pentesting 0.101.6 → 0.101.8

package/ARCHITECTURE.md

@@ -2,7 +2,9 @@
 
 This document reflects the current `main` branch architecture. It is the single,
 detailed reference for how the runtime is structured; the [README](README.md)
-stays intentionally short and usage-focused.
+stays intentionally short and usage-focused. For a diagram-level tour of the
+main runtime flows, see [Main Flows](docs/architecture/MAIN_FLOWS.md). Both are
+internal-only and are never mirrored to the public repo.
 
 > **Engine vs product.** The orchestration engine is **`builder`** — a
 > general-purpose, local-first Rust agent runtime. **`pentesting`** is the
@@ -394,11 +396,33 @@ battlefield rows. Core status read failures retain their existing error path.
 With no recorded run, `/status` still shows goal, manual/auto mode, queue, and
 usage without an evidence read. Recorded `TurnExit` and typed `MissionState` are
 shown separately so model Stop or run completion cannot appear as verified
-mission completion. The live status row deliberately remains limited to
-actionable progress/wait state: there is no frontier parsing, background refresh,
-write, dispatch shortcut, or hidden chrome state.
-
-Completed type-ahead inputs carry an explicit active-turn behavior. Safe
+mission completion. The live status row deliberately remains limited to
+actionable progress/wait state: there is no frontier parsing, background refresh,
+write, dispatch shortcut, or hidden chrome state.
+
+Interactive `/auto` progress is producer-owned rather than inferred from the
+latest conversation after the fact. Dispatch marks a self-prompt turn in flight;
+successful cleanup captures that turn's final assistant markdown in memory,
+records a deterministic completed-turn line in the transcript, and synchronizes
+optional `current/target` progress to the footer before queued user input is
+replayed. A regular `AUTO_GOAL_PROGRESS` line is observability-only.
+`AUTO_GOAL_COMPLETE` retains completion authority and
+`AUTO_GOAL_BLOCKED` remains non-terminal. Cancellation, goal/auto reset, and a
+manual user turn invalidate pending completion provenance so a later reply
+cannot be misattributed to the autonomous turn. Unexpected stream termination
+also revokes ownership before queue replay, and explicit stop interrupts disable
+auto mode before preserved input is replayed. Interrupt-listener shutdown
+linearizes the terminal boundary as stop, reader join, then pending-source
+recovery, so an Esc accepted concurrently with `TurnCompleted` wins before
+progress or completion can be committed. Tool/delegated-agent markdown and
+terminal events have no root completion authority while a nested producer owns
+the stream. The auto footer is process-level chrome: turn-local backend resets
+preserve it until an explicit UI state transition clears it. The footer receives
+a bounded single-line goal projection, while the deterministic progress title
+does not repeat the goal every turn, so multiline/control-bearing goals cannot
+corrupt fixed chrome or inflate transcript history.
+
+Completed type-ahead inputs carry an explicit active-turn behavior. Safe
 inspection commands (`/info`, `/usage`, `/context`, `/memory`, `/status`,
 `/help`, `/skill`, and `/tools`) are atomically extracted and
 rendered without cancelling the response stream. State-changing and modal
@@ -418,32 +442,32 @@ the reader resumes after modal ownership ends. Type-ahead is therefore buffered
 FIFO instead of racing or leaking into a later model, agent, or configuration
 field. Service-layer approval, secret, selection, and follow-up prompts acquire
 the same lifetime-bound modal handoff through the prompt-entry hook, and
-concurrent service prompts are serialized so two widgets never read stdin at
-once.
-
-`/resume` is the canonical saved-session selector; `/conversation` and
-`/conversations` remain compatibility aliases. The selector includes every
-conversation with persisted context, even when it has no title. Resuming a
-different conversation clears the process-local goal and forces auto mode off,
-so state from the previous session cannot drive the resumed one accidentally.
-`/new` applies the same process-local goal/auto reset at the fresh-session
-boundary while preserving the queued FIFO tail. Persisted titles are reduced to
-one bounded control-free selector row before that row is bound to its typed
-conversation ID. Local upserts stamp the activity time used by `/resume`,
-`--continue`, and `conversation resume <id>` ordering. The command remains
-FIFO-queued while a turn is active because its selector is a modal terminal
-owner.
-
-Normal `/exit` and empty-prompt Ctrl+D termination are serialized through the
-output actor. It rejects new writes, completes its current render batch, resets
-styles and terminal modes, restores the full scroll region, clears the tracked
-multiline footer, shows the cursor, disables raw mode, and drops the terminal
-surface before printing one plain saved-session message. The shutdown
-acknowledgement and actor join occur after that message, so no detached redraw
-can overwrite terminal cleanup. The generic `restore_terminal` function is a
-best-effort fallback for failures outside this coordinated path. An empty
-session reports that no resumable messages were created instead of promising a
-session that the repository intentionally excludes from the resume list.
+concurrent service prompts are serialized so two widgets never read stdin at
+once.
+
+`/resume` is the canonical saved-session selector; `/conversation` and
+`/conversations` remain compatibility aliases. The selector includes every
+conversation with persisted context, even when it has no title. Resuming a
+different conversation clears the process-local goal and forces auto mode off,
+so state from the previous session cannot drive the resumed one accidentally.
+`/new` applies the same process-local goal/auto reset at the fresh-session
+boundary while preserving the queued FIFO tail. Persisted titles are reduced to
+one bounded control-free selector row before that row is bound to its typed
+conversation ID. Local upserts stamp the activity time used by `/resume`,
+`--continue`, and `conversation resume <id>` ordering. The command remains
+FIFO-queued while a turn is active because its selector is a modal terminal
+owner.
+
+Normal `/exit` and empty-prompt Ctrl+D termination are serialized through the
+output actor. It rejects new writes, completes its current render batch, resets
+styles and terminal modes, restores the full scroll region, clears the tracked
+multiline footer, shows the cursor, disables raw mode, and drops the terminal
+surface before printing one plain saved-session message. The shutdown
+acknowledgement and actor join occur after that message, so no detached redraw
+can overwrite terminal cleanup. The generic `restore_terminal` function is a
+best-effort fallback for failures outside this coordinated path. An empty
+session reports that no resumable messages were created instead of promising a
+session that the repository intentionally excludes from the resume list.
 
