after moving all to cipher

worker-toolkit-stocks-in-the-future/explore/scripts/harness-registry.toml

@@ -4,6 +4,11 @@ version = 1
 id = "claude-code"
 label = "Claude Code"
 agent_import_path = "snapshot_agent:SnapshotClaudeCode"
+# `[metadata] browser = true` swaps in these: same reduced toolset plus `Read`, so an agent
+# given a browser can look at the screenshot it just took. Distinct classes with distinct
+# names, because a different toolset is a different agent.
+agent_import_path_browser = "snapshot_agent:BrowserSnapshotClaudeCode"
+agent_import_path_single_turn_browser = "snapshot_agent:BrowserPreinstalledClaudeCode"
 agent_import_path_single_turn = "snapshot_agent:PreinstalledClaudeCode"
 import_path_aliases = [
   "snapshot_agent:FullToolsetSnapshotClaudeCode",
@@ -29,7 +34,7 @@ install = "for i in 1 2 3; do curl -fsSL https://claude.ai/install.sh | bash &&
 # reduction is a launch flag here and `--tools Bash` in snapshot_agent.py for the trial.
 # Two expressions of one intent, which the $RACCOON_AGENT_FLAGS guard cannot police —
 # unlike model and effort, which are interpolated from this row.
-explore_launch = """exec claude --model '$RACCOON_MODEL' --effort $RACCOON_EFFORT --tools Bash --append-system-prompt "$RACCOON_TOOLSET_NOTE" --plugin-dir /workspace/plugins/create-snapshot --dangerously-skip-permissions "$@""""
+explore_launch = """exec claude --model '$RACCOON_MODEL' --effort $RACCOON_EFFORT --tools "$RACCOON_TOOLS" --append-system-prompt "$RACCOON_TOOLSET_NOTE" --plugin-dir /workspace/plugins/create-snapshot --dangerously-skip-permissions "$@""""
 
 [[harness]]
 id = "codex"
@@ -84,7 +89,7 @@ explore_config = """
 SessionStart = [ { hooks = [ { type = "command", command = "/workspace/plugins/create-snapshot/bin/save-session-info.mjs" } ] } ]
 UserPromptSubmit = [ { hooks = [ { type = "command", command = "/workspace/plugins/create-snapshot/bin/checkpoint-workspace.mjs" } ] } ]
 """
-explore_launch = """exec codex $RACCOON_AGENT_FLAGS --model $RACCOON_MODEL -c model_reasoning_effort=$RACCOON_EFFORT --dangerously-bypass-approvals-and-sandbox --dangerously-bypass-hook-trust "$@""""
+explore_launch = """exec codex $RACCOON_AGENT_FLAGS --model $RACCOON_MODEL -c model_reasoning_effort=$RACCOON_EFFORT ${RACCOON_BROWSER_FLAGS[@]+"${RACCOON_BROWSER_FLAGS[@]}"} --dangerously-bypass-approvals-and-sandbox --dangerously-bypass-hook-trust "$@""""
 
 [[harness]]
 id = "gemini-cli"

worker-toolkit-stocks-in-the-future/explore/scripts/lib/harness_registry.py

@@ -36,6 +36,11 @@ class Harness:
     seed_native: bool
     seed_atif: bool
     agent_import_path_single_turn: str | None = None
+    # Browser-opt-in variants (`[metadata] browser = true`). A harness that has no variant
+    # keeps its normal class: codex, for instance, gains the browser and its disclosure but
+    # has no `Read` equivalent to switch toolsets for.
+    agent_import_path_browser: str | None = None
+    agent_import_path_single_turn_browser: str | None = None
     import_path_aliases: tuple[str, ...] = ()
     legacy_bare_model_rows: bool = False
     default_model: str | None = None
@@ -67,9 +72,22 @@ class Harness:
     # be edited in lockstep with the schema.
     extra: dict = field(default_factory=dict, compare=False)
 
