@assuredloop/orca-bot-kit 0.8.0 → 0.9.0

package/README.md

@@ -529,7 +529,8 @@ name. Everything else goes through Orca's mailbox, which the kit does carry.
 
 That includes a Claude session still running under a name from before the
 token, `<bot>.<session>`: `message to` answers the mailbox road for it, never
-that name, until the session next starts a new conversation.
+that name, until the kit's launch line next starts it (`obk restart`, or
+`obk up` after its tab is gone), which gives it a token name of its own.
 
 A session's mailbox is made the first time the kit starts it, and written in
 the book beside its tab. It is an Orca Run rather than the session's tab,
@@ -598,7 +599,9 @@ cannot be read as one that passed. `-- --yes` is how you say you meant it. When
 Orca is not answering, the command says which Orca it asked and skips, rather
 than report a kit that is not broken. Name files after it to run only those;
 each must be one of the `*.test.js` files under `test/system/`, links followed,
-and a name that is not is refused before anything runs.
+and a name that is not is refused before anything runs. This command is the
+only way in: a system test loaded any other way, with `node --test` or an
+editor's runner, skips and says how to run it.
 
 `npm run mutate` runs [StrykerJS](https://stryker-mutator.io) over the
 JavaScript this branch changed against `main` — committed, still in the working

