fix: restore watch defaults and align agent status, undo, cron fork, and completion budget behavior (#336)

## Requirement or Bug

Restore filesystem-watch defaults and land a batch of session-behavior
fixes (agent status, undo, cron forks, completion budget).

## Bug Reproduction Steps

N/A (behavior restore + fixes).

## Root Cause

Watch was flipped off by default when it should not have been;
permission-mode changes never reached agent status consumers; undo left
a stale interruption reminder; forks inherited the source session's cron
tasks; a default completion token cap silently truncated model output.
Each fixed at the cause.

## Code Changes

- Filesystem watch defaults back on (`[watch] enabled = false` /
`PYTHINKER_CODE_WATCH=0` to disable).
- `setMode` publishes permission mode on `AgentStatusUpdated`.
- NotifyUser nudges only for clients with an updates panel
(`notifyUserAvailable` host gate).
- Undo removes a turn's interruption reminder with the turn.
- Forks clear inherited cron tasks and surface a one-shot notice.
- The default completion token cap is gone; set `maxCompletionTokens` in
modelOverrides to cap output. `usedContextTokens` reads the tokenizer
size.

## Impact Scope

- `packages/agent-core-v2` (watch, nudge, permission mode, interruption
reminder, cron runtime, usage/traits/requesters), `apps/vis` event
types, docs (`config-files.md`).
- Tests: suites for each behavior above; full suite green locally.

## Checklist

- [x] I have read the
[CONTRIBUTING](https://github.com/PyModel/pythinker-code/blob/main/CONTRIBUTING.md)
document.
- [x] I have linked a related issue (external PRs: issue must have a
maintainer's `/approve`). — No public issue; maintainer work.
- [x] I have added tests that prove my feature works.
- [x] Ran `gen-changesets` skill, or this PR needs no changeset.
- [x] Ran `gen-docs` skill, or this PR needs no doc update.

---------

Co-authored-by: Test User <test@example.test>

Author: elkaix

.changeset/completion-cap-opt-in.md

@@ -0,0 +1,5 @@
+---
+"@pymodel/pythinker-code": patch
+---
+
+Stop sending a default completion token cap to models; set maxCompletionTokens in modelOverrides to cap output again.

.changeset/fork-cron-clear.md

@@ -0,0 +1,5 @@
+---
+"@pymodel/pythinker-code": patch
+---
+
+Forked sessions no longer inherit the source session's scheduled tasks; the source keeps them and the fork notes the clearing.

.changeset/status-and-undo-fixes.md

@@ -0,0 +1,5 @@
+---
+"@pymodel/pythinker-code": patch
+---
+
+Publish permission mode changes on agent status updates, stop NotifyUser nudges in clients without an updates panel, and drop the interruption reminder when its turn is undone.

.changeset/trust-disclosure.md

@@ -0,0 +1,5 @@
+---
+"@pymodel/pythinker-code": minor
+---
+
+The workspace trust prompt now lists the MCP servers, extra directories, and project instruction sources that trusting would activate.

.changeset/trust-workspace-env.md

@@ -0,0 +1,5 @@
+---
+"@pymodel/pythinker-code": minor
+---
+
+Add PYTHINKER_CODE_TRUST_WORKSPACE=1 to trust the current workspace for headless runs without answering the trust prompt.

.changeset/watch-default-on.md

@@ -0,0 +1,5 @@
+---
+"@pymodel/pythinker-code": patch
+---
+
+Watch config, skills, and AGENTS.md files for changes again by default; set `[watch] enabled = false` or PYTHINKER_CODE_WATCH=0 to keep them off.

apps/desktop/package.json

@@ -20,7 +20,7 @@
     "@types/node": "^26.1.2",
     "@types/semver": "^7.7.0",
     "builder-util-runtime": "9.7.0",
-    "electron": "43.4.0",
+    "electron": "43.5.0",
     "electron-builder": "26.15.3",
     "electron-updater": "6.8.9",
     "semver": "^7.7.4",

apps/pythinker-code/dist-web/.web-bundle-manifest.json

@@ -1,4 +1,4 @@
 {
-  "sourceHash": "04602432b100c73fa465235500caccbe13e6af08198ab1c90198cdc5bd19fd1c",
+  "sourceHash": "0b9e0a931397c88206a0e22886da74780ce0c4a27202e3f6f9f81cd32777b557",
   "sourceFileCount": 496
 }