-    def agent_import_path_for(self, *, multi_turn: bool) -> str:
+    def agent_import_path_for(self, *, multi_turn: bool, browser: bool = False) -> str:
         """Agent class to launch. Multi-turn tasks need the resuming class; a
-        single-turn task given it would try to resume a session that isn't there."""
+        single-turn task given it would try to resume a session that isn't there.
+
+        ``browser`` selects the opt-in variant, which for claude also carries the ``Read``
+        built-in — a different toolset is a different agent, so it is a different class with
+        its own name rather than a flag on the canonical one. Harnesses without a variant fall
+        through to their normal class."""
+        if browser:
+            variant = (
+                self.agent_import_path_browser
+                if multi_turn
+                else (self.agent_import_path_single_turn_browser or self.agent_import_path_browser)
+            )
+            if variant:
+                return variant
         if multi_turn:
             return self.agent_import_path
         return self.agent_import_path_single_turn or self.agent_import_path
@@ -180,6 +198,8 @@ _KNOWN_FIELDS = frozenset(
         "label",
         "agent_import_path",
         "agent_import_path_single_turn",
+        "agent_import_path_browser",
+        "agent_import_path_single_turn_browser",
         "import_path_aliases",
         "legacy_bare_model_rows",
         "default_model",
@@ -315,6 +335,8 @@ def _build(entry: dict, index: int) -> Harness:
         label=entry["label"],
         agent_import_path=entry["agent_import_path"],
         agent_import_path_single_turn=entry.get("agent_import_path_single_turn"),
+        agent_import_path_browser=entry.get("agent_import_path_browser"),
+        agent_import_path_single_turn_browser=entry.get("agent_import_path_single_turn_browser"),
         import_path_aliases=tuple(entry.get("import_path_aliases", ())),
         legacy_bare_model_rows=bool(entry.get("legacy_bare_model_rows", False)),
         default_model=entry.get("default_model"),

worker-toolkit-stocks-in-the-future/explore/scripts/resolve_harness.py

@@ -36,6 +36,7 @@ from __future__ import annotations
 import argparse
 import json
 import os
+import re
 import shlex
 import sys
 import tomllib
@@ -77,6 +78,26 @@ def is_multi_turn(task_dir: str | None) -> bool:
     return session.is_file() and session.stat().st_size > 0
 
 
+def wants_browser(task_dir: str | None) -> bool:
+    """True when task.toml opts into a browser (`[metadata] browser = true`).
+
+    Read straight from the file rather than via tomllib: this must agree with
+    build-workspace.sh, which decides whether the IMAGE gets Playwright using the same
+    text match. If the two ever disagree the agent is told about a browser the image
+    lacks, which is the one failure the disclosure is designed to make impossible.
+    Accepts the quoted form for the same reason build-workspace.sh does."""
+    if not task_dir:
+        return False
+    toml_path = Path(task_dir) / "task.toml"
+    if not toml_path.is_file():
+        return False
+    try:
+        text = toml_path.read_text(encoding="utf-8")
+    except OSError:
+        return False
+    return re.search(r'^[ \t]*browser[ \t]*=[ \t]*"?true"?[ \t]*$', text, re.M) is not None
+
+
 def harness_from_task_toml(task_dir: str | None) -> str | None:
     """The task's own `[agent] harness` — the authoritative record of which harness
     this task was authored against.
@@ -388,8 +409,9 @@ def main(argv: list[str] | None = None) -> int:
 
