(* The agent, end to end (NEXT.md, dev loop step 3). test_reload.ml proves the primitive with a C harness driving it. This one proves the thing the dev loop actually is: a program that is running its own loop, a redefinition arriving over a socket while it runs, and the swap becoming visible at a point the program chose. The split the agent exists for is between two threads. [dlopen] relocates a module and takes the loader lock — milliseconds, unbounded — so it happens on the listener thread. [flan_reload_install] is one store per function, and it must not land while a redefined function is on the stack, so it happens on the game thread when it asks. Everything here is arranged to make that observable rather than to make it fast. *) open Flan (* The watchdog first: a hang is the one failure mode that reports nothing at all. See watchdog.ml. *) let () = Watchdog.arm ~seconds:600 "test_agent" let failures = ref 0 let fail fmt = Printf.ksprintf (fun s -> incr failures; print_endline ("FAIL " ^ s)) fmt let scratch = Filename.get_temp_dir_name () let tmp name = Filename.concat scratch ("flan-agent-" ^ name) (* Poll for a condition rather than sleeping a fixed time: the program has to bind its socket before there is anything to connect to, and how long that takes is not ours to predict. *) let rec await ?(ms = 3000) f = if f () then true else if ms <= 0 then false else begin ignore (Unix.select [] [] [] 0.005); await ~ms:(ms - 5) f end (* The socket file appears at [bind], which is a moment before [listen], so a connect can lose that race and get ECONNREFUSED. Retry rather than sleep. *) let rec connect ?(ms = 2000) path = let s = Unix.socket Unix.PF_UNIX Unix.SOCK_STREAM 0 in match Unix.connect s (Unix.ADDR_UNIX path) with | () -> s | exception Unix.Unix_error (Unix.ECONNREFUSED, _, _) when ms > 0 -> Unix.close s; ignore (Unix.select [] [] [] 0.005); connect ~ms:(ms - 5) path let send path line = let s = connect path in let msg = line ^ "\n" in ignore (Unix.write_substring s msg 0 (String.length msg)); (* Read to EOF, not once: a reply arrives in several pieces, and closing after the first one is what made the agent take SIGPIPE. *) let buf = Bytes.create 512 in let b = Buffer.create 512 in let rec drain () = match Unix.read s buf 0 512 with | 0 -> () | n -> Buffer.add_subbytes b buf 0 n; drain () | exception Unix.Unix_error _ -> () in drain (); Unix.close s; Buffer.contents b let () = match Sys.command "command -v clang > /dev/null 2>&1 && command -v llc > /dev/null 2>&1" with | 0 -> (* The session is the program the process is about to be built from. Going through it rather than calling Emit directly is the point: it is what knows [tick] is a name the host has, so the module binds to its cell as a symbol instead of inventing a registry entry nobody publishes. *) let t, l = Session.create ~file:"programs/agent.flan" () in (* A dev build, because that is what has cells to install into and exports them. The agent's own C and its -lpthread come from the package. *) let dev = { Build.default with Build.dev = true } in let exe = tmp "prog" in ignore (Build.executable ~opts:dev ~csrcs:l.Load.csrcs ~lflags:l.Load.lflags t.Session.host ~out:exe); (* And the same program without [--dev], which has to *link*. Its [main] calls [agent/start], so the package is reached and its C comes with it even through [Reach.link] — and that C refers to the dev runtime, so leaving it out made this an undefined symbol at the link rather than a missing flag. Nothing is run: with no cells the agent refuses every module, and linking is the whole claim. *) (match let p, csrcs, lflags = Reach.link l t.Session.host in Build.executable ~opts:Build.default ~csrcs ~lflags p ~out:(tmp "prog-release") with | _ -> () | exception Failure m -> fail "a release build of the agent: %s" m); (* Two evaluations from the one session, which is the daemon's loop and the thing no earlier test does. The first introduces a global the process was never built with; the second only reads it, and can only come back with 1007 if it found the storage the first one allocated rather than a fresh zeroed copy of it. *) let build_module src name = let c = Session.eval t src in let out = tmp name in ignore (Build.shared ~opts:dev ~ir:c.Session.ir ~out ()); out in let so1 = build_module "(defvar acc i64) (defn tick [] i64 (set acc (+ acc 1000)) acc)" "tick1.so" in let so2 = build_module "(defn tick [] i64 (set acc (+ acc 7)) acc)" "tick2.so" in let sock = tmp "sock" in let out = tmp "out" in (try Sys.remove sock with