Commit Graph

18 Commits

Author SHA1 Message Date
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
f92b0810c3 v1.11.6: doom-loop guard (3 identical tool calls aborts recursion) 2026-05-20 20:28:45 +00:00
89dcfb95dc v1.11.3: fix ctx_max capture via /props endpoint
- llama-server does not emit n_ctx in timings (confirmed empirically);
  dead code at inference.ts:479 and compaction.ts:300 never fired
- New model-context.ts: cached fetch of /upstream/<model>/props
  with positive-cache (no TTL) and 60s negative-cache
- Wired into all 4 ctx_max write sites: 3 in inference.ts
  (executeToolPhase, finalizeCompletion, runCapHitSummary) and
  1 in compaction.ts (summary row INSERT)
- AbortController 3s timeout, lenient parsing with sensible defaults
- 12 new vitest cases for the cache module (59 total)
- 7 historical assistant rows backfilled manually (see notes)
2026-05-20 19:29:26 +00:00
dc43dd44f9 v1.11: opencode-style compaction port
- compaction.ts: usable/isOverflow/estimate/turns/select/buildPrompt/process
- compaction-prompt.ts: SUMMARY_TEMPLATE verbatim from opencode
- schema: messages.{compacted_at,summary,tail_start_id} + chats.needs_compaction
- inference: auto-trigger on overflow, pre-fetch compaction before next turn
- /compact slash command rewired to new path
- WS: chat_status working/idle around compaction + compacted frame
- frontend: SummaryCard + sonner toast on compacted
- 24 unit tests for pure functions
2026-05-20 19:05:35 +00:00
8cea4a899c v1.10.5: inference XML tool-call fallback parser
Some local models (qwen3-coder via llama-swap) emit tool calls as inline XML
inside delta.content rather than structured delta.tool_calls. streamCompletion
now buffers delta.content, extracts complete <tool_call>...</tool_call> blocks
via parseXmlToolCall, and pushes synthetic entries (id prefix xml_call_) into
the existing toolCallsBuffer. Native JSON path unchanged — both coexist.
Partial openers are held back so a tool tag never leaks to the chat mid-tag.
Unclosed XML at end-of-stream is flushed as plain content (no silent drops).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 17:32:42 +00:00
d85b17081e v1.9.7: ask_user_input elicitation tool 2026-05-18 02:15:18 +00:00
09aecc4ee9 v1.9: settings pane + per-project defaults + bulk archive + themes lift
Adds a singleton, ephemeral 'settings' pane kind to the workspace.
Opened via a new bottom-pinned button in ProjectSidebar (emits an
open_settings_pane event when a session is mounted; navigates to
/settings otherwise). Pane has three sections — Session, Project,
Theme — and a maximize toggle that hides sibling pane columns via
display:none on desktop only. Settings panes don't count toward
MAX_PANES and are filtered out of the localStorage persistence layer
so reload always restores a clean workspace.

Schema (additive):
- projects.default_system_prompt TEXT NOT NULL DEFAULT ''
- projects.default_web_search_enabled BOOLEAN NOT NULL DEFAULT false
- sessions.web_search_enabled BOOLEAN  (nullable; null = inherit)

Inference resolves user_prompt = session.system_prompt.trim() ||
project.default_system_prompt.trim() — empty/whitespace at either
layer means "no override". Keeps the columns NOT NULL and matches
the existing inherit semantics.

Server routes:
- GET /api/projects/:id (new; settings pane refetches on
  project_updated)
- PATCH /api/projects/:id accepts default_system_prompt,
  default_web_search_enabled
- PATCH /api/sessions/:id accepts web_search_enabled (tri-state)
- POST /api/projects/:id/sessions/archive-all + GET
  /api/projects/:id/sessions/open-count
- POST /api/sessions/:id/chats/archive-all + GET
  /api/sessions/:id/chats/open-count
- PATCH /api/sessions/:id now broadcasts session_updated on every
  successful PATCH (was rename-only). Lets SettingsPane open in
  another tab pick up edits without a refetch.

Bulk-archive publishes one session_archived / chat_archived frame
per affected id so useSidebar's existing reducer cases handle them
incrementally — no new frame type, no payload widening.