     # Every assignment here becomes a harbor flag. Nothing else: the caller is bash, and
     # anything it would only echo back at the worker is said below instead.
+    browser = wants_browser(args.task_dir)
     assignments = {
-        "AGENT_IMPORT_PATH": harness.agent_import_path_for(multi_turn=multi_turn),
+        "AGENT_IMPORT_PATH": harness.agent_import_path_for(multi_turn=multi_turn, browser=browser),
         "MODEL": normalize_model(harness, model),
         "EFFORT_KWARG": harness.effort_kwarg,
         "EFFORT_VALUE": (harness.effort_default or "") if harness.effort_kwarg else "",
@@ -398,8 +420,17 @@ def main(argv: list[str] | None = None) -> int:
     warn(
         f"{harness.label} · model={assignments['MODEL']} · "
         f"{'multi-turn' if multi_turn else 'single-turn'} · "
+        f"{'browser · ' if browser else ''}"
         f"agent={assignments['AGENT_IMPORT_PATH']}"
     )
+    if browser and not harness.agent_import_path_browser:
+        # Not a failure: the image still gets Playwright and the agent is still told about
+        # it. Only the Read-enabled toolset swap is claude-specific, and saying so beats
+        # letting someone infer from a log line that the opt-in was ignored entirely.
+        warn(
+            f'"{harness.id}" has no browser-specific agent, so it runs its usual toolset. '
+            f"The browser and its disclosure are unaffected."
+        )
     if harness.flaky_hangs:
         warn(
             f"{harness.label} is known to hang with no client-side timeout on a small "

worker-toolkit-stocks-in-the-future/explore/scripts/setup-harnesses.sh

@@ -113,11 +113,24 @@ harness_install_launchers() {
     mkdir -p "$bin"
     # Read at launcher run time so the note stays a file, not a baked-in copy.
     local note_src="${HARNESS_TOOLSET_NOTE:-/workspace/scripts/toolset_note.md}"
+    local browser_note_src="${note_src%.md}_browser.md"
+    local read_note_src="${note_src%.md}_read.md"
     local agent_cli_dir="${AGENT_CLI_DIR:-/opt/agent-cli}"
 
-    local id cli launch
+    local id cli launch switchable
     while IFS=$'\t' read -r id cli launch; do
         [ -n "$cli" ] && [ -n "$launch" ] || continue
+        # Whether RACCOON_BROWSER_TASK can change THIS harness's toolset, read off the
+        # registry rather than hardcoded: a launch line that interpolates $RACCOON_TOOLS
+        # can, and one that doesn't cannot. codex is the second case — it ships view_image,
+        # so a browser task needs nothing added and the flag has nothing to switch.
+        # Match the whole variable name: a substring test also hits RACCOON_TOOLSET_NOTE,
+        # which every launch line references, and every harness would look switchable.
+        if [[ "$launch" =~ \$\{?RACCOON_TOOLS\}?([^A-Za-z0-9_]|$) ]]; then
+            switchable=1
+        else
+            switchable=0
+        fi
         cat > "$bin/raccoon-explore-$cli" <<LAUNCHER
 #!/bin/bash
 # GENERATED by scripts/setup-harnesses.sh from harness-registry.toml — do not edit.
@@ -127,7 +140,38 @@ if [ -f "$note_src" ]; then
 else
     RACCOON_TOOLSET_NOTE=""
 fi
-export RACCOON_TOOLSET_NOTE
+# RACCOON_BROWSER_TASK=1 explores with the toolset a \`browser = true\` task runs under.
+# Named for the flag it mirrors: one word, \`browser\`, whether it's set in task.toml or
+# here. Per invocation, not per container — authoring a browser task shouldn't need a
+# rebuild, and neither should changing your mind. Default off, so ordinary exploring
+# still mirrors an ordinary trial.
+#
+# The correction must be appended AFTER the base note, which says there is no Read tool.
+RACCOON_TOOLS="Bash"
+if [ "\${RACCOON_BROWSER_TASK:-0}" = "1" ] && [ "$switchable" = "1" ] && [ -f "$read_note_src" ]; then
+    RACCOON_TOOLS="Bash,Read"
+    RACCOON_TOOLSET_NOTE="\${RACCOON_TOOLSET_NOTE}
+
+\$(cat "$read_note_src")"
+fi
+export RACCOON_TOOLS
+# Only mention the browser on an image that actually has one — most don't. Probed at
+# launch, not baked in, so the same launcher is correct in whichever container it runs.
+#
+# Exported two ways because the harnesses take extra instructions differently: claude
+# appends the whole toolset note to --append-system-prompt, while codex has no equivalent
+# and takes -c developer_instructions=. codex must NOT get the claude-shaped toolset note
+# (it has no str_replace_editor), so the browser part is exported on its own too.
+RACCOON_BROWSER_NOTE=""
+RACCOON_BROWSER_FLAGS=()
+if command -v pw >/dev/null 2>&1 && [ -f "$browser_note_src" ]; then
+    RACCOON_BROWSER_NOTE="\$(cat "$browser_note_src")"
+    RACCOON_TOOLSET_NOTE="\${RACCOON_TOOLSET_NOTE}
+
+\${RACCOON_BROWSER_NOTE}"
+    RACCOON_BROWSER_FLAGS=(-c "developer_instructions=\${RACCOON_BROWSER_NOTE}")
+fi
+export RACCOON_TOOLSET_NOTE RACCOON_BROWSER_NOTE
 export RACCOON_HARNESS="$id"
 # No RACCOON_SNAPSHOT_DATA here on purpose. capture-snapshot.mjs and save-session-info.mjs
 # already share the same default ($HOME/.raccoon/snapshot-data), which is what codex needs
@@ -143,11 +187,33 @@ LAUNCHER
 
