@rse/ase 2.0.2 → 2.0.4

package/dst/man/ase-agent-qualifier.md

@@ -0,0 +1,426 @@
+# ase-agent-qualifier(1) -- Qualification Phase Agent
+
+## SYNOPSIS
+
+`ase agent qualifier start`
+\[`-n`|`--name` *name*\]
+\[`-t`|`--tool` `claude`|`copilot`|`codex`\]
+\[`-p`|`--parallel` *num*\]
+\[`-T`|`--timeout` *duration*\]
+\[`-o`|`--one-shot`\]
+\[`--agent-relay` *url*\]
+\[`-r`|`--repo` *url*\]
+\[`-d`|`--tempdir` *dir*\]
+\[`-m`|`--mode` `judge`|`qualify`\]
+\[`--`*group*`-`*item* *value* \[...\]\]
+\[`-f`|`--foreground`\]
+
+`ase agent qualifier status`
+\[`-n`|`--name` *name*\]
+
+`ase agent qualifier log`
+\[`-f`|`--follow`\]
+\[`-n`|`--lines` *n*\]
+\[`--name` *name*\]
+
+`ase agent qualifier stop`
+\[`-n`|`--name` *name*\]
+
+## DESCRIPTION
+
+**ase agent qualifier** drives the `Qualification` phase of the
+`enterprise` task lifecycle model (refused for any other model).
+
+It claims every task in the state `IMPLEMENTED` which is unassigned or
+assigned to the agent, which does not carry any tag `ase-agent-qualifier`
+yet (i.e., without its verdict yet, so a task already carrying a
+verdict of the qualifier is never picked up again), and whose `After:`
+predecessors (and, for an explicit epic, its group members) are
+`QUALIFIED` or later, moves it into `QUALIFYING`, and reviews its
+`Changeset:` (or the configured `project.task.default.changeset`) via
+the skill `ase-repo-review`:
+
+- `worktree`: The change set staged in its working copy, i.e., the Git
+  worktree `.ase/worktree/`*id* of a parallel implementer if existing,
+  else the working copy of the project.
+
+- `branch:`*name*: The branch against its base, via `ase-repo-review
+  --branch` *name*.
+
+- `attachment:`*name*: The change set staged in a temporary Git
+  worktree, detached at the `base` commit of the attachment and removed
+  afterwards.
+
+The verdict `APPROVE` resp. `REJECT` of the review (the last upper-case
+word after the label `REVIEW VERDICT` in the output of the successfully
+exited agent tool) is added as the tag `ase-agent-qualifier:approve`
+resp. `ase-agent-qualifier:reject`, while a failed or skipped review,
+which yields no verdict, adds the plain tag `ase-agent-qualifier`.
+
+In the default mode `judge`, the task is then put back into `IMPLEMENTED`
+for a human decision, while in mode `qualify`, it is put into `QUALIFIED`
+on the verdict `APPROVE`, into `DECLINED` on the verdict `REJECT`, and
+back into `IMPLEMENTED` without a verdict. In both modes, the task is
+unassigned afterwards.
+
+On an interrupt, a task being processed is put back, untagged and with
+its previous assignee, into `IMPLEMENTED`. See `ase-agent`(1) for the
+common mechanics of all agents.
+
+## OPTIONS
+
+- \[`-h`|`--help`\]: Show usage information of `ase agent qualifier` (or
+  of the given sub-command) only.
+
+All other options belong to the sub-commands (see **COMMANDS**).
+
+## COMMANDS
+
+- `ase agent qualifier start` \[*options*\]: Start the qualifier agent in
+  the background, logging into `.ase/agent/`*name*`.log`. The agent is
+  validated and initialized (e.g., its agent tool is looked up and the
+  task lifecycle model is checked) before the command returns (waiting
+  up to 30 seconds), so a failing agent is reported together with the
+  tail of its log. An agent of the same name already running is left
+  alone. The options are:
+
+    - \[`-n`|`--name` *name*\]: The name of the agent (default:
+      `qualifier`): up to 64 letters, digits, underscores, and dashes,
+      starting with a letter or digit, other than the name of another
+      agent kind, `relay`, or `fleet`. It names the agent in its log
+      lines (also in the shared processing log attachment `agent`), the
+      `Assignee:` of the tasks it processes, its temporary directory,
+      and its process files `.ase/agent/`*name*`.yaml` and
+      `.ase/agent/`*name*`.log`.
