after moving all to cipher

worker-toolkit-stocks-in-the-future/scripts/snapshot_agent.py

@@ -22,6 +22,7 @@ import tempfile
 from pathlib import Path
 
 import atif_session
+import browser_note
 from harbor.agents.installed.claude_code import ClaudeCode
 from harbor.models.trial.paths import EnvironmentPaths
 
@@ -101,7 +102,7 @@ _AGENT_CLI_NOTE_FALLBACK = (
 )
 
 
-def _toolset_note() -> str:
+def _toolset_note(with_browser: bool = False, with_read: bool = False) -> str:
     """The toolset note appended to Claude Code's stock ``--print`` system prompt
     (via ``--append-system-prompt``) for the canonical reduced toolset.
 
@@ -118,9 +119,23 @@ def _toolset_note() -> str:
     file is missing."""
     path = Path(__file__).resolve().parent / "toolset_note.md"
     try:
-        return path.read_text(encoding="utf-8").strip()
+        note = path.read_text(encoding="utf-8").strip()
     except OSError:
-        return _AGENT_CLI_NOTE_FALLBACK
+        note = _AGENT_CLI_NOTE_FALLBACK
+    # Order matters: the Read correction must come AFTER the base note, because it supersedes
+    # that note's "there are no Read/Grep/Glob tools" line. Shipping the base note alone to a
+    # Read-enabled agent would be a false statement about its own toolset.
+    if with_read:
+        read_note = Path(__file__).resolve().parent / "toolset_note_read.md"
+        try:
+            note = f"{note}\n\n{read_note.read_text(encoding='utf-8').strip()}"
+        except OSError:
+            _log.warning("toolset_note_read.md missing; Read correction omitted")
+    if with_browser:
+        extra = browser_note.browser_note()
+        if extra:
+            note = f"{note}\n\n{extra}"
+    return note
 
 
 class PreinstalledClaudeCode(ClaudeCode):
@@ -138,6 +153,10 @@ class PreinstalledClaudeCode(ClaudeCode):
     in the trial config's ``agent.import_path``.)
     """
 
+    # Set by _probe_browser() during install(); read by build_cli_flags(). Declared
+    # here so the full-toolset subclass (which skips the probe) still has a value.
+    _has_browser = False
+
     @staticmethod
     def name() -> str:
         return "claude-code-reduced-toolset"
@@ -176,6 +195,14 @@ class PreinstalledClaudeCode(ClaudeCode):
         editor CLI) and reuses ``_ensure_claude_binary`` directly."""
         await self._stage_agent_cli(environment)
         await self._ensure_claude_binary(environment)
+        await self._probe_browser(environment)
+
+    async def _probe_browser(self, environment) -> None:
+        """Record whether this image ships the Playwright `pw` wrapper, so the toolset
+        note mentions the browser only on images that have one. Runs during install(),
+        which harbor calls before build_cli_flags() reads the result. The probe and the
+        note text are shared with the codex adapter via browser_note.py."""
+        self._has_browser = await browser_note.probe_browser(environment)
 
     async def _ensure_claude_binary(self, environment) -> None:
         """Reuse the claude binary already baked into the task image instead
@@ -243,7 +270,8 @@ class PreinstalledClaudeCode(ClaudeCode):
         subclass overrides this back to stock ``ClaudeCode.build_cli_flags``.
         """
         flags = super().build_cli_flags()
-        extra = f"--tools Bash --append-system-prompt {shlex.quote(_toolset_note())}"
+        note = _toolset_note(with_browser=self._has_browser)
+        extra = f"--tools Bash --append-system-prompt {shlex.quote(note)}"
         return f"{flags} {extra}" if flags else extra
 
     async def _claude_format_session_path(self, environment, env, session_uuid: str) -> str:
@@ -845,6 +873,47 @@ class SnapshotClaudeCode(PreinstalledClaudeCode):
 # once every snapshot session.jsonl is re-recorded in the reduced format.
 
 
+class _BrowserToolsetMixin:
+    """The canonical reduced toolset PLUS the ``Read`` built-in, for tasks that opt into a
+    browser: a screenshot is only useful to an agent that can look at it, and ``Read`` is what
+    turns a PNG on disk into an image the model actually sees.
+
+    This is a SEPARATE AGENT, not a flag, per the rule that the toolset is chosen by which class
+    harbor runs and the class name records it — so a benchmark row can never silently compare an
+    agent that could see against one that couldn't.
+
+    Two things to be clear-eyed about:
+      * ``Read`` is not image-only. It also reads text files, PDFs and notebooks, so these tasks
+        get back a file-reading built-in the reduced toolset deliberately removes. There is no
+        narrower built-in; an image-only MCP tool was rejected because the canonical agent avoids
+        MCP (see the async-MCP startup race note at the top of this file).
+      * Tasks on this agent are not comparable with tasks on the canonical one. That is the point
+        of the distinct name.
+    """
+
+    def build_cli_flags(self) -> str:
+        flags = ClaudeCode.build_cli_flags(self)
+        note = _toolset_note(with_browser=self._has_browser, with_read=True)
+        extra = f"--tools Bash,Read --append-system-prompt {shlex.quote(note)}"
+        return f"{flags} {extra}" if flags else extra
+
+
+class BrowserPreinstalledClaudeCode(_BrowserToolsetMixin, PreinstalledClaudeCode):
+    """Reduced toolset + Read, manual (non-snapshot) tasks."""
+
+    @staticmethod
+    def name() -> str:
+        return "claude-code-reduced-toolset-browser"
+
+
+class BrowserSnapshotClaudeCode(_BrowserToolsetMixin, SnapshotClaudeCode):
+    """Reduced toolset + Read, snapshot tasks."""
+
+    @staticmethod
+    def name() -> str:
+        return "snapshot-claude-code-reduced-toolset-browser"
+
+
 class _FullToolsetMixin:
     """Override the canonical reduced toolset back to Claude Code's stock full
     built-in toolset: no str_replace_editor CLI to stage, and no --tools / note.