Sys_error _ -> ()); let fd = Unix.openfile out [ Unix.O_WRONLY; Unix.O_CREAT; Unix.O_TRUNC ] 0o600 in let pid = Unix.create_process exe [| exe; sock |] Unix.stdin fd Unix.stderr in Unix.close fd; if not (await (fun () -> Sys.file_exists sock)) then begin fail "the program never bound its socket"; (try Unix.kill pid Sys.sigkill with Unix.Unix_error _ -> ()) end else begin (* Refusing junk comes first, while the program is still running: the daemon is a separate process and can send anything, and a bad path must not take down the program it was sent to. Nothing is queued by it, so the program is still waiting afterwards. *) let reply = send sock "/nonexistent/nope.so" in if String.length reply < 4 || String.sub reply 0 4 <> "err " then fail "a bad path was not refused: %S" reply; (* "ok" means queued, not installed — the store happens on the other thread, at a time this one does not choose. *) let lines () = let text = In_channel.with_open_bin out In_channel.input_all in List.length (String.split_on_char '\n' text) - 1 in let reply = send sock so1 in if reply <> "ok\n" then fail "agent replied %S, wanted \"ok\\n\"" reply; (* Wait for the program to have consumed the first module before sending the second. Both at once is a legitimate thing for the agent to do — one poll installs everything queued — but then only the last one is ever observed and the sequencing is not what was tested. *) if not (await (fun () -> lines () >= 2)) then fail "the first reload was never installed"; let reply = send sock so2 in if reply <> "ok\n" then fail "agent replied %S, wanted \"ok\\n\"" reply; let _, status = Unix.waitpid [] pid in let text = In_channel.with_open_bin out In_channel.input_all in (* 1 from the original [tick]; 1000 from a body that did not exist when the program started, over a global that did not either; 1007 from a second body that only reads it. That last number is the whole point of doing this twice — a registry that handed out fresh storage per module would say 7. *) if status <> Unix.WEXITED 0 || text <> "1\n1000\n1007\n" then fail "agent reload\n got: %S (%s)\n wanted: %S" text (match status with | Unix.WEXITED c -> Printf.sprintf "exit %d" c | Unix.WSIGNALED c -> Printf.sprintf "signal %d" c | Unix.WSTOPPED c -> Printf.sprintf "stopped %d" c) "1\n1000\n1007\n" end; (* ── The break loop, spec-conditions.md §2 ──────────────────────── *) (* The claim is that an unhandled [error] stops rather than dying, and can be resumed into a restart chosen from outside. A program that died would exit 134 with no output; one that stopped and was never resumed would hang and be killed by the timeout. Only a resume produces both numbers, and they differ, so a loop that always took the same restart fails. *) let bsock = tmp "break.sock" and bout = tmp "break.out" in (try Sys.remove bsock with Sys_error _ -> ()); let bt, bl = Session.create ~file:"programs/break.flan" () in let bexe = tmp "break" in ignore (Build.executable ~opts:dev ~csrcs:bl.Load.csrcs ~lflags:bl.Load.lflags bt.Session.host ~out:bexe); let bfd = Unix.openfile bout [ Unix.O_WRONLY; Unix.O_CREAT; Unix.O_TRUNC ] 0o600 in let env = Array.append (Unix.environment ()) [| "FLAN_AGENT_SOCKET=" ^ bsock |] in let bpid = Unix.create_process_env bexe [| bexe |] env Unix.stdin bfd bfd in Unix.close bfd; if not (await (fun () -> Sys.file_exists bsock)) then fail "the broken program never listened" else begin (* It has to be *stopped* before the restarts are knowable: the listener refuses to walk a stack the game thread is still running on. *) let listed = ref "" in if not (await (fun () -> listed := send bsock "restarts"; !listed <> "" && not (String.length !listed >= 3 && String.sub !listed 0 3 = "err"))) then fail "the program never reached the break loop: %S" !listed else begin (* Innermost first, and both on offer. *) if !listed <> "0 + retry\n1 + use-placeholder\n.\n" then fail "restarts on offer\n got: %S\n wanted: %S" !listed "0 + retry\n1 + use-placeholder\n.\n"; (* A name nothing offers is refused *here*, before the reply. Answering ok and discovering it on the game thread would report success for something that cannot happen. *) let bad = send bsock "restart nonesuch" in if not (String.length bad >= 3 && String.sub bad 0 3 = "err") then fail "a restart nobody offers was accepted: %S" bad; ignore (send bsock "restart retry"); (* Wait for the *result* of that choice before making the next one. Asking whether it is stopped is not enough: it is still stopped in the first break until the resume lands, and a second choice sent then would be taken by the first one — which passes the listing check and then hangs, because the second break never gets an answer. The printed 7 is the only proof the first resume happened. *) let printed () = let t = In_channel.with_open_bin bout In_channel.input_all in List.exists (String.equal "7") (String.split_on_char '\n' t) in if not (await printed) then fail "the first restart never produced its value" else if not (await (fun () -> send bsock "restarts" = "0 + retry\n1 + use-placeholder\n.