[hooks]] in config.toml, exit code 2 blocks, 18 events as of 0.32.0). Parity is achievable. I have scoped it as follow-up rather than growing this PR further, but that is your call — say so and I'll add it here. Until it lands, a Kimi builder can write outside its worktree, and the docs now say exactly that.

Two decisions that are yours, not mine

A. The version floor moves 0.27.0 → 0.33.0, which drops working installs

This is a real compatibility reduction and I want it visible rather than buried in a diff. The reasoning chain:

1. --agent-file requires ≥ 0.31.0. Below that the role does not inject at all and the builder runs silently roleless — the worst available failure mode, and not one a user would notice quickly.
2. The folder-trust dialog appears at 0.33.0, which is what the trust pre-write exists to handle. On 0.31–0.32 there is no dialog, so that machinery is inert — but it also means those versions are a genuinely different startup path from the one I exercised.
3. 0.33.0 is an engine boundary: it made agent-core-v2 the default. Every live measurement backing this PR — store shape, trust behaviour, the render-gate composer profile — was taken on 0.34.0, i.e. on that engine. 0.31–0.32 run the old engine and are unmeasured.
4. Kimi ships weekly, and its store has already renamed a load-bearing field once inside this PR's lifetime. Under that cadence a narrow, evidence-backed floor is safer than a wide compatibility claim I cannot stand behind.

So the floor sits at the oldest version the evidence actually covers, not the oldest that would nominally function. If you would rather accept 0.31.0 (functional minimum, unmeasured) or hold at 0.27.0 (maximum compat, definitely broken for role injection), say which and I'll change the one constant in doctor.ts plus the docs.

B. The .builder-kimi marker is deleted — this is not a revert of your July fix

Your July REQUEST_CHANGES found a real bug: the bare launch shape (no role, no prompt) never persisted .builder-kimi-session, so an override-spawned bare Kimi builder (--builder-cmd kimi in a claude-configured workspace) fell through to claude's 80ms Enter and its mail was swallowed. That fix — touch the marker in the bare branch — was correct and shipped.

This PR removes the marker entirely, so I want to be explicit that the property your finding protected is now stronger, not weaker.

The marker was a separate artifact that every launch shape had to remember to write. That is a standing obligation, and the bare shape is precisely the one that forgot it — which is why your review caught a bug rather than a typo. Adding the missing touch fixed that instance; it did not remove the class. A future fifth launch shape could forget it again.

Pacing now reads the harness name out of the generated .builder-start.sh, which is generated from the resolved harness. There is nothing to remember: any shape that launches kimi necessarily names kimi in command position, because that is the launch. The obligation is discharged by construction rather than by discipline, and it is still override-proof for exactly your scenario — a --builder-cmd kimi spawn against a claude-configured workspace resolves kimi, because the script was generated from the override.

Tests keep your scenario pinned directly (mailbox-pacing.test.ts: "resolves kimi for the BARE launch shape too — the shape the old marker probe missed", plus an explicit override-proofness test), and spawn-worktree.test.ts pins that both generated shapes put kimi in command position, so a refactor that hid it would fail rather than silently degrade pacing.

What changed since your last review

Was	Now	Why
Seed bootstrap: kimi -p seed → capture session.resume_hint → pinned kimi -S <id> loop	Role via --agent-file; task via the mailbox	Drops 3 undocumented surfaces; role rides a system prompt instead of a user turn
seed-kick.ts: sentinel watcher + grace + BEGIN written straight to the PTY, verified via state.json.lastPrompt	Deleted. Spec 1313's render gate is the readiness barrier	A direct PTY write is exactly what Spec 1313 forbids; the gate already answers "is this composer empty?"
Resume: explicit -S <discovered-id>	kimi -c behind a fail-closed store probe	Documented flag; no undocumented id in generated bash
Pacing via a .builder-kimi marker file	Harness read from the generated .builder-start.sh	The marker obliged every launch shape to write one — the bare shape didn't, which was your finding last round. The launcher is generated from the resolved harness, so it cannot be forgotten or overridden away
message-pacing.ts + seedKick on createTerminal	resolvePacingForSession in mailbox-wiring.ts; SeedKickRequest removed from the SDK	Spec 1313 replaced the routes the old pacing hooked into — it was wired to nothing after the merge

What the 3-way review round found (and what it changed)

Before opening this for re-review I ran gemini, codex and claude over the post-merge delta, asking them to attack the shared gate edit hardest. gemini APPROVE; codex and claude both REQUEST_CHANGES — and they were right. Full dispositions are committed at codev/projects/1201-*/1201-cmap-postpivot-dispositions.md; the two blocking ones are worth stating here because they say something about where the risk in this PR actually lives:

