Commit Graph

5 Commits

Author SHA1 Message Date
93d3f86c2b v2.2-paseo-providers: Paseo provider stack + v2.2.1 pane-scoped chat fixes
Ship Paseo-equivalent provider snapshot, AgentComposerBar, ACP dispatch
rewrite with streaming/persist, permission prompts, and agent commands.
Follow-up: pane-scoped chat resolution, CoderMessageList tool timeline,
WS user-delta replace, and inference orphan tool_call stripping.
Archive openspec v2-2; update CHANGELOG and CURRENT.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-26 15:18:31 +00:00
34cbecf975 v1.13.15-tools: tiered tool loading via BOOCODE_TOOLS env var
Pattern lift from eyaltoledano/claude-task-master (MIT + Commons Clause
— pattern only, no code lift). Adds BOOCODE_TOOLS env var with three
tiers:

- core (4 tools): view_file, list_dir, grep, find_files. ~2k token
  schema cost.
- standard (15 tools): core + web_search, web_fetch, git_status, all
  8 codecontext_* tools. ~10k token schema cost.
- all (default; current behavior): every tool in ALL_TOOLS (20). ~21k
  token schema cost.

The env var is a CEILING — narrows agent whitelists, never expands.
Default behavior unchanged when var is unset. resolveToolTier is
case-insensitive and falls back to 'all' on unknown values.

CORE_TOOL_NAMES + STANDARD_TOOL_NAMES validated at module load against
TOOLS_BY_NAME via two top-level for-loops that throw on the first
missing name. Module fails to import if a tier references a tool that
doesn't exist in the registry — catches typos and stale tier
definitions at boot rather than silently filtering valid tools out of
agent whitelists.

Wiring: agents.ts parseAgentBlock now reads BOOCODE_TOOLS from
process.env per parse, intersects with the agent's declared frontmatter
tools (or DEFAULT_TOOLS when frontmatter omits the field). Per-parse
read is fine — agents are re-parsed on the existing 60s cache TTL.

Tests: tools.test.ts grows from 1 to 10 tests. Covers resolveToolTier
across tiers/case/unknown values + the CORE-subset-of-STANDARD invariant
+ TOOLS_BY_NAME existence for both tier sets. 204/204 pass (was 195;
+9 new).

Deviation from the brief: the codecontext tools in the actual registry
have NO codecontext_* prefix (the brief's STANDARD list assumed it).
Used the actual names (get_codebase_overview, search_symbols, etc.).
Module-load validation would have failed boot with the prefixed names.

Smoke: with BOOCODE_TOOLS unset, agents return their full 12-tool
whitelists. With BOOCODE_TOOLS=core in .env + container restart, the
same agents narrow to 4 tools (find_files, grep, list_dir, view_file)
— intersection of declared whitelist ∩ core tier. Reverted after
confirmation.

CLAUDE.md updated with BOOCODE_TOOLS in the Environment section's
Optional list. .env.example gained a commented BOOCODE_TOOLS=all line
with the per-tier token-cost table.

~110 LoC across 5 files (4 modified + 1 test expansion). Under the
brief's ~30 LoC estimate for code; the test suite expansion drove
most of the growth.
2026-05-22 14:59:01 +00:00
2fdbb05477 v1.11.8: web_search + web_fetch tools via SearXNG
Adds two new tools registered through the existing ALL_TOOLS registry:
  - web_search hits SearXNG's JSON API (Fathom, internal Tailscale URL,
    no auth) and returns top results
  - web_fetch retrieves a URL's text content, gated by isPublicUrl
    (url_guard.ts) which blocks loopback / RFC1918 / Tailscale CGNAT /
    link-local / .local / .internal / non-http schemes

Both tools are opt-in via the existing session.web_search_enabled flag
(plumbed in v1.9, activated here). Default off. UI labels updated to
"Enable web search and fetch" / "Web search and fetch" since fetch joins
the same store. Counts against the v1.8.2 per-turn budget; covered by
the v1.11.6 doom-loop guard.

Native Node 20 fetch — no new prod dep. HTML stripping via regex (script
and style content elided wholesale). 5MB body cap, 15s fetch timeout,
8000-char default output, 32000-char cap.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 21:38:02 +00:00
7f0fd1281b security: scope /opt mount to /opt/projects
Splits the previous /opt:/opt:rw bind into two mounts to narrow the
writable scope of the container:

- /opt:/opt:ro — read-only mount for legacy/existing project
  add-existing flow. resolveProjectPath still uses
  PROJECT_ROOT_WHITELIST (/opt by default) so existing projects under
  /opt/<name> (analytics, boolab, boocode itself) continue to resolve
  and serve their file-tree via the read-only tools.
- /opt/projects:/opt/projects:rw — writable mount targeted at the
  create-new-project bootstrap path.

Picked Option B from the spec (simpler than two scan roots):
PROJECT_ROOT_WHITELIST stays /opt, new BOOTSTRAP_ROOT env var defaults
to /opt/projects and is used by project_bootstrap.ts as the mkdir
target. Bootstrap path-escape check now compares against
BOOTSTRAP_ROOT.

Prereq: host must `mkdir -p /opt/projects` before next container
restart. Documented in CLAUDE.md and .env.example.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 04:35:59 +00:00
a7f218e182 initial 2026-05-14 19:24:50 +00:00