Sessions expose declared-and-connected only; 'all' is builtin-only; legacy true
migrates to the recommended refs, else nothing. Consent lists real names and
per-connector caps force re-consent when an update widens the grant.
Unparseable (_raw) args now get a truthful error: cut-off-by-output-limit says
'smaller pieces', bad JSON says 're-send with declared parameters'. Raw junk is
shrunk before entering history so replays can't teach the model the _raw shape.
Anthropic default max_tokens 16k -> 32k so typical report files fit outright.
Fact strip: 'OpenWorker installs its own verified copy from <publisher>' replaces
supply-chain jargon. On decline the engine re-resolves — a copy the user installed
themselves is handed to the agent as theirs, not treated as a refusal.
Registry metadata (version, publisher, checksum) moves to a distinct fact strip.
Decline button renamed to say the run continues; reason capped to one sentence.
trivy 0.74.0 pinned with per-platform digests so request_tool can install it.
tfsec is deprecated upstream; the bundle now drives trivy config instead.
Sidecar inherits the login shell's env; toolchain resolves absolute paths with pinned
installs; request_tool replaces the 'tool missing -> STOP' instruction that hid a check.
Bundle zip export + import (zip-slip guarded) through the picker's Import door; version+provenance with a replaces-note, re-consent only when capabilities grow.
Consent screen: trust warning first, capability summary with collapsed tool list, recommended connectors.
Bundle skills/ dir joins the persona's session menu (additive; user disables/mutes win); manifest skills: narrows the bundle; mcp: scopes raw servers.
Install snapshot now carries the skills folder — the sharing bundle shape.
Per-session coworker+folder chips replace the sidebar split-button picker; code family gets a send-time folder dialog with git-ready temp dirs and Save as project.
Builtins ship enabled; user-facing noun is Coworker; personas flag now defaults on.
guard.get_checked previously resolved a name for the address check and then let
the client resolve it again to connect, so a ~0-TTL record could flip to
127.0.0.1 (or the metadata endpoint) between the two — the exact gap the module
docstring called out as "not covered".
Every hop now connects to the address that passed its check: the request URL
carries the vetted IP, Host keeps the original name (and explicit port) for
virtual hosting, and the sni_hostname extension keeps the TLS handshake — and
certificate verification — against the name. Literal-IP URLs are unchanged.
Redirect Locations are resolved against the logical URL, and the final logical
URL rides resp.extensions["logical_url"] so web_fetch reports the name, not the
pinned address.
Verified against a local TLS server whose cert carries only DNS:pinned.test:
the pinned request (URL=127.0.0.1, sni_hostname=pinned.test) verifies and the
server sees Host: pinned.test; the same request without the extension fails
with "IP address mismatch" — httpcore does verify certificates against
sni_hostname, not the URL host.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The artifacts scan used rglob and filtered after descending, so a home directory
workspace walked into ~/Library and triggered the macOS App Data consent prompt on
every turn. Walk with pruning instead, and skip Library / AppData in search too.
The composer chip now shows the session total by default, with the context window
bar behind a Settings toggle.
Follow up to #290. Add RFC 6598 shared space (100.64.0.0/10, used by
Tailscale) to the address guard, and run the same guard on the Playwright
browser_open_url before navigating.
The live smoke exposed a harness trap: driving each turn through its own
asyncio.run() binds the engine asyncio primitives to the first loop, and
every later stream silently takes the interrupted path - full provider
replies persisted as empty assistant messages. The scripted smoke had
the same latent artifact and did not assert reply content, so it stayed
green. Now the whole scenario runs on ONE loop (like the real server)
and every turn asserts a real reply.
A long multi-turn session driven through the real SessionManager with a
forced 3k-token cap: repeated compactions advance the boundary, later
summaries fold the previous one in, the provider verifiably receives the
compacted view (summary block + verbatim tail, bounded) while the
canonical transcript keeps every turn, state survives a mid-conversation
rebuild, and the persisted record round-trips the final boundary.
Scripted stand-in for the live-model smoke: intent survival across a
real summarizer (prompt tuning) still needs a configured provider key.
Settings -> Models grows a Context compaction card next to Token savings:
the trigger % of the context window (10-95), the absolute token cap
(clamped 10k-2M), and the summarizer-model pin (default: the session's
own model). POST /v1/settings/compaction persists them; engines read the
knobs live per check, so changes apply to running sessions immediately.
The "context compacted" divider rides the existing notice machinery: the
persisted `compacted` notice replays on reload (itemsFromMessages) and
the live COMPACTED event appends the same info notice mid-turn. The
transcript itself stays intact - outbound-only by construction.
Covered by vitest (marker replay), a settings-card e2e (defaults +
clamped POSTs + model pin), and a mid-session divider e2e driven by the
fixtures' scripted `compacted` event.
Minimal engine footprint: a checkpoint at each iteration top (between tool
turns and before a new turn), the usage signal captured per round-trip
(context_tokens; chars/4 estimate when never reported), and
_outbound_messages consulting the boundary. The summarizer runs off-loop
through the normal provider router, so the Settings model pin is just an
id.
Failure policy per spec: retry once in both modes; attended sessions get
the Retry / Trim-oldest-10% prompt (via the ask_user plumbing, gated by an
is_attended callback the WS surface wires); unattended runs auto-trim and
continue — never parked on internal bookkeeping. Raw context-overflow 400s
from the main model route into the same policy, progress-guarded so a
still-overflowing model terminates in the error path.