• The false CLEAN described above. Claude reproduced it on a constructed screen and flagged honestly that it had no live kimi to confirm the real multi-row geometry. I measured it — kimi renders exactly that shape. Claude also proposed a second input (a marker row inside a second box below the composer); measured, that one is not reachable, because kimi's / menu renders as unclosed │ rows with no ╰ beneath them, so anything inside it yields no-region-end → held. Both are now fixtures.
• The store probe diverged from the TypeScript it mirrors, and the cross-check test did not catch it because it compared two implementations of the same omissions. Codex found the dangerous direction: an archived session authorized -c, which kimi then refuses to continue, producing the silently-roleless session the guard exists to prevent. Claude found the safe-but-harmful direction: readdirSync on a stray non-directory threw ENOTDIR into the single outer try, so one .DS_Store in ~/.kimi-code/sessions/ disabled resume machine-wide, permanently and silently.

Also fixed from that round: shell metacharacters in a builder id or task path could execute when the launch script printed a recovery hint (all three reviewers, from different angles); a crash loop re-queued the same task every ~2s even though the mailbox persists held rows; and both drift probes reported healthy forever after a store migration, because "any record still matches" is satisfied by the pre-migration records.

The common thread: every one of these lives in a state a happy-path run does not produce — an empty composer and a clean store both behave correctly, which is precisely why three passing live demos missed them.

One more disclosure, since it affects how you should read the demo. Two demo steps were failing when I picked this back up, and the cause was the demo, not the product: its role told the model to prefix every reply with a token, which measures whether K3 honours a persistent output-format constraint rather than whether the role was injected. The --agent-file probe, run against a production-identical agent file, passed 7/7 including role survival across kimi -c. The demo now asks for a codeword instead — the same oracle the probe uses — and carries a comment explaining why, so the weaker check does not come back.

Verification

• pnpm build clean; full suite 4900 passed / 48 skipped / 0 failed.
• Live demo against real kimi 0.34.0, 7/7 (codev/spikes/pir-1201-kimi-builder-demo.mjs, runs the REAL dist modules): render gate classifies the live composer; --agent-file role honored in the interactive TUI; paced multi-line delivery submits; crash → store probe → kimi -c → role survives; probe fails closed on an empty store; trust pre-write idempotent.
• Pivot validation, 7/7 (pir-1201-kimi-agentfile-probe.mjs): --agent-file injects in both -p and the interactive TUI; TUI start mints no session, the first message mints exactly one; kimi -c resumes with the role binding intact and mints no second session.
• Gate fixtures are real 0.34.0 captures (pir-1201-kimi-gate-measure.mjs), committed raw — they carry only throwaway /tmp paths. Idle → clean; draft, multi-line draft, the bare-> multi-line draft, / menu, @ picker and the folder-trust dialog → busy (so a blind Enter can never confirm filesystem trust).

Out of scope

Kimi as architect (stage 2); ACP / kimi server adapter; #1018 write-guard parity (now achievable — see above).

[mohidmakhdoomi]

Architect Integration Review

Contributor-side review summary for maintainers (this PR was developed under the PIR protocol on our fork; we do not merge — that call is yours).

Process: Plan and dev-approval were human-gated pre-PR. The dev-approval gate included a full-path live demo through a locally installed build — a real afx spawn of a Kimi builder through Tower showing (1) seed-session bootstrap with session-id capture, (2) sentinel-gated, store-verified BEGIN delivery, (3) multiline afx send at the pinned Enter delay, and (4) inner-restart context retention via kimi -S — plus codev doctor's new kimi checks.

Consultation (CMAP, single advisory pass): gemini APPROVE, claude APPROVE, codex REQUEST_CHANGES. The codex finding was real and was accepted + fixed in 732f04b: seed-kick delivery confirmation was a substring match on lastPrompt, and the fresh-spawn seed prompt itself contains "BEGIN", so verification false-positived before the kick submitted — defeating the swallowed-Enter recovery. Fix is whitespace-normalized equality, with two pinning regression tests (both fail pre-fix), seed-kick suite 14/14, and a post-fix live demo re-run (5/5).

Architect verification of the post-CMAP fix (since PIR's single-pass consultation does not re-review fixes): I reviewed confirmed() in seed-kick.ts and the pinning tests directly — the equality predicate is correct, preserves the multiline-payload fallback (kimi flattens submitted newlines; normalization covers it), and the retry ladder (Enter re-send → one re-kick → loud warn) is intact. Known benign edge: a message raced into the session during the ~10s verify window causes one bounded re-kick, then a warning.

