Crafter.Review/interfaces/Crafter.Review-Pool.cppm

// SPDX-License-Identifier: AGPL-3.0-only
// SPDX-FileCopyrightText: Copyright (C) 2026 Catcrafts®

export module Crafter.Review:Pool;
import std;
import :Json;
import :SeatPool;
import :Memory;
import :PgWire;

// One `claude --print` process per pass, a pool with gating, retries,
// rate-window pauses and progress; with seats every process runs on the seat
// picked for it and a seat's limit pauses that seat, not the pool. What else
// holds a launch back is the pass's environment, never its lens (Admission):
// a pass that drives an application waits for a stack of its own (Stacks),
// and every pass waits until it fits in free memory at its environment's
// measured cost. A pass with the database alone shares the first stack:
// every SQL call is its own transaction, rolled back.
//
// Every pass runs under the supervisor (`crafter-review __supervise`), so a
// timeout, an abort or the driver's death takes its whole tree down - the
// MCP server and Chromium with it.
export namespace Crafter::Review::Pool {
    using Log = std::function<void(const std::string&)>;
    // (status, reason)
    using Verdict = std::pair<std::string, std::string>;

    // seats.find_claude_bin
    std::string DefaultBin();
    // The exact Bash prefix a lens with the database under test runs SQL with:
    // this binary's `sql`, spelled absolute (allowlisted as a prefix).
    std::string SqlCommand();
    // The exact Bash line a lens with an application under test runs for a
    // one-time code: this binary's `totp <fixture>`; nullopt without one.
    std::optional<std::string> TotpCommand(const std::optional<std::string>& fixture);
    // Trees outside the working directory: the CLI must be told (--add-dir)
    // and Read allowed there, because --setting-sources '' drops the
    // project's additionalDirectories and a read there would prompt.
    std::vector<std::string> ExtraDirs(std::span<const std::string> trees);
    // A pass with the browser that returned ok, fail closed: the Playwright
    // server connected with its tools (2026-10-15: --safe-mode had dropped it
    // and four units came back n/a), and the browser answered - an empirical
    // lens's whole pass must have called it, and no pass may have had every
    // browser call fail.
    Verdict McpConnected(const Json& parsed, std::string_view kind = "block", bool empirical = true);
    // A pass that ran the SQL helper and never got the database's answer had
    // no database: its verdict is not evidence from one.
    Verdict DbAnswered(const Json& parsed, std::string_view kind = "block", bool empirical = false);
    // Every instrument the environment gives must show it was there.
    Verdict Exercised(const Json& parsed, std::string_view environment, std::string_view kind = "block", bool empirical = false);
    // A stack's name on the board, the same in every driver: its
    // application's address, localhost and 127.0.0.1 one host, a default port
    // spelled out; a stack without a URL is its id.
    std::string StackKey(const Json& stack);
    // The read-only tools, git -C on every tree in both spellings, and what
    // the environment adds: the browser tools and curl, the SQL helper, and
    // with an application the one-time-code command and the config's extras.
    std::vector<std::string> AllowedTools(std::string_view lensFile, std::string_view kind, std::span<const std::string> trees, std::span<const std::string> extra = {},
                                          const std::optional<std::string>& loginFixture = std::nullopt, std::string_view environment = "none");

    // The stacks a run's passes use (2026-10-22): the one the config names,
    // or the slots brought up side by side. A pass whose environment drives an
    // application holds a stack of its own from launch to end, least recently
    // returned first; another driver's pass holds one too (`held`, the
    // StackKey of every stack the other drivers on this machine hold).
    class Stacks {
    public:
        explicit Stacks(std::vector<Json> stacks);
        std::size_t Size() const;
        // nullptr when there is none.
        const Json* First() const;
        const std::vector<Json>& All() const;
        const std::string& KeyOf(const std::string& id) const;
        // Is a stack free (prefer: the one a resumed session ran on - only
        // that one will do)?
        bool Can(const std::optional<std::string>& prefer = std::nullopt, const std::set<std::string>& held = {}) const;
        Json Take(const std::optional<std::string>& prefer = std::nullopt, const std::set<std::string>& held = {});
        void Give(const std::string& id);
        std::vector<std::string> Free() const;

    private:
        std::vector<Json> all;
        std::map<std::string, std::string> keys;
        std::vector<std::string> free;
        mutable std::mutex lock;
    };