ModelPicker refactored: shared ModelList inside a responsive shell.
Desktop = labeled trigger + DropdownMenu, mobile = icon-only Cpu
button + BottomSheet. Header in Session.tsx drops the pill wrap on
mobile since the new trigger is the visual.

ChatInput gains an icon-only '+' DropdownMenu next to AgentPicker
when sessionId + webSearchEnabled props are provided. One item for
now — Web search — with a checkmark reflecting the stored value
(true), not the effective one. Click PATCHes the override; to
restore inherit-from-project the user opens SettingsPane.

ThemePicker lifted out of pages/Settings.tsx into a reusable
component. The standalone /settings route is now a thin wrapper
that mounts <ThemePicker /> with a Back button on top
(navigate(-1) with fallback to '/'); the SettingsPane Theme tab
renders the same picker bare.

Project section delete-flow removed (button + confirm dialog +
handler). Replaced with "Archive all sessions" using the same
two-step count → confirm → fire pattern as "Archive all chats" in
the Session section. api.projects.remove() stays in the client
because useProjects.ts still uses it.

Hand-rolled Switch primitive in SettingsPane (no shadcn switch in
the project; spec said no new deps). Section nav is plain buttons
(no shadcn Tabs).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-17 17:37:29 +00:00
5c61cc7281 v1.8.2: tool loop cap-hit summary + tool call UI compaction
Old hardcoded MAX_TOOL_LOOP_DEPTH=15 replaced by per-agent
max_tool_calls (1-100, AGENTS.md frontmatter) with defaults: 30 for
read-only-only agents, 10 for agents that include any non-read-only
tool, 15 for raw chat. When the loop hits cap, fire one final summary
call with tools disabled, stream the wrap-up into the in-flight
assistant message, then insert a system sentinel with
metadata.kind='cap_hit'. The sentinel renders an amber bubble with a
Continue button (latest sentinel only) that POSTs to a new
/api/chats/:id/continue route to extend. Hard ceiling: 3 cap-hits per
chat (2 continues max) — third sentinel reports can_continue=false.

Error frames carry a machine-readable reason code alongside human
error text. Failed messages persist the reason via
metadata.kind='error' so the bubble renders specifics on reload (WS
error frame is one-shot).

Tool call UI rewired: ToolCallLine renders inline (↳ name args
spinner/check/✗, expand-on-tap for args+result); ToolCallGroup
collapses 3+ consecutive same-tool runs into a compact card.
MessageList owns a three-pass pre-render (flatten + fold tool
results onto matching runs by id + group same-tool runs + number
sentinels). MessageBubble drops tool rendering and adds the
sentinel / error-reason branches. ToolCallCard deleted.

