@rse/ase 2.0.3 → 2.0.5

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

@@ -0,0 +1,383 @@
+# ase-agent-condenser(1) -- Plan Condensing Agent
+
+## SYNOPSIS
+
+`ase agent condenser start`
+\[`-n`|`--name` *name*\]
+\[`-t`|`--tool` `claude`|`copilot`|`codex`\]
+\[`-p`|`--parallel` *num*\]
+\[`-T`|`--timeout` *duration*\]
+\[`-o`|`--one-shot`\]
+\[`--agent-relay` *url*\]
+\[`--`*group*`-`*item* *value* \[...\]\]
+\[`-f`|`--foreground`\]
+
+`ase agent condenser status`
+\[`-n`|`--name` *name*\]
+
+`ase agent condenser log`
+\[`-f`|`--follow`\]
+\[`-n`|`--lines` *n*\]
+\[`--name` *name*\]
+
+`ase agent condenser stop`
+\[`-n`|`--name` *name*\]
+
+## DESCRIPTION
+
+**ase agent condenser** compresses the wording of the plans of tasks in
+the `Planning` phase of the `enterprise` task lifecycle model (refused
+for any other model), while preserving all their semantics.
+
+As a plan is condensed only on the explicit request of a human, the
+condenser claims only the tasks in the state `DRAFTED` whose `Assignee:`
+frontmatter key already is its agent name (default: `condenser`), i.e.,
+which a human assigned to the condenser. Such a task is claimed
+immediately, without waiting for its `After:` predecessors (and, for an
+explicit epic, its group members), except for a predecessor still being
+processed by a condenser or a cancelled `After:` predecessor.
+
+The condenser moves each claimed task into `PLANNING`, tags it with
+`ase-agent-condenser:active`, and condenses its plan via the skill
+invocation `ase-task-condense --next DONE` *id*. The processing succeeds
+if the agent tool succeeded and the skill reported no error, which
+includes an already condensed plan, left untouched by the skill.
+Afterwards, on success as well as on failure, the condenser puts the
+task back into `DRAFTED`, removes its tag, and unassigns it. As the
+task is no longer assigned to the condenser, it is not claimed again,
+while assigning it to the condenser again requests another condensing.
+
+On an interrupt, a task being processed is put back, untagged and with
+its previous assignee (i.e., still assigned to the condenser), into
+`DRAFTED`. The condenser works in the project root only, so it
+neither requires a Git working copy nor `git`, and it accepts no
+`--repo` and `--tempdir`. See `ase-agent`(1) for the common mechanics of
+all agents.
+
+## OPTIONS
+
+- \[`-h`|`--help`\]: Show usage information of `ase agent condenser` (or
+  of the given sub-command) only.
+
+All other options belong to the sub-commands (see **COMMANDS**).
+
+## COMMANDS
+
+- `ase agent condenser start` \[*options*\]: Start the condenser 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:
+      `condenser`): 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, and its process files `.ase/agent/`*name*`.yaml` and
+      `.ase/agent/`*name*`.log`. Agents of the kind `condenser` under
+      different names form a pool, competing for the same tasks, but each
+      claims only the tasks explicitly assigned to its own name.
+
+    - \[`-t`|`--tool` *tool*\]: 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).
+
+    - \[`--title` *text*\]: The one-line title of the operation of the
+      agent (at most 80 characters), shown on the task boards. Built-in:
+      `Condense the plans of assigned tasks`.
+
+    - \[`--description` *text*\]: 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.
+
+    - \[`--type` `phase`|`request`\]: 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: `project`.
+
+    - \[`--lifecycle` *model*\]: 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 condenser
+      claims the tasks into its activity state.
+
+    - \[`--params` *name*`=`*value*\]: The value of a parameter
+      declared by the definition (repeatable). Built-in: none declared.
+
+    - \[`--state-incoming` *state*\]: A state of the tasks to claim
+      (mandatory for `phase`, repeatable with `--unclaimed` or
+      `--state-activity` only). Built-in: `DRAFTED`.
+
+    - \[`--state-activity` *state*\]: The state of a task during its
+      processing. Generic default: the incoming state. Built-in:
+      `PLANNING`.
+
+    - \[`--state-success` *state*\]: The target state on success, or
+      `previous` for the incoming state of the claim. Generic default:
+      the incoming state. Built-in: `DRAFTED`.