    // May the pool launch this pass now? No per-lens number (2026-10-22): an
    // environment that drives an application needs a stack of its own, and the
    // pass must fit the memory budget - free memory at the gate's start less
    // the reserve, less what the passes in flight were admitted at - with the
    // machine still holding its cost free beyond the reserve right now. With
    // nothing in flight on the machine a pass is admitted whatever the memory
    // says, and the log says so once. `others` is what the other drivers'
    // passes hold, as the board's last fold left it.
    class Admission {
    public:
        using CostOf = std::function<double(const Json& job)>;
        using NeedsStack = std::function<bool(const Json& job)>;
        using Available = std::function<std::optional<double>()>;
        Admission(CostOf costOf, NeedsStack needsStack, Stacks* stacks = nullptr, std::optional<double> budget = std::nullopt, double reserve = 0, Available available = {}, Log log = {});
        bool Can(const Json& job);
        // The pass's memory and its stack taken: _admitted, stack, prevStack
        // and stackKey on the job.
        void Take(Json& job);
        void Give(Json& job);
        void SetOthers(SeatPool::Others others);
        SeatPool::Others OthersNow() const;
        std::int64_t Inflight() const;
        double Held() const;

    private:
        CostOf costOf;
        NeedsStack needsStack;
        Stacks* stacks;
        std::optional<double> budget;
        double reserve;
        Available available;
        Log log;
        std::int64_t inflight = 0;
        double held = 0;
        bool warned = false;
        SeatPool::Others others;
        mutable std::mutex lock;
        std::optional<std::string> Prefer(const Json& job) const;
    };

    struct RunnerOptions {
        std::filesystem::path repo;
        std::filesystem::path scratch;
        // "": REVIEW_GATES_CLAUDE_BIN, else DefaultBin().
        std::string bin;
        std::string effort = "xhigh";
        Log log;
        bool dryRun = false;
        std::string harness = "claude";
        std::optional<std::string> variant;
        std::string opencodeBin;
        // The config's functional section: the MCP server, the extra tools.
        Json functional = Json::object();
        std::optional<std::string> loginFixture;
        // {lens file: environment}
        std::map<std::string, std::string> environments;
        // The first stack's: a pass with the database alone runs there.
        std::optional<std::string> dbUrl;
        Memory::Sampler* sampler = nullptr;
        // The database URLs stay in the driver; a db pass gets the broker's
        // address and a token.
        PgWire::Broker* broker = nullptr;
    };

    class Runner {
    public:
        explicit Runner(RunnerOptions options);
        // Every running pass stopped (its supervisor takes the tree down); how
        // many.
        std::int32_t KillChildren();
        std::string EnvOf(const Json& job) const;
        // A pass's process environment: the seat's (base), plus - when its
        // environment reaches the database - the broker's address and the
        // token of the database of the stack it holds (none for a stack
        // without one), else the run's first stack's.
        std::map<std::string, std::string> ProcessEnv(const Json& job, const std::map<std::string, std::string>& base) const;
        // The login fixture of the stack it holds, else the run's.
        std::optional<std::string> LoginOf(const Json& job) const;
        // The --mcp-config of a pass, nullopt for an environment without the
        // browser.
        std::optional<std::string> McpConfig(const Json& job) const;
        std::vector<std::string> Cmd(const Json& job, const std::filesystem::path& systemPath, std::string_view schema, std::span<const std::string> trees, std::int64_t maxTurns, bool persist,
                                     const std::string& sessionId, bool resume = false) const;
        // One pass: (record, the structured output or null).
        std::pair<Json, Json> Run(const Json& job, const std::string& prompt, const std::filesystem::path& systemPath, std::string_view schema, std::span<const std::string> trees,
                                  std::int64_t maxTurns, std::int64_t timeoutMin, bool persist = false);
        // The seats a job's `seat` names, as they were when the pool began:
        // only what never changes (id, kind, secret) is read from them.
        void SetSeats(const std::vector<Json>& seats);
        const std::string& Bin() const;
        // The environment every pass starts from.
        std::map<std::string, std::string>& Env();
        const std::filesystem::path& Scratch() const;
        std::filesystem::path opencodeHome;