+
+      Agents of the kind `qualifier` under different names form a pool,
+      competing for the same tasks and processing them in parallel to
+      each other.
+
+    - \[`-t`|`--tool` *tool*\]: The headless agent tool processing the
+      tasks: `claude` (*Anthropic Claude Code CLI*), `copilot` (*GitHub
+      Copilot CLI*), or `codex` (*OpenAI Codex CLI*) (default:
+      `$ASE_TOOL`, else `claude`). Its command has to be found in
+      `$PATH`.
+
+    - \[`-p`|`--parallel` *num*\]: The maximum number of tasks processed
+      in parallel by this agent (default: `1`), a positive integer.
+
+    - \[`-T`|`--timeout` *duration*\]: The maximum duration of
+      processing a task (the run of the agent tool), as *number* *unit*
+      (without a space) with *unit* `s` (seconds), `m` (minutes), or `h`
+      (hours) (default: `60m`). A processing exceeding it is aborted and
+      counts as failed.
+
+    - \[`-o`|`--one-shot`\]: Terminate the agent, instead of observing
+      for further tasks, once a check of the task store finds no
+      dispatchable task while the agent processes no task anymore --
+      intended for CI contexts like GitHub Actions, and not allowed in a
+      fleet. A task still waiting for its predecessors at that time is
+      left for a later run. A check of the task store failing three
+      times in a row then terminates the agent with a non-zero exit
+      status (instead of being retried endlessly after a growing delay).
+
+    - \[`--agent-relay` *url*\]: The agent relay to pass the live
+      presence of the agent to, as `ase://`*addr*`:`*port*\[`/`*token*\]
+      resp. `ases://`*addr*`:`*port*\[`/`*token*\]\[`?insecure`\] for
+      HTTPS (default: the configured `project.relay.url`, else none).
+      See **AGENT RELAY** in `ase-agent`(1).
+
+    - \[`-r`|`--repo` *url*\]: The Git repository to clone once into the
+      temporary directory of the agent, where every task without a
+      `worktree` value is processed in its own temporary Git worktree of
+      this clone, and changed branches are pushed back to its origin
+      (default: none, i.e., all tasks are processed in the Git working
+      copy the agent is started in, which is hence mandatory).
+
+      Requires a task store not located in the working copy (i.e., not a
+      local `ase:`*path* one). See **WORKING COPY, CLONES, AND WORKTREES**
+      in `ase-agent`(1).
+
+    - \[`-d`|`--tempdir` *dir*\]: Create the temporary directory of the
+      agent as the sub-directory *name* of *dir*, where `%p` is expanded
+      to the process id of the agent, `%h` to a hash value unique to the
+      process, and `%%` to `%` (default: a fresh, private directory
+      below the system temporary directory). A missing *dir* is created
+      private to the current user, while an existing *dir* has to be a
+      directory (no symbolic link) owned by the current user.
+
+    - \[`-m`|`--mode` *mode*\]: The mode of the agent (default:
+      `judge`): `judge` just adds the verdict tag and puts the task back
+      into `IMPLEMENTED` for a human decision, while `qualify`
+      additionally qualifies resp. declines the task by its verdict,
+      i.e., puts it into `QUALIFIED` on the verdict `APPROVE`, into
+      `DECLINED` on the verdict `REJECT`, and back into `IMPLEMENTED`
+      without a verdict. An invalid mode is an error.
+
+    - \[`--title` *text*\]: The one-line title of the operation of the
+      agent (at most 80 characters), shown on the task boards. Built-in:
+      `Review implemented tasks and tag their verdict` (`judge`) resp.
+      `Review implemented tasks and decide by verdict` (`qualify`).
+
+    - \[`--description` *text*\]: The brief description of the operation
+      of the agent (about 3-6 lines, at most 600 characters, with its
+      whitespace collapsed), shown on the task boards. Built-in: a
+      description of the operation of the mode.
