Commit Graph

120 Commits

Author SHA1 Message Date
eef4782383 v1.12.3: stale-stream banner with Retry/Discard
When an assistant message sits status='streaming' with no token activity
for 60+ seconds, the chat shows a banner above the input offering Retry
or Discard. Both clear the stale row via a new backend endpoint
POST /api/chats/:id/discard_stale that updates status='failed' and
publishes chat_status='idle'.

Closes the UX gap that caused the 2026-05-21 debugging spiral —
slow streams and dead streams now look different to the user.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
v1.12.3-stale-banner
2026-05-21 20:48:22 +00:00
a7104691aa v1.12.2: live tok/s + ctx display next to status indicator
ChatThroughput renders inline beside StatusDot while streaming or
tool_running. Subscribes to existing usage frames via sessionEvents.
Hides when status drops to idle/error or data is older than 10s.

Addresses the 2026-05-21 spike's UX gap where slow streams looked
identical to dead streams — now there's a live token velocity readout
that immediately distinguishes the two.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
v1.12.2-live-toks
2026-05-21 20:45:53 +00:00
1a0a3b1673 v1.12.1: stop-handler writes terminal status + constraint cleanup + dead code removal
- handleAbortOrError now writes status='cancelled' on user stop; rows
  no longer stuck 'streaming' forever
- Drop stale messages_status_check constraint (only messages_status_chk
  remains, allowing 'cancelled' via TS MESSAGE_STATUSES)
- Remove detectSameNameLoop and DOOM_LOOP_SAME_NAME_THRESHOLD (added
  during 2026-05-21 debugging spike, never fired in any real run,
  existing detectDoomLoop covers actual failure modes)
- Remove 12 ctx.log.info diagnostic markers added during the same
  spike (verbose for production)
- Bundles workspace pane sync + status indicator overhaul +
  startup hung-row sweep landed earlier in v1.12.1 work

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
v1.12.1-stop-handler
2026-05-21 20:34:40 +00:00
48ee63a286 v1.12.1: rich status indicator + server-side workspace pane sync
Status indicator (StatusDot): drops the flat amber pulse for a richer set
of states — orbiting amber for streaming, spinning sky ring for tool_running,
static violet for waiting_for_input, plus the existing idle/error. Backend
chat_status frame widens from 'working|idle|error' to discriminate streaming
vs tool execution vs paused for user input.

Workspace pane sync: pane layout moves from per-device localStorage to
server-side sessions.workspace_panes jsonb. PATCH /api/sessions/:id/workspace
broadcasts session_workspace_updated on the user channel for cross-device live
sync. Echo dedup via JSON comparison so the round-trip frame doesn't loop.
Legacy localStorage seeds the server on first hydrate, then is deleted.
Deprecated session_panes table dropped.

Resilience: startup sweep marks any stale 'streaming' message older than
5 minutes as 'failed' so v1.12.0-style hung rows clear on container restart.
useWorkspacePanes gains validatePanes() to prune dead chatId references from
saved pane state when the chat list lands.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-21 20:32:02 +00:00
d58d553503 v1.12.1: same-name doom-loop guard + runAssistantTurn trace logging
Add detectSameNameLoop (threshold 5) to catch over-verification hangs
where tool args vary but the model is stuck on one tool. Add 12 structured
log points across the inference state machine (runAssistantTurn,
executeToolPhase, runDoomLoopSummary) to diagnose the deterministic hang
surfaced in v1.12.0 smoke testing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-05-21 17:15:02 +00:00
fce8c06932 Merge v1.11.10 + doc refinements onto v1.12.0 main
# Conflicts:
#	CLAUDE.md
2026-05-21 15:22:46 +00:00
684612f3cd docs: capture v1.12 learnings in CLAUDE.md (whitelist drift, AGENTS.md single source, MCP NDJSON framing) 2026-05-21 15:19:46 +00:00
16c69a38a1 Merge v1.12 track B: codecontext sidecar
# Conflicts:
#	apps/web/src/components/ToolCallLine.tsx
#	docker-compose.yml
v1.12.0-codecontext
2026-05-21 15:12:30 +00:00
be3c38ff2f Merge v1.12 track A: container guidance + skills 2026-05-21 15:11:12 +00:00
a2e2481ef9 v1.12 track A: container guidance + skills 2026-05-21 15:11:04 +00:00
78914466d1 v1.12 track B.3: agent whitelists + .codecontextignore template + CLAUDE.md updates
Removed /opt/boocode/AGENTS.md (per-project override) — the project's
agents now resolve from the global /data/AGENTS.md only. Eliminates the
two-files-must-stay-in-sync footgun that surfaced during B.3
verification.