CompactionState persists on the session record (new sqlite column, same
defensive parse as grants), so reloads keep the compacted view. A
persisted compacted notice + a new COMPACTED event mark the spot for
the GUI divider (rendered in commit 3).
Trigger math (usage signal, chars/4 estimate fallback, min(80% x window,
250k cap) with overridable knobs), boundary picking that never splits a
turn (user-message starts preferred, iteration starts inside a giant tool
loop), the 8-section summarizer prompt with the continuation contract,
mechanical working-state extraction from tool records, deterministic
user-message preservation, the trim-oldest fallback, outbound-view
application, and context-overflow detection. Injectable provider seam;
no engine changes yet.
Options accept {label, description, recommended, preview} objects (plain
strings unchanged — old sessions render as today's pills), and `questions`
groups up to 4 questions into one call, rendered as a stepper via the
header chips. Any option preview switches the card to a two-pane layout:
options left, monospace pane right, following hover/focus.
Grouped calls resolve with a JSON map keyed by header-or-question and
return {answers: {...}} to the agent (single stays {answer: ...});
a grouped item's first question doubles as its title/options so channel
mirrors and legacy surfaces degrade sensibly. Channel buttons use option
labels; grouped items mirror as text with the open-the-app hint.
web_fetch and browser_read_url take a URL straight from the model. The model's
input is untrusted by design - both tools' own descriptions call fetched
content "data to evaluate, not instructions" - and web_fetch is
requires_approval=False, so nothing prompts the user before the request goes
out.
Neither validated the address. Verified against a scratch server on loopback:
web_fetch("http://127.0.0.1:9931/")
-> {"text": "Directory listing for /\n.git/\n.github/..."}
No prompt, no error. The same call reaches http://169.254.169.254/ for cloud
metadata when OpenWorker runs on a VM, an Ollama instance on :11434, or any
service on the user's LAN. It cannot reach OpenWorker's own sidecar, which
requires COWORKER_API_TOKEN.
Adds coworker/web/guard.py: resolve the host and refuse when any answer lands
in loopback, private, link-local (which covers the metadata endpoint),
multicast or reserved space. Checking every resolved address means a name with
one public and one private A record is refused rather than raced.
Redirects are the usual bypass, so follow_redirects is off and the chain is
walked here with each hop checked before it is requested. _request grows an
opt-in check_addresses flag used only by browser_read_url; the hardcoded vendor
endpoints the rest of the connectors call skip the guard and its DNS lookup.
Not covered, and stated in the module docstring: DNS rebinding. The name is
resolved by the guard and again by the client when it connects, so a near-zero
TTL record can change in between. Closing that needs connection-level IP
pinning. The hop check is the cheap 90%.
Tests: tests/test_url_address_guard.py - literals, IPv4-mapped IPv6 loopback,
names resolving into private space, split-horizon answers, non-http schemes,
redirect into loopback proven not to be requested, and a bounded redirect
loop.
_build_openai: no custom base_url -> OpenAIResponsesProvider; a custom
endpoint (Azure /openai/v1, vLLM, compat gateways) keeps the Chat
Completions OpenAIProvider, as do Ollama and every compat vendor. Verify
path (raw GET /models) and matrix ids are untouched.
/v1/chat/completions rejects function tools with any reasoning_effort
other than none on GPT-5.6, so native OpenAI has run with reasoning OFF.
OpenAIResponsesProvider speaks /v1/responses instead: reasoning + tools
at real effort, streamed reasoning summaries into the existing
reasoning_delta plumbing, and CoT continuity across tool round-trips via
store:false + encrypted reasoning replayed through a new _openai message
sidecar (same extras contract as _anthropic/_gemini). Not routed yet.
Coworkers remember durable things you tell them and use them in future sessions.
One Settings screen lists everything remembered - edit, delete, or stop new saves; standing instructions ride along.
Knowledge is session-stable, the save switch is per-message; sqlite gains a summary column via in-place migration.
Two ephemeral breakpoints per request (last system block, final message's
last block) so append-only history re-reads the prior turns' cache;
outbound-only, persisted history stays clean.
Normalized TokenUsage (input/output/cache split) captured in every provider's
stream and complete paths, persisted as an assistant-message sidecar and sent
on the assistant_message event; matrix gains verified context-window sizes.
Model listing 403/404s under plain ADC; countTokens is free and proves
project+location+API in one call. Verified live: Gemini (global), Qwen MaaS (us-south1).
Segmented track + inset per-method panel with its own Test & save footer.
Vertex gains the same treatment: Google Cloud login (default), service account,
and API key (express mode, Gemini-only with a clear error elsewhere).
Untrusted repos must not define stdio MCP servers that spawn at session open. Skip <.coworker/mcp.json> until the workspace is trusted, matching allowed_commands consent.
Fixes#213
'Connect with' segmented choice (API key / profile / IAM keys) shows only that
method's fields; non-selected fields are dropped at build so stale values can't leak.
New optional field: paste the console-generated key, no CLI/IAM setup needed.
Takes precedence over SigV4 credentials, matching boto3; live-tested on Converse.
resolve_from_reply decided allow/deny with 'in' checks on the whole message,
so "disallow" resolved as allow (checked first, and it contains "allow") and
replies containing words like "note" or "not" resolved as deny instead of
being recorded as free-text answers. Since this gates parked unattended
actions, a false allow is the worst-case direction.
Keyword intent now requires word boundaries (with the common -d forms added);
emoji checks stay as substring matches. Anything that matches neither list
falls through to the existing free-text path, which records the reply verbatim
instead of acting on it.
Rohit C Prasad