+
+    - \[`--state-failure` *state*\]: The target state on failure, or
+      `previous` for the incoming state of the claim. Generic default:
+      the incoming state. Built-in: `DRAFTED`.
+
+    - \[`--state-phase` *state*\]: The phase success state, into which
+      the skill itself can move a task. Generic default: the success
+      state, resp. the activity state for a `previous` success state.
+      Built-in: not set (hence `DRAFTED`).
+
+    - \[`--state-passed` *state*\]: The first state from which on a task
+      has passed the phase for its `After:` successors. Generic default:
+      the phase success state. Built-in: not set (hence `DRAFTED`, the
+      first state, so the predecessors impose no gate).
+
+    - \[`--state-verdict` *VERDICT*`=`*state*\]: The target state per
+      verdict (repeatable). Built-in: not set.
+
+    - \[`--tag-name` *tag*\]: The tag of the processed tasks
+      (`ase-agent-`*word*). Generic default: `ase-agent-`*name*, resp.
+      for `request` always `ase-agent-`*request-name*. Built-in: not set.
+
+    - \[`--tag-success` *tag*\]: The tag on success: *tag-name*,
+      *tag-name*`:`*value*, or `none` (`phase` only). Generic default:
+      *tag-name*. Built-in: `none`.
+
+    - \[`--tag-failure` *tag*\]: The tag on failure: *tag-name*,
+      *tag-name*`:`*value*, or `none` (`phase` only). Generic default:
+      *tag-name*. Built-in: `none`.
+
+    - \[`--tag-require` *tag*\]: 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: enabled.
+
+    - \[`--assign-success` *who*\]: 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 condenser 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 condenser is of type `phase`.
+
+    - \[`--prompt-skill` *name*\]: The skill to invoke (mutually
+      exclusive with `--prompt-text` and `--prompt-file`). Built-in:
+      `ase-task-condense`.
+
+    - \[`--prompt-args` *template*\]: The argument template of the
+      skill. Generic default: `{id}` for `phase`, `{id}: {prompt}` for
+      `request`. Built-in: `--next DONE {id}`.
+
+    - \[`--prompt-text` *template*\]: 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 `clean`.
+
+    - \[`--success-match` *regex*\]: 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: not set.
+
+    - \[`--verdict-allow` *VERDICT*\]: An accepted verdict (repeatable).
+      Generic default: the verdicts of `--state-verdict`, else any.
+      Built-in: not set.
+
+    - \[`--attach-output` *kind*\]: 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 condenser works in the project root.
+
+    - \[`--finish-success` *cmd*\]: 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 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
+  `condenser`). See `ase-agent-adhoc`(1) for their full semantics.
+
+- `ase agent condenser status` \[`-n`|`--name` *name*\]: Report whether
+  the condenser agent of the name *name* (default: `condenser`) is
+  running, as `agent` *name*`: running (pid` *pid*`)` resp. `agent`
+  *name*`: not running` (exit status 1).
+
+- `ase agent condenser log` \[`-f`|`--follow`\] \[`-n`|`--lines` *n*\]
+  \[`--name` *name*\]: Show the log `.ase/agent/`*name*`.log` of the
+  condenser agent of the name *name* (default: `condenser`) 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: `condenser`),
+      given in its long form only, as `-n` is the short form of
+      `--lines`.
+
+- `ase agent condenser stop` \[`-n`|`--name` *name*\]: Stop the condenser
+  agent of the name *name* (default: `condenser`) 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-condenser/`*store-hash*`/`*run-id*`.lock` and `.json`:
+  The run lock and the run record of each condenser agent process, used
+  to recover the tasks of terminated agent processes (see **INTERRUPTS
+  AND RECOVERY** in `ase-agent`(1)).
+
+## EXIT STATUS
+
+`ase agent condenser 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 condenser status` exits with status `1` if the agent is not
+running.
+
+## EXAMPLES
+
+```sh
+# start the condenser, condensing the plans of the tasks assigned to it
+$ ase agent condenser start
+
+# request the condensing of a drafted task by assigning it to the condenser
+$ ase task assign FOO-42 condenser
+```
+
+## SEE ALSO
+
+`ase`(1), `ase-agent`(1), `ase-agent-rebooter`(1),
+`ase-agent-researcher`(1), `ase-agent-implementer`(1),
+`ase-agent-qualifier`(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>
+