Roadmap follow-up logged: add explicit max_tool_calls: 30 to the 6
agents in /data/AGENTS.md and /opt/boocode/AGENTS.md post-ship for
discoverability (defaults handle behavior identically).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-17 10:31:32 +00:00
2bce4d85fa feat(mobile): v1.8 tab switcher + branch indicator + git_status tool
Mobile header is now two rows. Row 1: hamburger | project · branch
indicator (live via GET /api/projects/:id/git, 30s poll) | ModelPicker |
FolderTree. Row 2: pane-switcher pill (hand-rolled BottomSheet) +
NewPaneMenu. Chat-within-pane navigation hidden on mobile; users switch
panes via the sheet. Cross-tab status sync via chat_status frames
published from inference.ts at working/idle/error transitions; StatusDot
component renders amber-pulse/green/red/gray on each pane row and on
desktop ChatTabBar tabs. Level 1 git awareness exposes a read-only
git_status tool to the model, backed by services/git_meta.ts (execFile
+ 2s timeout + 30s cache). Workspace.tsx now receives panes/chats hooks
as props (hoisted into Session.tsx) so the header pill shares state
with the pane grid.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 20:07:53 +00:00
92bd3b1cdf feat(agents): Tier 2 — AGENTS.md + per-session picker
Six builtin defaults (Code Reviewer, Debugger, Refactorer, Architect,
Security Auditor, Prompt Builder) with no model field so session.model
wins. Project root AGENTS.md parsed on demand with mtime cache; when
present, only its agents are shown. sessions.agent_id resolves per turn
into effective system prompt, temperature, and a tool whitelist applied
in inference. AgentPicker mounts in the ChatInput toolbar; SettingsDrawer
agent surface deferred to Batch 7.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 20:06:51 +00:00
6fa6eb7f32 feat(inference): raise MAX_TOOL_LOOP_DEPTH from 5 to 15
Allows assistant turns up to 15 tool calls in a single chain before
the loop-depth guard trips. Real chats commonly need 6-10 tool calls
(grep -> view_file -> view_file -> grep -> view_file -> answer); the
old cap of 5 was firing on legitimate investigation patterns.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 06:37:27 +00:00
9436a81b5f refactor: split FileBrowserPane / Workspace / runAssistantTurn
- FileBrowserPane.tsx: deleted (unreferenced post-v1.4 PaneTab.tsx removal;
  the legacy file_browser pane kind isn't part of the active WorkspacePane
  taxonomy).
- Workspace.tsx (524 -> 172 lines): extracted useWorkspacePanes(sessionId)
  and useSessionChats(sessionId) hooks. Workspace is layout-only composition
  now. localStorage key + WS frame handling + drag semantics unchanged.
- inference.ts runAssistantTurn (~265 -> 48 lines): bundled args into
  TurnArgs interface, extracted executeStreamPhase / executeToolPhase /
  finalizeCompletion / handleAbortOrError. All WS publish ordering preserved
  byte-for-byte (mentally traced for tool / non-tool / abort / error /
  depth-exceeded paths). flushPromise chain + setImmediate + signal
  propagation unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 04:35:20 +00:00
59fe6f0522 v1.4-fork-header: fork from message + delete message + header polish + housekeeping
- Fork: POST /api/chats/:id/fork creates a new chat in the same session,
  copies messages up to target (status=complete) with row-offset
  clock_timestamp() for stable ordering. Client emits open_chat_in_active_pane
  event; Workspace opens it in the active pane. No maybeAutoNameChat on forks.
- Delete: DELETE /api/chats/:id/messages/:message_id with 409 if the chat is
  currently streaming. Cascading-forward delete (created_at >= target).
  MessageBubble Trash button + confirm Dialog.
- Header: Projects -> Project -> Session breadcrumb, model badge pill,
  inline session rename, active file path via new useActivePane() hook.
  Server now publishes session_renamed on PATCH /api/sessions/:id;
  client-side dup emit removed from Session.tsx.
- Housekeeping: NOW() -> clock_timestamp() in schema.sql defaults, dead
  PaneTab.tsx and panes/PaneShell.tsx removed, session_panes backfill
  INSERT removed (CREATE TABLE retained), Tailnet trust comment near
  app.listen().

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-16 04:12:01 +00:00
c35ec65fc4 batch4: chats-in-sessions, force-send, /compact, right-rail file browser
Session 1:N Chat data model with backfill. Workspace switches to client-side
multi-tab pane management. Right-rail file browser with float-over viewer and
click-drag line selection replaces FileBrowserPane. Adds /compact streaming
summarizer (respects compact markers in context builder), force-send (cancels
in-flight, persists partial as 'cancelled', awaits cancellation completion via
deferred Promise + 5s timeout), message queue, stop generation, chat
auto-rename, session archive/unarchive with Closed Sessions section on repo
landing page. CHECK constraints on sessions.status, messages.role,
messages.status with KEEP IN SYNC comments tying to MESSAGE_ROLES /
MESSAGE_STATUSES const arrays. Deletes dead pane routes/hook and the
api.panes.* client block.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-15 20:39:48 +00:00
8fc525eab9 batch3 T3: broker user channel + /api/ws/user + project/session/inference emits
- broker.subscribeUser/publishUser via separate user topics map
- /api/ws/user WS route subscribes to the user channel
- projects/sessions POST/DELETE handlers emit lifecycle frames
- inference 3 terminal-state sites emit session_updated with RETURNING

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-15 15:06:31 +00:00
842cf146ec v1.1 batch 2: sidebar restructure — chats under projects, max 5 + view-all, live updates
Schema (idempotent):
  ALTER TABLE sessions ADD COLUMN IF NOT EXISTS updated_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp();
The column already exists from v1 (DEFAULT NOW()); ALTER is a no-op kept for
self-documentation. Explicit clock_timestamp() bumps now run wherever the
column actually matters — see services/inference.ts and routes/sessions.ts.