package/SETUP.md

@@ -37,7 +37,7 @@ node --version                                          # 24.21.0 or newer
 git --version
 /Applications/Orca.app/Contents/Resources/bin/orca status --json
 claude --version                                        # at least one of these
-codex --version
+codex --version                                         # 0.156.1 or newer
 ```
 
 The Orca line must come back with `ok: true` and `result.runtime.reachable:
@@ -55,6 +55,10 @@ first release measured here that loads it without an experimental warning.
 If neither harness is installed, say so and stop. If only one is, that is fine,
 and it is the one Bot Father will run on.
 
+If Codex is older than 0.156.1, say so and ask them to update it before a bot
+runs on Codex. The kit starts Codex with `--no-daemon`, and older Codex refuses
+that flag.
+
 ## 2. Make `obk` runnable
 
 **First ask whether it already is:**
@@ -206,8 +210,9 @@ empty book and nothing says why.
 Codex's trust question applies to the **repository root**, which for a bot means
 the whole bots folder rather than the one bot. That is what they are agreeing to.
 
-Codex's `/new` question (0.156.1 on) is always answered with the current
-checkout, which is the bot home. The kit never makes a git worktree, so
+Codex's `/new` question (seen on 0.156.1; 0.157.1 did not show it in the runs
+seen so far) is always answered with the current checkout, which is the bot
+home. The kit never makes a git worktree, so
 `2. New worktree` is never the answer.
 
 **Anything you do not recognise: type nothing.** Tell them what is on the

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@assuredloop/orca-bot-kit",
-  "version": "0.8.0",
+  "version": "0.9.0",
   "license": "MIT",
   "repository": {
     "type": "git",

package/skills/obk-bot-building/SKILL.md

@@ -260,9 +260,10 @@ table: a harness that has added an option has moved them. Codex's hooks
 question matters most. The kit's hook is how the book learns which
 conversation the session is running, and until it is answered the
 conversation has not started. Codex's trust applies to the repository root,
-which is the whole bots folder. Codex's `/new` asks where the new
-conversation runs; the answer is always the current checkout, the bot home,
-and never `2. New worktree`: the kit never makes a git worktree.
+which is the whole bots folder. Codex's `/new` may ask where the new
+conversation runs (0.156.1 did; 0.157.1 has not so far); the answer is
+always the current checkout, the bot home, and never `2. New worktree`:
+the kit never makes a git worktree.
 
 Where the kit says no session came up, the shell swallowed the launch line,
 usually while it was asking its own question. Answer the shell, then close

package/src/launch.js

@@ -99,6 +99,48 @@ export const setsNetworkAccess = (session) =>
 export const reachesMail = (session, harness) =>
   harness !== 'codex' || !turnedOff(session);
 
+/** Codex's flag for running without its shared background server (0.156.1 on). */
+const NO_DAEMON = '--no-daemon';
+
+// A string is shell text, so it is read as the shell will split it: `'--no-daemon'`
+// is the flag, and `'/tmp/a --no-daemon b'` is one path that merely says it.
+const setsNoDaemon = (session) => {
+  const extra = session.extra_args;
+  const words = Array.isArray(extra) ? extra.map(String) : set(extra) ? shellWords(String(extra)) : [];
+  return words.includes(NO_DAEMON);
+};
+
+/**
+ * The words a shell makes of `text`: split on blanks outside quotes, quotes
+ * removed, a backslash keeping the next character. Nothing is expanded.
+ */
+function shellWords(text) {
+  const words = [];
+  let word;
+  let quote;
+  for (let at = 0; at < text.length; at += 1) {
+    const char = text[at];
+    if (quote === "'") {
+      if (char === "'") quote = undefined;
+      else word += char;
+    } else if (quote === '"') {
+      if (char === '"') quote = undefined;
+      else if (char === '\\' && '"\\$`'.includes(text[at + 1] ?? ' ')) word += text[(at += 1)];
+      else word += char;
+    } else if (/\s/.test(char)) {
+      if (word !== undefined) words.push(word);
+      word = undefined;
+    } else {
+      word ??= '';
+      if (char === "'" || char === '"') quote = char;
+      else if (char === '\\') word += text[(at += 1)] ?? '';
+      else word += char;
+    }
+  }
+  if (word !== undefined) words.push(word);
+  return words;
+}
+
 const turnedOff = (session) =>
   extraWords(session.extra_args).some((word) => word.includes(`${NETWORK_ACCESS}=false`));
 
@@ -174,6 +216,11 @@ export function launchCommand(session, { harness, home, workDir, prompt, promptF
   // take every other flag exactly as a fresh session does.
   if (resume !== undefined && harness === 'codex') words.push('resume');
   words.push(...APPROVAL[harness][set(session.approval) ? session.approval : DEFAULT_APPROVAL]);
+  // Codex 0.157 shares one background server between sessions by default, and
+  // a resume through it was seen to fail; without it Codex runs as 0.156 did
+  // (tech notes, section 3, #330). Codex refuses the flag twice, so the user's
+  // own wins.
+  if (harness === 'codex' && !setsNoDaemon(session)) words.push(NO_DAEMON);
 
   if (harness === 'claude') {
     // The name is the address other Claude sessions write to, so it goes on

package/src/up.js

@@ -377,13 +377,13 @@ function launchFor(bots, bot, session, harness, home, workDir, resume, held) {
   // through the tab's shell a character at a time.
   const promptFile = prompt === undefined || isShortPrompt(prompt) ? undefined : promptPath(bots, bot.name, session.name);
   // A new conversation is given a new name. A resume goes on under the one the
-  // kit gave it, and under no `-n` at all when the book `held` none of the
-  // kit's own: a resume keeps whatever name the conversation has, which is
-  // proven, and whether `-n` renames it is not (#286). Such a session is
-  // written to through its mailbox until it next starts fresh.
+  // kit gave it, and gets a new one when the book `held` none of the kit's own:
+  // `--resume <id> -n <name>` renames the conversation, proven live (#319), so
+  // a session still under the shared `<bot>.<session>` moves to an address of
+  // its own here.
   const address = harness !== 'claude' ? undefined
-    : resume === undefined ? addressOf(bot.name, session.name)
-    : isAddressOf(bot.name, session.name, held) ? held : undefined;
+    : resume !== undefined && isAddressOf(bot.name, session.name, held) ? held
+    : addressOf(bot.name, session.name);
   const line = launchCommand(session, {
     harness,
     home,