+
+    - \[`--type` `phase`|`request`\]: The processing type: `phase`
+      claims the tasks by their lifecycle status, `request` processes
+      the prompt requests attached to the tasks. Generic default:
+      `phase`. Built-in: `phase`.
+
+    - \[`--workdir` *kind*\]: The working directory of the agent tool:
+      `project`, `source`, `changeset`, `changeset-read`, or `target`.
+      Generic default: `project`. Built-in: `changeset-read`.
+
+    - \[`--lifecycle` *model*\]: A supported task lifecycle model
+      (`solo`, `team`, or `enterprise`, repeatable). Generic default:
+      every model containing all given states, resp. all models for
+      `request` and with `--unclaimed`. Built-in: `enterprise`.
+
+    - \[`--serial`\]: Process the tasks serially only, ignoring
+      `--parallel`. Built-in: not set.
+
+    - \[`--unclaimed`\]: Process the tasks of the incoming states
+      without claiming them, independent of their assignee and
+      predecessors, and without ever changing their status and assignee
+      (`phase` only). Built-in: not set. Not allowed, as the qualifier
+      claims the tasks into its activity state.
+
+    - \[`--params` *name*`=`*value*\]: The value of a parameter
+      declared by the definition (repeatable). Built-in: none declared.
+
+    - \[`--state-incoming` *state*\]: The state of the tasks to claim
+      (mandatory for `phase`, repeatable with `--unclaimed` only).
+      Built-in: `IMPLEMENTED`.
+
+    - \[`--state-activity` *state*\]: The state of a task during its
+      processing. Generic default: the incoming state. Built-in:
+      `QUALIFYING`.
+
+    - \[`--state-success` *state*\]: The target state on success.
+      Generic default: the incoming state. Built-in: `IMPLEMENTED`.
+
+    - \[`--state-failure` *state*\]: The target state on failure.
+      Generic default: the incoming state. Built-in: `IMPLEMENTED`.
+
+    - \[`--state-phase` *state*\]: The phase success state, into which
+      the skill itself can move a task. Generic default: the success
+      state. Built-in: `QUALIFIED`.
+
+    - \[`--state-passed` *state*\]: The first state from which on a task
+      has passed the phase for its `After:` successors. Generic default:
+      the phase success state. Built-in: `QUALIFIED`.
+
+    - \[`--state-verdict` *VERDICT*`=`*state*\]: The target state per
+      verdict (repeatable). Built-in: not set (mode `judge`),
+      `APPROVE=QUALIFIED` and `REJECT=DECLINED` (mode `qualify`).
+
+    - \[`--tag-name` *tag*\]: The tag of the processed tasks
+      (`ase-agent-`*word*). Generic default: `ase-agent-`*name*, resp.
+      for `request` always `ase-agent-`*request-name*. Built-in:
+      `ase-agent-qualifier`.
+
+    - \[`--tag-success` *tag*\]: The tag on success: *tag-name*,
+      *tag-name*`:`*value*, or `none` (`phase` only). Generic default:
+      *tag-name*. Built-in: not set.
+
+    - \[`--tag-failure` *tag*\]: The tag on failure: *tag-name*,
+      *tag-name*`:`*value*, or `none` (`phase` only). Generic default:
+      *tag-name*. Built-in: not set.
+
+    - \[`--tag-require` *tag*\]: A tag a claimable task has to carry
+      (repeatable). Built-in: not set.
+
+    - \[`--tag-exclude` *tag*\]: A tag a claimable task must not carry
+      (repeatable). Built-in: not set.
+
+    - \[`--tag-retry`\]: A shorthand for `--tag-failure none`, so a
+      failed task is claimed again after a growing delay (`phase` only).
+      Built-in: not set.
+
+    - \[`--assign-name` *who*\]: The assignee under which the tasks are
+      claimed, held, recognized, and released, and which names the
+      agent-owned worktrees. Generic default: the agent name. Built-in:
+      not set.
+
+    - \[`--assign-required`\]: Claim only the tasks explicitly assigned
+      to *who* of `--assign-name` (`phase` only). Built-in: not set.