Scope: verified against issue #1201's builder-MVI checklist — no architect-parity changes (tower-utils/tower-instances/tower-terminals/session-manager/architect.ts untouched), no ACP adapter; kimi-as-architect fails loudly. Undocumented Kimi surfaces are labeled as observed, pinned to kimi >= 0.27.0 with a doctor smoke probe.

---

Architect integration review

[waleedkadous]

Outstanding work — this is one of the most disciplined external PRs we've received; the observed-vs-documented honesty around Kimi's store and the store-verified BEGIN ladder are exactly right. I'd like to see one change before merge: the bare launch path (no role, no prompt) doesn't persist .builder-kimi-session, so pacing resolution falls back to workspace config and an override-spawned bare Kimi builder gets Claude's Enter timing — the swallowed-Enter bug this PR fixes. Persisting a marker on every Kimi launch shape (plus a regression test for the override-spawn case, and softening the arch.md "exists iff Kimi-shaped" claim) closes it. I've added the area/tower label to #1201 for you.

[mohidmakhdoomi]

Architect Response — maintainer review addressed (2abd362)

Thank you for the review — the finding is real and is fixed in 2abd362.

The gap, confirmed: KIMI_HARNESS.buildBuilderLaunchScript's bare branch (no role, no prompt — the --builder-cmd kimi override-spawn / afx spawn --worktree shape) returned a plain TUI loop that never wrote .builder-kimi-session. Seed and resume shapes both persist it, so pacing's marker-first probe held for them — but a bare builder fell through to the config-resolved harness and, in a claude-configured workspace, got the 80ms Enter that Kimi's paste detection swallows.

Fix: the bare branch now touches the marker before the loop — empty, since there is no session id to pin. touch preserves a previously seeded id; an empty file keeps the seed ! -s guard and buildResume's empty-id fallthrough intact, so no other shape's semantics move.

Regression tests (all fail pre-fix where noted):

• spawn-worktree.test.ts — the override-spawn pin you asked for; notably this test previously asserted the marker's absence in the bare script, which is how the gap survived review. Flipped and failing pre-fix.
• harness.test.ts — same pin at the provider-script layer; failing pre-fix.
• message-pacing.test.ts — real-fs test: an empty marker (exactly what touch produces) must resolve Kimi pacing over a claude workspace config. Passes pre-fix by design — it pins the probe as existence-based so a future content-based "improvement" can't silently re-open the bare shape.

Docs: arch.md's pacing paragraph and the message-pacing.ts header now carry the softened claim — every Kimi launch shape persists the marker (existence-based probe), and the converse is explicitly not claimed: a leftover marker is a launch breadcrumb, not proof of a live Kimi session (staleness cost: a ~1s-slower Enter). The literal "exists iff Kimi-shaped" phrasing traced to the builder's thread journal; corrected there via an appended dated entry rather than rewriting history.

Suites: harness 75/75, spawn-worktree 86/86, message-pacing 8/8, seed-kick 14/14; package build clean.

---

Architect integration review

CMAP results (iterated to convergence)

The maintainer-response change set was reviewed by a 3-way CMAP loop (gemini, codex, claude), re-run after every change until a full pass returned zero findings: iteration 1 reviewed the fix (2abd362), iteration 2 the resulting test-hardening commit (642b172), and iteration 3 the entire cumulative response diff (47d12ba..1de55e1) as a holistic convergence check.

Model	Verdict	Findings across iterations
gemini	APPROVE ×3	Iter 2 NIT (accepted): the pre-existing exit 1-before-loop assertion lacked a toContain('exit 1') guard — removing exit 1 would vacuous-pass (indexOf → -1, and -1 < any positive index) → fixed in 1de55e1. Iters 1 and 3: none.
codex	APPROVE ×3	Iter 1 MINOR (accepted): tests pinned the touch's presence but not that it stays before the while true loop → fixed in 642b172 (ordering assertions at both test layers). Iters 2 and 3: none.
claude	APPROVE ×3	Iter 1 NIT (thread-log phrasing) — explicitly no-action. Iter 2 NIT (accepted): the new ordering assertions lacked toContain('while true') — sound, but opaque failure diagnostic → fixed in 1de55e1; every ordering assertion now guards both substrings. Iter 3: none — additionally verified the no-race property (the touch completes before Tower can deliver a first send) and that the marker claims in the KIMI_SESSION_FILE JSDoc, message-pacing.ts header, and arch.md are mutually consistent.