    private:
        RunnerOptions options;
        std::map<std::string, std::string> env;
        std::map<std::string, Json> seatsById;
        std::map<std::int64_t, bool> running;
        mutable std::mutex lock;
        std::pair<Json, Json> RunOpenCode(const Json& job, const std::string& prompt, const std::filesystem::path& systemPath, std::span<const std::string> trees, std::int64_t timeoutMin,
                                          const Json& seat, Json rec, const std::filesystem::path& out, const std::filesystem::path& err, const std::string& sessionId);
        std::optional<std::int32_t> Wait(std::int64_t pid, std::int64_t timeoutMin, bool& timedOut);
    };

    struct SchedulerOptions {
        Runner* runner = nullptr;
        std::int64_t concurrency = 8;
        Log log;
        std::optional<std::filesystem::path> progressPath;
        double pauseAt = 85;
        double maxWaitMin = 360;
        // The key of a pass's prompt prefix (nullopt: none), which the driver
        // keeps on the job as `cacheKey`; and whether a running pass's first
        // response is in.
        std::function<std::optional<std::string>(Json& job)> cacheKey;
        std::function<bool(const Json& job)> warmProbe;
        double warmTtl = 240;
        double warmTimeout = 180;
        double warmPoll = 5;
        std::vector<Json>* seats = nullptr;
        // null: from the environment.
        Json seatConfig;
        Json apiConfig;
        SeatPool::Ledger* ledger = nullptr;
        std::function<double()> now;
        Admission* admission = nullptr;
        SeatPool::Board* board = nullptr;
        double noRoomWait = 30;
        // A stop that came before this pool (a signal, `crafter-review stop`):
        // the pool starts aborted.
        std::optional<std::string> abort;
    };

    struct Done {
        Json job;
        Json rec;
        Json raw;
    };

    // Runs jobs on a pool; onDone(job, rec, raw) -> the follow-up jobs (the
    // blocks after a passing whole pass). Retries: error/timeout once (x1.5
    // budget for a timeout); limit -> pause until resetsAt (or a backoff) and
    // requeue (<= 4); auth or a seven_day rejection -> abort. With seats every
    // launch is placed (with the board: placed, admitted and registered under
    // its lock, the pool width the machine's cap), every finished process
    // settled onto its seat and taken off the board. One thread per pass.
    class Scheduler {
    public:
        using ExecJob = std::function<std::pair<Json, Json>(const Json& job, std::int64_t attempt)>;
        using OnDone = std::function<std::vector<Json>(const Json& job, const Json& rec, const Json& raw)>;
        explicit Scheduler(SchedulerOptions options);
        const std::vector<Done>& Run(std::vector<Json> jobs, const ExecJob& exec, const OnDone& onDone);
        // From any thread: the pool stops launching and returns once what runs
        // has ended.
        void Abort(const std::string& reason);
        std::optional<std::string> Aborted() const;
        const std::vector<Done>& DoneList() const;
        // pause_until: 0 until a pause raised it.
        Json PauseUntil() const;

    private:
        SchedulerOptions o;
        std::vector<Done> done;
        std::optional<std::string> abort;
        Json pauseUntil = 0;
        Json roomWait;
        double waitedMin = 0;
        bool heldOff = false;
        std::map<std::pair<std::string, std::string>, double> warm;
        std::map<std::pair<std::string, std::string>, std::pair<std::string, double>> warming;
        mutable std::mutex lock;
        std::condition_variable wake;
        bool Capped(const Json& job);
        bool Launchable(Json& job, const std::vector<Json*>& running, double now, const std::optional<std::string>& seatId);
        void RaisePause(double until);
        void Sleep(double seconds);
        void Progress(const std::vector<std::string>& running, const std::vector<std::string>& queued);
        void Log(const std::string& line) const;
    };
}