+
+    - \[`--assign-success` *who*\]: The assignee of a task after its
+      successful processing: a name, `none`, or `previous`. Generic
+      default: `none` for `phase`, `previous` for `request`. Built-in:
+      not set.
+
+    - \[`--assign-failure` *who*\]: The assignee of a task after its
+      failed processing: a name, `none`, or `previous`. Generic default:
+      `none` for `phase`, `previous` for `request`. Built-in: not set.
+
+    - \[`--request-name` *name*\]: The name of the processed requests
+      (`request` only). Generic default: the agent name. Built-in: not
+      set. Not allowed, as the qualifier is of type `phase`.
+
+    - \[`--request-done` *word*\]: The word naming a processed task in
+      the log lines (`request` only). Generic default: `processed`.
+      Built-in: not set. Not allowed, as the qualifier is of type
+      `phase`.
+
+    - \[`--prompt-skill` *name*\]: The skill to invoke (mutually
+      exclusive with `--prompt-text` and `--prompt-file`). Built-in:
+      `ase-repo-review`.
+
+    - \[`--prompt-args` *template*\]: The argument template of the
+      skill. Generic default: `{id}` for `phase`, `{id}: {prompt}` for
+      `request`. Built-in: `{?changeset-type=branch:--branch
+      {changeset-name}}`.
+
+    - \[`--prompt-text` *template*\]: The prompt text template to invoke
+      instead of a skill. Built-in: not set.
+
+    - \[`--prompt-file` *file*\]: The file with the prompt text template
+      to invoke instead of a skill. Built-in: not set.
+
+    - \[`--prepare-run` *cmd*\]: A shell command run in the working
+      directory before the prompt (repeatable). Built-in: not set.
+
+    - \[`--success-criterion` *criterion*\]: A success criterion:
+      `exit`, `clean`, `changed`, `verdict`, `attachment`, or `status`
+      (repeatable). Generic default: `exit` and `clean` for `phase`,
+      `clean` and `changed` for `request`. Built-in: `exit` and
+      `verdict`.
+
+    - \[`--success-match` *regex*\]: A regular expression an output line
+      has to match (repeatable). Built-in: not set.
+
+    - \[`--verdict-label` *label*\]: The label after which the verdict
+      is given in the output. Built-in: `REVIEW VERDICT`.
+
+    - \[`--verdict-allow` *VERDICT*\]: An accepted verdict (repeatable).
+      Generic default: the verdicts of `--state-verdict`, else any.
+      Built-in: `APPROVE` and `REJECT`.
+
+    - \[`--attach-output` *kind*\]: The kind of the attachment storing
+      the output lines of the prompt. Built-in: not set.
+
+    - \[`--attach-expect` *spec*\]: The attachment
+      \[*mime-type*`;`\]*kind* to be created or changed by the
+      processing for the success criterion `attachment`. Built-in: not
+      set.
+
+    - \[`--attach-skip` *spec*\]: The attachment
+      \[*mime-type*`;`\]*kind* leaving a task unclaimed (`phase` only).
+      Built-in: not set.
+
+    - \[`--attach-changeset` *kind*\]: The kind of the attachment
+      `text/x-diff;`*kind* storing the change set snapshot of the task
+      (with `--workdir changeset` or `target` only). Built-in: not set.
+
+    - \[`--finish-commit`\]: Commit the work onto a `branch:` changeset
+      and publish it (with `--workdir changeset` only). Built-in: not
+      set. Not allowed, as the qualifier works with `--workdir
+      changeset-read`.
+
+    - \[`--finish-success` *cmd*\]: A shell command run in the working
+      directory after a successful processing. Built-in: not set.
+
+    - \[`--finish-failure` *cmd*\]: A shell command run in the working
+      directory after a failed processing. Built-in: not set.
+
+    - \[`-f`|`--foreground`\]: Run the agent in the current process
+      instead, logging to the terminal, until it is interrupted (e.g.,
+      via `CTRL+C`) or stopped, where an agent of the same name already
+      running is an error.
+
+    - \[`-h`|`--help`\]: Show the usage information of the sub-command
+      only.