Backend updated_at maintenance:
- services/inference.ts: after each terminal status UPDATE on the assistant
  message (failure / tool-call complete / clean complete), also bump
  sessions.updated_at = clock_timestamp() so the parent session jumps to
  the top of recency ordering on every assistant turn.
- routes/sessions.ts PATCH: NOW() → clock_timestamp() for consistency.

New endpoint GET /api/sidebar (routes/sidebar.ts):
  { projects: [{ id, name, recent_sessions[≤6], total_sessions }] }
One outer query for projects ordered added_at DESC; per-project Promise.all
over (recent_sessions LIMIT 6 ORDER BY updated_at DESC) and COUNT(*)::int.
Outer Promise.all parallelizes across projects. Two queries per project; the
composite idx_sessions_project(project_id, updated_at DESC) serves the inner
query. Auth via the global Remote-User hook. types/api.ts gains
SidebarSession / SidebarProject / SidebarResponse; index.ts wires the route.

Frontend foundations:
- api/types.ts mirrors the three sidebar interfaces.
- api/client.ts: api.sidebar.get() → Promise<SidebarResponse>.
- hooks/sessionEvents.ts: five-variant union — added project_created,
  project_deleted, session_created, session_deleted. session_renamed
  unchanged from Batch 1. Bus internals untouched (still a dumb
  Set<Listener>, no validation).

New hooks/useSidebar.ts (module-singleton):
- Module-scope sharedData/sharedError/sharedLoading/initialized/fetchInFlight/
  subscribers; a single sessionEvents.subscribe at module-top-level mutates
  sharedData via an exhaustive switch over the five events. load() dedupes
  parallel calls via fetchInFlight. Hook is a thin subscription layer: any
  number of mount points share state and the very first one triggers the
  single GET /api/sidebar. Subsequent mounts read cached state synchronously
  (no skeleton flash). Public shape: { data, error, loading, retry }.
- Lift to module-scope was driven by the "ONE sidebar request on mount"
  spec promise — both ProjectSidebar AND Home consume the hook now, and
  they share the singleton.

Frontend UI:
- components/ProjectSidebar.tsx (rewrite, 234 lines): per-project chevron +
  folder + name; chevron toggles expand, name navigates /project/:id.
  Expanded → ≤5 sessions with MessageSquare + name + muted relTime()
  timestamp. "View all (N)" link when total_sessions > 5, routing to
  /project/:id. Active session row uses bg-sidebar-accent. Active project
  always renders expanded (URL-derived: direct /project/:id or scan of
  recent_sessions for /session/:id). Expanded ids persisted in
  localStorage['boocode.sidebar.expanded'] with try/catch on both read and
  write. Loading shows 4 muted-pulse skeleton blocks; empty + error +
  retry button; error toast guarded by ref so it fires once per distinct
  message and resets on recovery. Remove path calls api.projects.remove
  directly + explicit project_deleted emit (replaced the prior
  useProjects() dependency which fired a redundant /api/projects on
  mount, violating the one-fetch promise).
- components/AddProjectModal.tsx: captures returned Project and emits
  project_created before onAdded() / onOpenChange(false).
- pages/Project.tsx: emits session_created after create(); trash button is
  now async with try/catch — emits session_deleted on success,
  toast.error on failure.
- pages/Home.tsx: switched from useProjects to useSidebar so loading /
  fires exactly one /api/sidebar, with no parallel /api/projects.
- pages/Session.tsx: manual inline rename now emits session_renamed on
  the success path so the sidebar updates live without a refresh (also
  fixes the regression made visible by Batch 2 — the sidebar caches
  session names where the project page used to re-fetch on every visit).

useProjects.ts retains a project_deleted emit inside remove for any future
caller; no live consumer uses it (ProjectSidebar calls api.projects.remove
directly). Acknowledged dead code, to be removed in the next cleanup pass
along with three remaining NOW() → clock_timestamp() consistency flips at
routes/messages.ts:70, routes/messages.ts:127, and services/auto_name.ts:144.