Fix: agents.ts ALL_TOOL_NAMES was a hardcoded 9-item whitelist that
silently filtered any unknown tool name from agent.tools arrays. This
caused web_search/web_fetch (v1.11.8) and the 8 codecontext tools to be
dropped at parse time. Replaced with ALL_TOOLS.map(t => t.name) for
single source of truth. Pre-existing exposure was dormant since no
builtin agent listed web_search; surfaced by adding codecontext.
2026-05-21 15:09:11 +00:00
136e9538aa v1.12 track B.2: codecontext tool wrappers + tests 2026-05-21 13:35:44 +00:00
4fae77e526 v1.12 track B.1: codecontext sidecar container + HTTP shim
New /opt/boocode/codecontext/ directory holding the codecontext sidecar
that BooCode's tool wrappers (track B.2) will talk to. No BooCode-side
changes yet — this commit lands the sidecar standalone.

- Dockerfile: multi-stage golang:1.24-alpine → alpine:3.20. Clones
  codecontext at v3.2.1 from github.com/nmakod/codecontext (cgo build for
  tree-sitter bindings), builds the shim alongside (CGO_ENABLED=0).
- shim.go: stdlib-only Go HTTP server wrapping codecontext's stdio MCP
  child. Newline-delimited JSON framing per the MCP transport spec
  (NOT LSP-style Content-Length). 8 POST /v1/* endpoints, one per MCP
  tool, plus GET /health. Child supervised via child.Wait() goroutine
  that os.Exit's on death so the container's restart: unless-stopped
  policy fires (Signal(0) on a zombie returns nil and is not a liveness
  check — discovered during kill-restart testing).
- go.mod: no third-party deps; future Go security advisories don't apply.

docker-compose service: joins boocode_net (no host port), mounts
/opt:/opt:ro (BooCode projects live at /opt/<slug>, not exclusively
under /opt/projects), healthcheck on /health.

Verified: build clean, healthcheck reports healthy ~15s after up,
multi-project queries return valid markdown, target_dir swap works on
subtree paths. Kill-restart cycle completes in ~200ms with one failed
health poll observed (no misleading "ok" during the gap). Memory: 24.6
MiB after 5 search_symbols calls, 5.6 MiB after 30 min idle — codecontext
releases the per-call graph between target_dir swaps, so the shim doesn't
hold the indexed state.
2026-05-21 12:30:48 +00:00
5cd3f63df5 mobile: add explicit close button to nav drawer 2026-05-21 04:06:35 +00:00
cc73ed1957 docs: refine CLAUDE.md (TurnArgs, web tools, env vars, new-tool convention) 2026-05-21 02:57:32 +00:00
3e1e17ecf6 v1.11.10: stream-cap response body at 5MB, abort on overflow v1.11.1-consolidation 2026-05-21 02:27:31 +00:00
ab01e04d77 v1.11.9: manual redirect handling — re-run URL guard on each hop 2026-05-21 00:37:35 +00:00
4e67a265ac v1.11.8: address review — inject fetcher, byte-count limit, redirect TODO 2026-05-20 21:40:11 +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
863452ae07 v1.11.7: secret-file deny list for codebase tools
Ports continue.dev's DEFAULT_SECURITY_IGNORE_FILETYPES + ignored-dir lists
into apps/server/src/services/secret_guard.ts plus a small BooCode
additions block (id_rsa*, *credentials*, .netrc, *.kdbx). Tiny glob-to-
regex matcher; no new prod dep.

view_file hard-refuses via SecretBlockedError. list_dir / grep /
find_files filter their results and surface a pathguard_note string
field with the hidden count — never list the offending paths back.

Named secret_guard.ts (not safety/pathGuard.ts) to avoid collision with
the existing path_guard.ts which already exports a pathGuard() function.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 20:55:50 +00:00
85037f000d Merge v1.11.6-doom-loop-guard 2026-05-20 20:28:45 +00:00
f92b0810c3 v1.11.6: doom-loop guard (3 identical tool calls aborts recursion) 2026-05-20 20:28:45 +00:00
4ec196273b sessions: default new sessions to no agent (raw chat)
Was picking the alphabetically-first agent from AGENTS.md ("Code
Reviewer") which felt presumptuous. New sessions now create with
agent_id=null; user picks from the AgentPicker if they want one.
Removes resolveDefaultAgent helper + the getAgentsForProject import
since this was the only caller. The project SELECT no longer needs
the path column either.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 20:11:57 +00:00
1ffcf67c47 v1.11.5: ContextBar inline next to agent picker; remove ChatContextPopover
ContextBar relocated from a dedicated row above MessageList to inline with
the agent-picker row, filling the space to the right of the picker + plus
button. Always-visible (zero-state when no assistant message has run yet)
via chat.model_context_limit, which GET /api/sessions/:id/chats now
populates from a single getModelContext lookup per session.