 Typing `/` opens the complete registered command catalog. Search includes
 canonical names and aliases; Up/Down changes the selection, and Enter inserts
@@ -560,12 +584,12 @@ Inside an interactive session, these commands inspect and drive runtime state
 /memory        Show stored conversation memories for the current conversation
 /tools         List the currently available tools and schemas
 /agent         Switch the active agent
-/resume        Resume a saved session for the active workspace
+/resume        Resume a saved session for the active workspace
 /goal <task>   Set the active goal without enabling autonomous mode
 /auto          Toggle autonomous mode for the current goal (default: off; Esc stops it)
 /update        Download and apply the latest public release asset for supported native targets
 /help          Show all commands
-/exit          Save the session, restore the terminal, and quit
+/exit          Save the session, restore the terminal, and quit
 ```
 
 ## Security Domain Skills

package/README.md

@@ -73,7 +73,9 @@ Provider variables are optional — the TUI launches without them and lets you l
 | The best design blueprint is the human being | Better systems begin with better self-observation: understand how we perceive, decide, learn, and recover, then make those loops observable |
 | The agent is the bottleneck | As AI models advance, the agent framework and the surrounding system must evolve with them |
 
-### Capability record
+---
+
+## Capability record
 
 | Date | Result | Test setup | Note |
 | --- | --- | --- | --- |
@@ -90,13 +92,11 @@ Provider variables are optional — the TUI launches without them and lets you l
 | `/model [query]` | Switch provider, model, or custom endpoint |
 | `/goal <objective>` | Set or clear the active goal |
 | `/auto` | Run the active goal automatically; Esc stops it |
-| `/status` | Show the current run and verified mission status |
-| `/new` · `/retry` | Start a new conversation or retry the last turn |
-| `/resume` | Resume a saved session from the current workspace |
-| `/config` | Edit runtime configuration |
-| `/exit` | Save the session, restore the terminal, and quit |
-
-> The command you run is always **`pentesting`**. The internal engine is **`builder`** — `pentesting` runs it under the hood; the engine name never surfaces in normal use.
+| `/status` | Show the current run and verified mission status |
+| `/new` · `/retry` | Start a new conversation or retry the last turn |
+| `/resume` | Resume a saved session from the current workspace |
+| `/config` | Edit runtime configuration |
+| `/exit` | Save the session, restore the terminal, and quit |
 
 ---
 
@@ -115,3 +115,9 @@ Provider variables are optional — the TUI launches without them and lets you l
 > Each voice sings its most beautiful song from its own place, yet when combined, they create one grand, beautiful melody. I believe this structure is no different from AI agents.
 >
 > — *agnusdei1207*
+
+---
+
+## 💡 Insight
+
+> Analyzing countless starred agent repos and papers gave me insights, but adopting them didn't actually solve the core problem. What did, I think: primitive CS theory — backtracking, Monte Carlo, Prim, Kruskal — and ideas from observing myself, the best design blueprint and best practice there is. The AI era keeps pushing sensational marketing, and I've lost trust in analyzing it. I think refining the fundamentals, internalizing them, and finding my own way matters more, especially now.

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "pentesting",
-  "version": "0.101.6",
-  "builderReleaseTag": "v0.101.6",
+  "version": "0.101.8",
+  "builderReleaseTag": "v0.101.8",
   "description": "Penetration testing AI agent powered by Rust, with audited reverse-shell capture, verified PTY upgrades, and evidence-first orchestration.",
   "license": "MIT",
   "author": "agnusdei1207",