 # Alias lines for ~/.bashrc.
 harness_alias_lines() {
-    local id cli launch
+    local id cli launch switchable
+    local browser_clis=""
     while IFS=$'\t' read -r id cli launch; do
         [ -n "$cli" ] && [ -n "$launch" ] || continue
         echo "alias $cli=\"raccoon-explore-$cli\""
+        # Same derivation as the launcher: only a harness whose launch line takes
+        # $RACCOON_TOOLS has a toolset the flag can change.
+        if [[ "$launch" =~ \$\{?RACCOON_TOOLS\}?([^A-Za-z0-9_]|$) ]]; then
+            browser_clis="${browser_clis:+$browser_clis }$cli"
+        fi
     done < <(_harness_query --explore-launchers 2>/dev/null || true)
+
+    # The browser hint belongs at the shell prompt, not in the launcher. Claude Code takes the
+    # alternate screen buffer, so anything printed just before exec is hidden for the whole
+    # session and resurfaces only after quitting — advice arriving exactly too late. Here it
+    # lands in ordinary scrollback, before any TUI exists, and there is nothing to quit yet.
+    #
+    # `pw` is probed at shell start, so one ~/.bashrc is correct in a container with a browser
+    # and in one without.
+    [ -n "$browser_clis" ] || return 0
+    local first="${browser_clis%% *}"
+    cat <<HINT
+if [[ \$- == *i* ]] && [ "\${RACCOON_BROWSER_TASK:-0}" != "1" ] && command -v pw >/dev/null 2>&1; then
+    echo "browser available (Playwright + Chromium, \\\`pw <script.js>\\\`)."
+    echo "Authoring a \\\`browser = true\\\` task? Start it with:  RACCOON_BROWSER_TASK=1 $first"
+fi
+HINT
 }
 
 # Write each harness's config file from the registry, replacing whatever was there.

worker-toolkit-stocks-in-the-future/explore/scripts/toolset_note_browser.md

@@ -0,0 +1,4 @@
+## Browser
+
+Chromium is available in this environment via Playwright. `pw <script.js>` runs Node with
+`require("playwright")` resolvable (CommonJS — `import` will not find it).

worker-toolkit-stocks-in-the-future/explore/scripts/toolset_note_read.md

@@ -0,0 +1,7 @@
+## Correction to the toolset above: you also have `Read`
+
+This task runs with `Read` in addition to `Bash`, so the statement above that there is no `Read`
+tool does not apply here. `Read` renders images — use it to look at a screenshot you have
+written to disk. Everything else above still holds: no `Grep`, `Glob`, `Edit`, `Write`,
+`MultiEdit`, `NotebookEdit`, `Task`, `TodoWrite` or `AskUserQuestion`, and you still create and
+edit files with `str_replace_editor`.