ChatContextPopover above the input is removed entirely along with its
useChatContextStats hook (no remaining callers). Color tiers and the
auto-compaction threshold tooltip unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 20:11:49 +00:00
3a5cf0c81a merge v1.11.3-ctxmax v1.11.0-context-bar 2026-05-20 19:29:26 +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
8cd270a5da ContextBar: persistent context-usage indicator above MessageList
Walks chat messages newest-first for the latest ctx_used/ctx_max pair.
Color tiers fire against (max - 20k compaction reserve) so the bar warns
amber/orange/red at the same boundaries auto-compaction triggers.
"Context" → "Ctx" at <640px, (NN%) drops at <380px.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 19:18:27 +00:00
c48de06f42 merge v1.11-compaction 2026-05-20 19:05:35 +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
6aab4f7d2a ChatTabBar: + button dropdown to add chat / terminal / agent pane
Replaces single onNewChat handler with onAddPane(kind). Terminal pane
header gets matching + dropdown. Context menu "New chat" stays.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-20 18:13:55 +00:00
2d841ee0b4 handoff 2026-05-20 14:56:02 +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
3fceea064a booterm: fitFull() bypasses FitAddon scrollbar subtraction; push initial PTY size
FitAddon's proposeDimensions() always subtracts a phantom scrollbar width even
when CSS hides the scrollbar — losing one column of usable width. fitFull()
divides host clientWidth/clientHeight by the renderer's reported cell size
directly. Also POSTs the resized cols/rows back to /api/term/.../resize on
initial mount and after fonts.ready so bash/opencode get the correct PTY
size before the user types.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 17:32:42 +00:00
fccab20920 merge v1.10.4-booterm-mobile 2026-05-19 17:16:50 +00:00
ea9d261f0f v1.10.4: booterm mobile UX — copy/paste, swipe-close, send-to-chat, search
- Long-press selection + floating menu (mobile + desktop right-click): Copy,
  Paste, Select All, Search, Send to chat. Tap-outside / Esc dismiss.
- Pane-header Paste button (📋) for iOS user-gesture clipboard read.
- Swipe-left-to-close on mobile pane pill with red "Close" overlay and
  translateX visual hint; spring-back below 80px threshold.
- Send-to-chat reverse path: chatInputsRegistry + sendToChat event mirror
  the existing terminalsRegistry pattern. ChatInput appends with newline
  separator on receive and focuses (no auto-send).
- Scrollback search via xterm-addon-search@^0.13.0: SearchBar overlay with
  N-of-M match counter (onDidChangeResults), Enter/Shift-Enter cycling.
- Cmd/Ctrl+F intercept in Session.tsx when active pane is terminal; xterm
  also intercepts when focused. Browser native find passes through elsewhere.
- terminalsRegistry signature extended with openSearch + paste callbacks.

Includes deferred CLAUDE.md updates documenting v1.10/v1.10.1/v1.10.2/v1.10.3
learnings (uid 1000 collision, libc match, two event buses, vite proxy order,
mobile pane URL sync, xterm canvas selection).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 17:16:47 +00:00
4d466c5710 merge v1.10.3-booterm-ux 2026-05-19 13:52:50 +00:00
875db86e31 v1.10.3: booterm mobile/UX fixes + global keyboard shortcuts
Five issues + keyboard shortcuts across booterm and the workspace shell.

Auto-switch on create (mobile): addSplitPane now returns the new pane id;
Session.tsx wraps it with addPaneAndSwitch which pushes ?pane=<newId> on
mobile so the URL-sync effect doesn't fight the just-set activePaneIdx.
NewPaneMenu uses the wrapper; desktop Split dropdown is unaffected.

Tab-away reconnect: TerminalPane has a connect()/manualReconnect() state
machine. ws.onclose backs off 500ms/1s/2s × 3 attempts, then surfaces a
[Disconnected] banner with a Reconnect button. visibilitychange listener
calls manualReconnect when the tab returns and the WS isn't OPEN. tmux
session persists server-side so scrollback is intact on resume.

Copy/paste: attachCustomKeyEventHandler binds Cmd/Ctrl-C (copy if
selection, else send ^C), Cmd/Ctrl-Shift-C (always swallow — copy if any,
no-op otherwise — never sends ^C), Cmd/Ctrl-V and Cmd/Ctrl-Shift-V
(navigator.clipboard.readText → ws.send). No custom right-click menu —
browser's native menu is preserved.