\n")) then fail "the program never stopped a second time" else begin ignore (send bsock "restart use-placeholder"); (* -- Taking a restart by index ------------------------------- *) (* The third break is inside a [restart-case] whose name the frame below it also offers. Both are listed; §4's by-name walk can only ever reach the first. So this takes the *second*, and 900 is a value nothing else in the program can produce — the assertion on the output at the end is what makes this test about shadowing rather than about a reply. *) let printed2 () = let t = In_channel.with_open_bin bout In_channel.input_all in List.exists (String.equal "-1") (String.split_on_char '\n' t) in if not (await printed2) then fail "the second restart never produced its value" else if not (await (fun () -> send bsock "restarts" = "0 + retry\n1 + retry\n.\n")) then fail "the program never stopped on the shadowed pair" else begin (* Out of range is refused before the reply, like a bad name. *) let oob = send bsock "restart-at 7" in if not (String.length oob >= 3 && String.sub oob 0 3 = "err") then fail "an index nothing offers was accepted: %S" oob; (* The name rides along as a receipt, not as the lookup: an index whose name has moved is refused rather than silently taken, which is the same failure by-name lookup had. *) let drift = send bsock "restart-at 1 use-placeholder" in if not (String.length drift >= 3 && String.sub drift 0 3 = "err") then fail "an index whose name had drifted was accepted: %S" drift; ignore (send bsock "restart-at 1 retry") end end end end; let bstatus = ref (Unix.WEXITED 0) in let reaped = await ~ms:5000 (fun () -> match Unix.waitpid [ Unix.WNOHANG ] bpid with | 0, _ -> false | _, s -> bstatus := s; true) in if not reaped then begin (try Unix.kill bpid Sys.sigkill with Unix.Unix_error _ -> ()); fail "the program never resumed out of the break loop" end else begin let text = In_channel.with_open_bin bout In_channel.input_all in let want = "7\n-1\n900\n" in let got = String.concat "\n" (List.filter (fun l -> l <> "" && not (String.length l >= 5 && String.sub l 0 5 = "flan:") && not (String.length l >= 2 && String.sub l 0 2 = " ")) (String.split_on_char '\n' text)) in if !bstatus <> Unix.WEXITED 0 || got ^ "\n" <> want then fail "break loop transcript\n got: %S\n wanted: %S" got want end; (* ── The job ring, and what a full one does ─────────────────────── *) (* Two claims, one program. A module the agent refuses because it carries no installer is *closed* rather than leaked; and a ring with no room refuses the module instead of overwriting the slot the game thread is reading. The program blocks on stdin until the test has finished filling the ring, so neither claim is a race against how fast sixty-five connections are served. *) let qsock = tmp "queue.sock" and qout = tmp "queue.out" in (try Sys.remove qsock with Sys_error _ -> ()); let qt, ql = Session.create ~file:"programs/agent-queue.flan" () in let qexe = tmp "queue" in ignore (Build.executable ~opts:dev ~csrcs:ql.Load.csrcs ~lflags:ql.Load.lflags qt.Session.host ~out:qexe); (* One module, sent many times. dlopen keys on the path, so this is the same relocation over and over — what is being counted is publishes, and building sixty-five of them would measure llc instead. *) let qso = tmp "queue-tick.so" in let qc = Session.eval qt "(defn tick [] i64 (set ticks (+ ticks 1)) ticks)" in ignore (Build.shared ~opts:dev ~ir:qc.Session.ir ~out:qso ()); let noinstall = tmp "noinstall.so" in let cc = Printf.sprintf "clang -shared -fPIC -o %s noinstall.c 2>/dev/null" (Filename.quote noinstall) in if Sys.command cc <> 0 then fail "could not build noinstall.so" else begin (* Close-on-exec, or the child inherits the write end and its own stdin never reaches end of file: the program would sit in its last read waiting for a byte only it could send. The read end is dup'd onto fd 0 by [create_process], which clears the flag on the copy. *) let rfd, wfd = Unix.pipe ~cloexec:true () in let qfd = Unix.openfile qout [ Unix.O_WRONLY; Unix.O_CREAT; Unix.O_TRUNC ] 0o600 in let qpid = Unix.create_process qexe [| qexe; qsock |] rfd qfd qfd in Unix.close qfd; Unix.close rfd; let qtext () = In_channel.with_open_bin qout In_channel.input_all in let has needle = let t = qtext () in List.exists (String.equal needle) (String.split_on_char '\n' t) in if not (await (fun () -> Sys.file_exists qsock && has "ready")) then begin fail "the queue program never bound its socket"; (try Unix.kill qpid Sys.sigkill with Unix.Unix_error _ -> ()) end else begin (* A module with no installer. The refusal was always there; what is new is that the handle is closed, and the destructor saying so *while the program is still running* is the only way to see it — at exit the loader would run it either way. *) let r = send qsock noinstall in if r <> "err no flan_reload_install\n" then fail "a module with no installer: %S" r; if not (await (fun () -> has "unloaded")) then fail "the refused module was not closed: %S" (qtext ()); (* QUEUE slots, then one more. The one more is refused, at the sender, with a reason — the old code took it, wrote it over slot 0, and said ok. *) let queue_size = 64 in let bad = ref "" in for _ = 1 to queue_size do let r = send qsock qso in if r <> "ok\n" && !bad = "" then bad := r done; if !bad <> "" then fail "a module that fitted was refused: %S" !bad; let full = send qsock qso in if full <> "err reload queue full; the program is not calling agent/poll\n" then fail "a full ring did not refuse: %S" full; (* Let it poll. Every slot the ring kept is installed here, so the number is how many survived — 64, not 65 and not some torn count. *) ignore (Unix.write wfd (Bytes.of_string "\n") 0 1); if not (await (fun () -> has "64")) then fail "the ring never drained: %S" (qtext ()) else begin (* ── The 4K result cap ─────────────────────────────────────── NEXT.md names this buffer twice as having no coverage at all, because it is on the agent's path and so needs a socket. There is a socket here. The value is a 5000-byte string literal, which is longer than anything [emit] will keep, so what comes back is the clamp and the ellipsis [result_end] puts there to say it clamped — and it comes back through the seqlock's copy rather than off a borrowed pointer. *) let long = String.make 5000 'x' in let ec = Session.eval_expr qt ("\"" ^ long ^ "\"") in let eso = tmp "queue-eval.so" in ignore (Build.shared ~opts:dev ~ir:ec.Session.ir ~out:eso ()); (* ── A stopped-only job that reaches a running program ──────── The [reg at] TOCTOU, pinned at the one place it can be pinned deterministically. In the daemon it is a race: [inspect] by address checks that the program is stopped, spends a third of a second building a thunk with that address baked in, and a [restart] landing in the window resumes the game thread before the thunk runs. Reproducing *that* means winning a race against llc. What the fix actually turns on does not need the race at all — a job tagged stopped-only, arriving at a frame boundary with no break in force, must be dropped — and this program is never stopped, so "no break in force" is not something to arrange. It is also the A/B, in one program at one moment, which is why it sits beside the eval module rather than in a block of its own. Two jobs are queued back to back: the same [tick] module the ring above installed sixty-four times, now sent stopped-only, and the eval module sent plainly. The program polls once and prints how many it installed. One. Without the flag it is two, and the two deliveries differ in nothing but the word in front of the path. *) let refusals_before = send qsock "refusals" in let s = send qsock ("stopped-only " ^ qso) in if s <> "ok\n" then fail "a stopped-only module was not queued: %S" s; let r = send qsock eso in if r <> "ok\n" then fail "the eval module was not queued: %S" r; ignore (Unix.write wfd (Bytes.of_string "\n") 0 1); if not (await (fun () -> has "1")) then fail "the eval thunk never ran: %S" (qtext ()) else begin let reply = send qsock "result" in match String.index_opt reply '\n' with | None -> fail "no result header: %S" reply | Some i -> let hdr = String.sub reply 0 i in let body = String.sub reply (i + 1) (String.length reply - i - 1) in (* Exactly the cap, ellipsis included: [result_end] makes room for it rather than assuming there is any. *) if String.length body <> 4096 then fail "the 4K result cap: %d bytes back, header %S" (String.length body) hdr; let tail n = if String.length body < n then body else String.sub