aepkit 0.7.0__tar.gz → 0.7.2__tar.gz

{aepkit-0.7.0 → aepkit-0.7.2}/CHANGELOG.md

@@ -7,6 +7,37 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.7.2] - 2026-11-08
+
+### Added
+- `references/autonomous-mode.md`: an optional step at a phase's close. Once the gate is
+  `APPROVED`, the work is pushed and the Auditor brief is up to date, the Auditor may compact
+  its own session and resume itself from the brief.
+- `aeprogress` 0.3.0: a `compact_and_resume` tool for the Auditor. After its turn ends, a band
+  counts down 40 seconds with Cancel and Compact now; at zero the session is compacted and the
+  Auditor resumed with its own `resume` message. A prompt typed by the owner, Esc on the turn,
+  or Cancel drops it; a manual `/compact` during the countdown resumes once; a refused or vetoed
+  compaction resumes nothing. Options for the seconds and to turn it off.
+
+## [0.7.1] - 2026-11-08
+
+### Added
+- `references/handoffs.md`: an optional `Load: docs-only` line in the handoff template, for
+  runs where a tool holds back Executor launches while the machine is busy. It marks a task
+  that builds nothing, so it may run beside one that builds; a handoff without it counts as
+  a build. The protocol does not require it.
+- `aeprogress` 0.2.0 (`integrations/claude-code/aeprogress/`): a launch limit that, while a
+  run is found, refuses launching another Executor past 2 live workers, 1 building worker,
+  or a machine more than 75% busy for a build (each a `/config` option), with the reason in
+  the refusal. It sees Claude Code subagents whose prompt names a task of the run, and Orca
+  `worker-start` and `send` to a dispatch that is not live; it counts both together, and
+  refuses when Orca cannot be asked. The pane shows the machine's load (Linux `/proc`,
+  macOS and BSD `sysctl`, Windows PowerShell) and how full the limit is. On macOS, when
+  Spotlight's indexing stays busy, it recommends excluding the project folder in System
+  Settings; it never changes a setting.
+- `aeprogress`: Windows fallbacks for finding aepkit (`python -m`, `py -m`,
+  `%USERPROFILE%\.local\bin`).
+
 ## [0.7.0] - 2026-11-08
 
 ### Added
@@ -315,7 +346,9 @@ Fixes from an independent review of 0.3.0.
 - Multi-framework agent installation support for Antigravity, Claude Code, and Cursor.
 - Zero-dependency test runner (`tests/run.py`).
 
-[Unreleased]: https://github.com/tBeltty/auditor-executor-protocol/compare/v0.7.0...HEAD
+[Unreleased]: https://github.com/tBeltty/auditor-executor-protocol/compare/v0.7.2...HEAD
+[0.7.2]: https://github.com/tBeltty/auditor-executor-protocol/compare/v0.7.1...v0.7.2
+[0.7.1]: https://github.com/tBeltty/auditor-executor-protocol/compare/v0.7.0...v0.7.1
 [0.7.0]: https://github.com/tBeltty/auditor-executor-protocol/compare/v0.6.0...v0.7.0
 [0.6.0]: https://github.com/tBeltty/auditor-executor-protocol/compare/v0.5.1...v0.6.0
 [0.5.1]: https://github.com/tBeltty/auditor-executor-protocol/compare/v0.5.0...v0.5.1

{aepkit-0.7.0/src/aepkit.egg-info → aepkit-0.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aepkit
-Version: 0.7.0
+Version: 0.7.2
 Summary: Mechanical support for the Auditor/Executor protocol: scaffold, lint, and negative-control the document set for a multi-phase, multi-agent execution.
 Author-email: tBeltty <jhonatan@tbelt.online>
 License-Expression: MIT
@@ -178,7 +178,7 @@ A failure only proves something if it is the failure you meant. A syntax error,
 