Scroll: removed `set -g mouse on` from tmux.conf so xterm.js sees wheel
and touch events natively. scrollback: 10_000, fastScrollModifier: 'shift',
altClickMovesCursor: false. Container has touch-action: pan-y for mobile.

Right-edge gap: inline <style> overrides xterm's defaults to width:100%
height:100% and hides the scrollbar chrome. Host container is
flex-1 min-w-0 self-stretch w-full. Three refit triggers: ResizeObserver
(rAF-wrapped), document.fonts.ready, and useEffect on the new active prop.
Background color matched between outer div, inner div, and xterm theme.

Keyboard shortcuts in Session.tsx (window-level keydown):
  Cmd/Ctrl+`              focus active terminal, else jump to last
  Cmd/Ctrl+Shift+T        new terminal pane
  Cmd/Ctrl+Shift+C        new chat pane (defers to xterm copy if focused)
  Cmd/Ctrl+W              close active pane
  Cmd/Ctrl+Tab/Shift+Tab  cycle next / prev pane
  Cmd/Ctrl+1..9           jump to pane N
terminalsRegistry gains a focus() callback per registration so Cmd+`
can call term.focus() on the active terminal.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 13:52:44 +00:00
8eaf9591dc merge v1.10.2-booterm-glibc 2026-05-19 13:14:25 +00:00
5d52b79a07 v1.10.2: booterm runtime on bookworm-slim (glibc), su-exec → gosu
Switched the booterm runtime + proddeps stages from node:20-alpine (musl)
to node:20-bookworm-slim (glibc) so host-installed glibc binaries (Claude
Code, opencode, nvm node) run inside the container when invoked from the
terminal pane. node-pty's native .node has to be compiled in the same
libc env as the runtime, so both stages flip together; the TypeScript-only
builder stage stays on alpine.

su-exec is alpine-only; Debian replacement is gosu — swapped in both the
runtime apt install and the tmux default-command. uid/gid 1000 collision
with the bookworm `node` user handled via userdel/groupdel before
groupadd/useradd.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 13:14:21 +00:00
ead7cb9d01 merge v1.10.1-booterm-user v1.10.1-booterm-user 2026-05-19 13:07:59 +00:00
d04b30687f v1.10.1: booterm runs shells as samkintop with login bash 2026-05-19 13:07:59 +00:00
9250632ac3 merge v1.10-booterm v1.10.0-booterm 2026-05-18 14:06:46 +00:00
7486e7d3e0 v1.10: booterm container — xterm.js + tmux + node-pty 2026-05-18 14:06:46 +00:00
d85b17081e v1.9.7: ask_user_input elicitation tool v1.9.2-ask-user-input 2026-05-18 02:15:18 +00:00
adb5d7b3bb Merge v1.9-skills: skills + /skill slash command v1.9.1-skills 2026-05-18 01:52:15 +00:00
80fd3d9fa9 feat(web): /skill slash command with autocomplete
Trigger /<name>, dropdown lists all skills filtered by name prefix,
arg passthrough sends the rest as the user message. Synthetic
skill_use tool_use renders identically to model-invoked skills.
2026-05-18 01:10:51 +00:00
eaacd432e8 feat(web): skills API types + client methods 2026-05-18 01:10:51 +00:00
529a77c959 feat(server): skills v1 — parser, tools, /api/skills, mount
- /data/skills mount (host: /opt/skills)
- skill_find, skill_use, skill_resource added to default read-only
  tool set; opt-in for agents with explicit tools: whitelist
- AGENTS.md builtin agents drop explicit tools: arrays to inherit
  the new default (now includes skill tools)
- POST /api/chats/:id/skill_invoke for slash-command flow
- 19 SKILL.md files seeded at /opt/skills/ across 6 source groups
2026-05-18 01:10:51 +00:00
9a7b35b677 build: harden .dockerignore (secrets/, data/)
The host-side docker-compose mounts secrets/ and data/ read-only at
runtime, but the build context still slurped them in. Add secrets/,
data/, and general SSH key patterns (*.pem, *.key, id_rsa*,
id_ed25519*, known_hosts, .ssh/) so private material can never be
baked into the image even by accident.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-17 20:50:37 +00:00
98b432ebce refactor: drop type-to-confirm gate on chat delete
The chat-delete dialog required typing the chat name to confirm
deletion. Single-user app — typing friction is annoying, not safety.
Match the archive dialog pattern in SettingsPane.tsx: title +
description naming the chat in mono font, plain Cancel + destructive
Delete button.

Removes the deleteInput state, deleteExpected / deleteEnabled
deriveds, the <Input> field, and its lone <Input> import.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-17 20:50:30 +00:00