Cross-tab parity for session_created/session_deleted/project_created/
project_deleted is deferred — those events are tab-local in Batch 2 per
spec. session_renamed continues to propagate cross-tab via the existing
WS frame from Batch 1.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-15 14:19:59 +00:00
2464d23bb6 v1.1 batch 1: markdown, message actions, tok/s+ctx, AI naming
Four features land together on this branch:

1. Markdown rendering — assistant messages go through react-markdown +
   remark-gfm. Fenced code blocks render via existing CodeBlock (with copy
   button); inline `code` is styled inline. User messages stay plain text.
   No raw HTML (no rehype-raw).

2. Per-message Copy + Regenerate. New endpoint
   POST /api/sessions/:id/messages/:message_id/regenerate validates the
   target (404/400/409), atomically deletes the target plus any later
   messages in the session, inserts a fresh streaming assistant row, and
   enqueues a normal inference run. The DELETE bound uses a SQL subquery
   (`created_at >= (SELECT created_at FROM messages WHERE id = $1)`)
   instead of a JS round-trip so postgres TIMESTAMPTZ µs precision is
   preserved — otherwise sub-ms clock_timestamp() differences between the
   user row and the assistant row collapsed to the same JS Date, pulling
   the triggering user message into the >= bound. New `messages_deleted`
   WS frame so already-connected clients prune the stale tail without
   needing a full snapshot resend.

3. tok/s + ctx counter. Five new nullable message columns: tokens_used,
   ctx_used, ctx_max, started_at, finished_at. started_at is set right
   before the OpenAI call in services/inference.ts (not in the route, not
   in the frame handler); finished_at + tokens_used + ctx_used + ctx_max
   are committed in the same UPDATE that flips status to 'complete'. The
   inference request now opts into stream_options.include_usage so the
   final chunk carries usage; defensive parsing also picks up timings.n_ctx
   when llama.cpp emits it (currently absent for our llama-swap models, so
   ctx_max stays NULL and the UI just shows `<used> ctx`). message_complete
   frame extended with tokens_used / ctx_used / ctx_max / started_at /
   finished_at / model. Frontend StatsLine in MessageBubble computes tok/s
   client-side from the timestamps and renders muted mono text below the
   body of completed assistant messages.

4. AI chat naming after the first turn. Backend services/auto_name.ts
   runs via setImmediate after the top-level inference resolves; it
   checks that there is exactly one completed assistant message and that
   the session has not been user-renamed (`name IS NULL OR name = '' OR
   name = 'New session'`), then fires a single non-streaming chat
   completion with the spec prompt. Qwen3 chat templates emit chain-of-
   thought into reasoning_content and burn the entire max_tokens budget
   without producing visible output, so the request includes
   `chat_template_kwargs: { enable_thinking: false }` and max_tokens=30.
   Title is trimmed, quote-stripped, "Title:" prefix dropped, and
   truncated to 60 chars before a guarded UPDATE on sessions.name. New
   `session_renamed` WS frame propagates to the open session view
   directly and to the project's session list via a tiny module-scope
   event bus (apps/web/src/hooks/sessionEvents.ts) — kept dumb: one event
   type, two methods, no library.

Cleanups: dropped the now-unused splitCodeBlocks export from CodeBlock.tsx
(react-markdown supersedes it), and added a long-form NOTE in auto_name.ts
documenting the enable_thinking + max_tokens pattern for any future Qwen-
family non-streaming utility calls (planned: fork-message, agent-routing,
web-search summarization).

Schema bootstrap remains idempotent (ADD COLUMN IF NOT EXISTS). Auth,
broker, clock_timestamp() conventions, and zod validation all unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-14 22:52:40 +00:00
a7f218e182 initial 2026-05-14 19:24:50 +00:00