 ### Optional: Progress Pane for Claude Code
 
-`aeprogress` is a Claude Code mod that keeps a pane beside the chat with the run's overall percentage, a bar per phase, who is working on which task ID (Claude Code subagents, Orca workers, or any other harness through a command of your own), what awaits audit and what needs attention. It reads the log through `aepkit status --json` and refreshes after each turn, and every 20 seconds while the pane is open. The protocol does not depend on it.
+`aeprogress` is a Claude Code mod that keeps a pane beside the chat with the run's overall percentage, a bar per phase, who is working on which task ID (Claude Code subagents, Orca workers, or any other harness through a command of your own), what awaits audit, what needs attention, and the machine's load. It reads the log through `aepkit status --json` and refreshes after each turn, and every 20 seconds while the pane is open. While a run is found it also holds back launching another Executor past a worker count or a machine load (2 workers, 1 building, 75% busy by default; a handoff marked `Load: docs-only` does not count as a build), and on macOS it recommends excluding the project from Spotlight when indexing keeps the machine busy. The protocol does not depend on it.
 
 ```
 /plugin install aeprogress --marketplace tBeltty/auditor-executor-protocol

{aepkit-0.7.0 → aepkit-0.7.2}/README.md

@@ -140,7 +140,7 @@ A failure only proves something if it is the failure you meant. A syntax error,
 
 ### Optional: Progress Pane for Claude Code
 
-`aeprogress` is a Claude Code mod that keeps a pane beside the chat with the run's overall percentage, a bar per phase, who is working on which task ID (Claude Code subagents, Orca workers, or any other harness through a command of your own), what awaits audit and what needs attention. It reads the log through `aepkit status --json` and refreshes after each turn, and every 20 seconds while the pane is open. The protocol does not depend on it.
+`aeprogress` is a Claude Code mod that keeps a pane beside the chat with the run's overall percentage, a bar per phase, who is working on which task ID (Claude Code subagents, Orca workers, or any other harness through a command of your own), what awaits audit, what needs attention, and the machine's load. It reads the log through `aepkit status --json` and refreshes after each turn, and every 20 seconds while the pane is open. While a run is found it also holds back launching another Executor past a worker count or a machine load (2 workers, 1 building, 75% busy by default; a handoff marked `Load: docs-only` does not count as a build), and on macOS it recommends excluding the project from Spotlight when indexing keeps the machine busy. The protocol does not depend on it.
 
 ```
 /plugin install aeprogress --marketplace tBeltty/auditor-executor-protocol

{aepkit-0.7.0 → aepkit-0.7.2}/references/autonomous-mode.md

@@ -94,6 +94,12 @@ each handoff. The shape that has worked here:
    yet expanded, expand it (tasks, gate, model per task, log sections) before launching
    its first task.
 
+Optional, at a phase's close: once the gate is `APPROVED`, the work is pushed and the
+Auditor brief is up to date on disk, the Auditor may compact its own session and resume
+itself from the brief, so a long run does not carry every earlier phase in its context.
+On Claude Code the optional `aeprogress` mod offers this as a tool that waits out a short
+countdown the owner can cancel. The protocol does not depend on it.
+
 Do not end a turn between a verdict and the next launch unless something on the
 critical-risk list is open. A run that stops to report an `APPROVED` and wait is Guided
 mode by accident.

{aepkit-0.7.0/src/aepkit/skill → aepkit-0.7.2}/references/handoffs.md

@@ -32,6 +32,8 @@ ROLE: Executor. Work from <EXECUTION_GUIDE> (Phase <n>, `<TASK-ID>`) only; repor
 [Autonomous mode only:] You are the Auditor's subagent. Questions go as BLOCKED in the
 log and in your final report; you do not address the owner.
 
+[Optional, only when the run uses a launch limit:] Load: docs-only
+
 REPORTED STATE: <what is already DONE in the log, and whether it was audited or only
 self-reported — do not conflate the two>. Do not reopen <prior tasks>.
 
@@ -71,6 +73,13 @@ mid-task.
 Do not paste a rules-of-engagement block from one project's run into another's handoff
 without re-confirming it applies. It is a per-run artifact, not part of this skill.
 