body (String.length body - n) n in let head n = if String.length body < n then body else String.sub body 0 n in if tail 3 <> "..." then fail "a clamped result did not say so: %S" (tail 8); if head 2 <> "\"x" then fail "the result is not the value that was rendered: %S" (head 8) end; (* And the program says so, because a job that vanishes quietly is the same lie the ring's dropped-oldest was. The count is what the daemon compares either side of a delivery; the sentence is what it puts in front of the person, and it lives here so that there is one copy of it. *) let refusals_after = send qsock "refusals" in let count r = match String.index_opt r '\n' with | None -> None | Some i -> int_of_string_opt (String.sub r 0 i) in (match (count refusals_before, count refusals_after) with | Some b, Some a when a = b + 1 -> () | _ -> fail "a dropped stopped-only job was not counted: %S then %S" refusals_before refusals_after); let wanted = "the program resumed while this inspection was being built — \ stop it again and re-ask" in (match String.index_opt refusals_after '\n' with | Some i when String.trim (String.sub refusals_after (i + 1) (String.length refusals_after - i - 1)) = wanted -> () | _ -> fail "the refusal does not say why: %S" refusals_after); (try Sys.remove eso with Sys_error _ -> ()) end; Unix.close wfd; let qstatus = ref (Unix.WEXITED 0) in let reaped = await ~ms:5000 (fun () -> match Unix.waitpid [ Unix.WNOHANG ] qpid with | 0, _ -> false | _, s -> qstatus := s; true) in if not reaped then begin (try Unix.kill qpid Sys.sigkill with Unix.Unix_error _ -> ()); fail "the queue program never finished" end else begin let got = String.concat "\n" (List.filter (fun l -> l <> "") (String.split_on_char '\n' (qtext ()))) in if !qstatus <> Unix.WEXITED 0 || got <> "ready\nunloaded\n64\n1" then fail "job ring\n got: %S\n wanted: %S" got "ready\nunloaded\n64\n1" end end end; (* ── condition_name[128] ────────────────────────────────────────── *) (* The other named buffer with no coverage at all, and it needs a socket for the same reason: nothing but [status] ever reads it. The condition class is 198 characters, so what comes back is the 127 that fit and a terminator — a clamp, not an overrun, and now measured rather than read. Aborting out of it also pins that the break loop's way out is still exit status 134 now that it takes it with _exit. *) let lsock = tmp "long.sock" and lout = tmp "long.out" in (try Sys.remove lsock with Sys_error _ -> ()); let lt, ll = Session.create ~file:"programs/agent-longname.flan" () in let lexe = tmp "long" in ignore (Build.executable ~opts:dev ~csrcs:ll.Load.csrcs ~lflags:ll.Load.lflags lt.Session.host ~out:lexe); let lfd = Unix.openfile lout [ Unix.O_WRONLY; Unix.O_CREAT; Unix.O_TRUNC ] 0o600 in let lenv = Array.append (Unix.environment ()) [| "FLAN_AGENT_SOCKET=" ^ lsock |] in let lpid = Unix.create_process_env lexe [| lexe |] lenv Unix.stdin lfd lfd in Unix.close lfd; let stopped = ref "" in if not (await (fun () -> Sys.file_exists lsock && (stopped := send lsock "status"; String.length !stopped > 8 && String.sub !stopped 0 8 = "stopped "))) then begin fail "the long-named condition never stopped: %S" !stopped; (try Unix.kill lpid Sys.sigkill with Unix.Unix_error _ -> ()) end else begin let got = String.trim (String.sub !stopped 8 (String.length !stopped - 8)) in if String.length got <> 127 then fail "condition_name clamps at 127: got %d characters" (String.length got); if String.length got >= 7 && String.sub got 0 7 <> "Missing" then fail "the clamped name is not the condition's: %S" got; ignore (send lsock "abort"); let lstatus = ref (Unix.WEXITED 0) in let reaped = await ~ms:5000 (fun () -> match Unix.waitpid [ Unix.WNOHANG ] lpid with | 0, _ -> false | _, s -> lstatus := s; true) in if not reaped then begin (try Unix.kill lpid Sys.sigkill with Unix.Unix_error _ -> ()); fail "abort did not end the program" end else if !lstatus <> Unix.WEXITED 134 then fail "abort left status %s, wanted exit 134" (match !lstatus with | Unix.WEXITED c -> Printf.sprintf "exit %d" c | Unix.WSIGNALED c -> Printf.sprintf "signal %d" c | Unix.WSTOPPED c -> Printf.sprintf "stopped %d" c) end; List.iter (fun f -> try Sys.remove f with Sys_error _ -> ()) [ exe; so1; so2; sock; out; bsock; bout; bexe; qexe; qso; qsock; qout; noinstall; lexe; lsock; lout ]; if !failures = 0 then print_endline "agent: all tests passed" else begin Printf.printf "\n%d failure(s)\n" !failures; exit 1 end | _ -> print_endline "agent: skipped (no clang or llc on PATH)"