Loop terminated at iteration 3: unanimous APPROVE, zero findings, on the full change set. Suites green throughout (harness 75, spawn-worktree 86, message-pacing 8, seed-kick 14); package build clean.

[waleedkadous]

Heads-up for your next iteration: PR #1244 (in review) changes the builder launch-loop contract — a deliberate agent exit (exit 0, no signal; see isDeliberateExit() in shellper-protocol.ts) now ends the loop with a keypress-gated relaunch instead of auto-respawning. The Kimi provider-owned loops in this PR replicate the old blind while true shape, so once #1244 lands, please adopt the shared LAUNCH_LOOP_TAIL (or its exit-code branch) in the Kimi script paths too — happy to point at the exact spots if useful.

[mohidmakhdoomi]

#1244 launch-loop contract adopted (bfc8d62)

Per the heads-up above: merged origin/main (brings PR #1244) and adopted the shared LAUNCH_LOOP_TAIL in the Kimi provider-owned launch scripts.

Change: LAUNCH_LOOP_TAIL was module-local to spawn-worktree.ts; since spawn-worktree.ts already imports from utils/harness.ts, the constant moved there (exported, JSDoc noting why it lives in the harness module) — no circular import, and both Kimi loops (the pinned -S loop shared by the fresh/resume shapes, and the bare TUI loop) now interpolate it. A deliberate exit 0 gates the relaunch on a keypress; nonzero/signal exits keep the auto-restart.

Tests: new it.each pins in harness.test.ts (fresh/resume/bare provider shapes) and spawn-worktree.test.ts (seeded + bare-override worktree shapes) assert status=$?, the exit-0 branch, the keypress gate, and the untouched crash path. Suites: harness + spawn-worktree 169/169, message-pacing + seed-kick 22/22, full package suite 3802 passed / 48 skipped; build clean.

Live verification (kimi 0.29.1, tmux PTY, the actual bare launch script generated from built dist):

• /quit in the TUI → exit 0 → Agent exited at your request. Press Enter to relaunch… — gate held with no respawn (observed >10s); pressing Enter relaunched the TUI via continue.
• SIGKILL on the kimi-code process → Agent exited (code 137). Restarting in 2 seconds… → auto-restarted, TUI back up.

CMAP results (gemini, codex, claude — parallel review of the merge-resolution + adoption change set; clean in one iteration):

Model	Verdict	Findings
gemini	APPROVE	none — confirmed status=$? placement, read -r || exit 0 EOF semantics, all three Kimi shapes converted, no import cycle
codex	APPROVE	none — no remaining blind-restart Kimi loop; test coverage adequate across generic + provider shapes
claude	APPROVE	none — grep-verified the only sleep 2/restart echo in production code is inside LAUNCH_LOOP_TAIL's crash branch, across all 8 interpolation sites; template-literal $status/$SID interpolation safe

Ready for merge whenever you are.

[waleedkadous]

Heads-up on the exit-handling contract I asked this PR to adopt — it just evolved, and I want you building against the current state rather than the deprecated one.

• PR [Bugfix #1241] Auto-restart only on unnatural exits — a deliberate quit ends cleanly #1244's isDeliberateExit semantics (clean exit → session ends dead) turned out to be wrong for architect terminals and were replaced in PR [Bugfix #1264] A clean harness exit reruns fresh instead of killing the session #1266 (issue Regression (3.2.4): double Ctrl-C on an agent no longer restarts it fresh — classified as deliberate quit #1264): for architect sessions, any clean exit now keeps the shellper/session alive and reruns the harness fresh (new conversation, no --resume); crashes still restart with recovery.
• Builder launch loops — which is what this PR's Kimi support runs as — are unchanged for now: clean exit still Enter-gates the relaunch per [Bugfix #1241] Auto-restart only on unnatural exits — a deliberate quit ends cleanly #1244. That half of the new spec is tracked in Builder launch loop: clean-exit relaunch should rerun the harness fresh (no --resume), matching architect semantics from #1264 #1267 and hasn't been designed yet.

Practical upshot for this PR: mirror the current builder bash-loop behavior (Enter-gated relaunch on clean exit, auto-restart on crash) rather than the architect-side contract, and keep an eye on #1267 — when it lands, Kimi loops should move with it. Happy to review again whenever you've iterated!

[mohidmakhdoomi]

Will wait for #1267 to be completed before updating this PR. Also once #1330 is merged to main, will need to update this PR to have Kimi work with the new afx send mailbox delivery.