+`Load: docs-only` is for runs where a tool holds back Executor launches while the machine
+is busy, such as the optional `aeprogress` mod for Claude Code. Put it on its own line in
+a handoff whose task compiles, builds and tests nothing (documentation, a plan, a review),
+so it can run beside a task that builds. Leave it out when unsure: a handoff without it
+counts as a build, which is the safe side. The protocol does not require the line, and a
+run with no such tool ignores it.
+
 ## Remediation handoff (Auditor)
 
 A verdict is not the deliverable — a well-evidenced `CONDITIONAL` or `REJECTED` that

aepkit-0.7.2/src/aepkit/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.7.2"

{aepkit-0.7.0 → aepkit-0.7.2}/src/aepkit/skill/references/autonomous-mode.md

@@ -94,6 +94,12 @@ each handoff. The shape that has worked here:
    yet expanded, expand it (tasks, gate, model per task, log sections) before launching
    its first task.
 
+Optional, at a phase's close: once the gate is `APPROVED`, the work is pushed and the
+Auditor brief is up to date on disk, the Auditor may compact its own session and resume
+itself from the brief, so a long run does not carry every earlier phase in its context.
+On Claude Code the optional `aeprogress` mod offers this as a tool that waits out a short
+countdown the owner can cancel. The protocol does not depend on it.
+
 Do not end a turn between a verdict and the next launch unless something on the
 critical-risk list is open. A run that stops to report an `APPROVED` and wait is Guided
 mode by accident.

{aepkit-0.7.0 → aepkit-0.7.2/src/aepkit/skill}/references/handoffs.md

@@ -32,6 +32,8 @@ ROLE: Executor. Work from <EXECUTION_GUIDE> (Phase <n>, `<TASK-ID>`) only; repor
 [Autonomous mode only:] You are the Auditor's subagent. Questions go as BLOCKED in the
 log and in your final report; you do not address the owner.
 
+[Optional, only when the run uses a launch limit:] Load: docs-only
+
 REPORTED STATE: <what is already DONE in the log, and whether it was audited or only
 self-reported — do not conflate the two>. Do not reopen <prior tasks>.
 
@@ -71,6 +73,13 @@ mid-task.
 Do not paste a rules-of-engagement block from one project's run into another's handoff
 without re-confirming it applies. It is a per-run artifact, not part of this skill.
 
+`Load: docs-only` is for runs where a tool holds back Executor launches while the machine
+is busy, such as the optional `aeprogress` mod for Claude Code. Put it on its own line in
+a handoff whose task compiles, builds and tests nothing (documentation, a plan, a review),
+so it can run beside a task that builds. Leave it out when unsure: a handoff without it
+counts as a build, which is the safe side. The protocol does not require the line, and a
+run with no such tool ignores it.
+
 ## Remediation handoff (Auditor)
 
 A verdict is not the deliverable — a well-evidenced `CONDITIONAL` or `REJECTED` that

{aepkit-0.7.0 → aepkit-0.7.2/src/aepkit.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aepkit
-Version: 0.7.0
+Version: 0.7.2
 Summary: Mechanical support for the Auditor/Executor protocol: scaffold, lint, and negative-control the document set for a multi-phase, multi-agent execution.
 Author-email: tBeltty <jhonatan@tbelt.online>
 License-Expression: MIT
@@ -178,7 +178,7 @@ A failure only proves something if it is the failure you meant. A syntax error,
 
 ### Optional: Progress Pane for Claude Code
 
-`aeprogress` is a Claude Code mod that keeps a pane beside the chat with the run's overall percentage, a bar per phase, who is working on which task ID (Claude Code subagents, Orca workers, or any other harness through a command of your own), what awaits audit and what needs attention. It reads the log through `aepkit status --json` and refreshes after each turn, and every 20 seconds while the pane is open. The protocol does not depend on it.
+`aeprogress` is a Claude Code mod that keeps a pane beside the chat with the run's overall percentage, a bar per phase, who is working on which task ID (Claude Code subagents, Orca workers, or any other harness through a command of your own), what awaits audit, what needs attention, and the machine's load. It reads the log through `aepkit status --json` and refreshes after each turn, and every 20 seconds while the pane is open. While a run is found it also holds back launching another Executor past a worker count or a machine load (2 workers, 1 building, 75% busy by default; a handoff marked `Load: docs-only` does not count as a build), and on macOS it recommends excluding the project from Spotlight when indexing keeps the machine busy. The protocol does not depend on it.
 
 ```
 /plugin install aeprogress --marketplace tBeltty/auditor-executor-protocol

aepkit-0.7.0/src/aepkit/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.7.0"