+
+  The options `--`*group*`-`*item* above override the built-in
+  definition of the mode of the agent (where an option also replaces its
+  mutually exclusive alternatives, e.g., `--prompt-text` replaces the
+  skill of `--prompt-skill`), while the agent keeps the identity of its
+  kind (its runs, its presence, and its agent-owned worktrees are named
+  after `qualifier`). See `ase-agent-adhoc`(1) for their full semantics.
+
+- `ase agent qualifier status` \[`-n`|`--name` *name*\]: Report whether
+  the qualifier agent of the name *name* (default: `qualifier`) is
+  running, as `agent` *name*`: running (pid` *pid*`)` resp. `agent`
+  *name*`: not running` (exit status 1).
+
+- `ase agent qualifier log` \[`-f`|`--follow`\] \[`-n`|`--lines` *n*\]
+  \[`--name` *name*\]: Show the log `.ase/agent/`*name*`.log` of the
+  qualifier agent of the name *name* (default: `qualifier`) run in the
+  background, where an agent of a fleet logs into the log of the fleet
+  instead (see `ase-agent-fleet`(1)). Without a log file, an
+  informational message is shown only. The options are:
+
+    - \[`-f`|`--follow`\]: Show the last *n* lines (default: 10) and
+      then follow all newly appended lines, in the style of `tail -f`,
+      until interrupted.
+
+    - \[`-n`|`--lines` *n*\]: Show the last *n* lines only (default:
+      all, or 10 with `--follow`).
+
+    - \[`--name` *name*\]: The name of the agent (default: `qualifier`),
+      given in its long form only, as `-n` is the short form of
+      `--lines`.
+
+- `ase agent qualifier stop` \[`-n`|`--name` *name*\]: Stop the qualifier
+  agent of the name *name* (default: `qualifier`) by `SIGTERM`, waiting
+  (up to 5 minutes) until it aborted its running processings and put
+  their tasks back. An agent not running is reported informationally
+  only.
+
+## ENVIRONMENT
+
+- `ASE_TOOL`: The default agent tool of `--tool` (default: `claude`).
+
+- `ASE_AGENT_RELAY_TOKEN`: The bearer token of the agent relay, if not
+  embedded in the URL of `--agent-relay` resp. `project.relay.url`.
+
+- `ASE_HEADLESS`: Set to `true` for the agent tool processes spawned by
+  the agent.
+
+## FILES
+
+- `.ase/agent/`*name*`.yaml`: The process state (kind, process id, and
+  process start time) of the agent, existing while it runs.
+
+- `.ase/agent/`*name*`.log`: The log of the agent run in the background.
+
+- *per-user state
+  directory*`/agent-qualifier/`*store-hash*`/`*run-id*`.lock` and
+  `.json`: The run lock and the run record of each qualifier agent
+  process, used to recover the tasks of terminated agent processes (see
+  **INTERRUPTS AND RECOVERY** in `ase-agent`(1)).
+
+## EXIT STATUS
+
+`ase agent qualifier start` exits with status `0` once the agent started
+(or was already running), resp. once a foreground agent terminated
+regularly, and with status `1` on any error (e.g., an invalid option, a
+task lifecycle model other than `enterprise`, or a missing agent tool).
+`ase agent qualifier status` exits with status `1` if the agent is not
+running.
+
+## EXAMPLES
+
+```sh
+# review the implemented tasks, leaving the decision to a human
+$ ase agent qualifier start -m judge -p 2
+
+# review the implemented tasks and decide on them by the verdict
+$ ase agent qualifier start -m qualify
+```
+
+## SEE ALSO
+
+`ase`(1), `ase-agent`(1), `ase-agent-rebooter`(1),
+`ase-agent-condenser`(1), `ase-agent-researcher`(1),
+`ase-agent-implementer`(1), `ase-agent-integrator`(1),
+`ase-agent-editor`(1), `ase-agent-estimator`(1), `ase-agent-adhoc`(1),
+`ase-agent-fleet`(1), `ase-agent-relay`(1), `ase-task`(1),
+`ase-task-board`(1).
+
+## AUTHOR
+
+Dr. Ralf S. Engelschall <rse@engelschall.com>