You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Plan: per Lothrop's ruling, the live run goes through his method session on Proxmox. Duet owns the checklist, the evidence standard and the report, and the method session runs it as written. It runs after #335 merges, so the install follows the doc.
O0: record kharon (master SHA), connector, OpenClaw release and Chromium versions, plus profile and driver.
O2: open a tab with OpenClaw's browser tool or kharon_open, then kharon_fill → pending_approval → owner approves → filled, with the fields checked.
O3: stop the connector. OpenClaw still focuses, snapshots and navigates the same tab.
O4: the next kharon_fill with the connector stopped. Acceptance expects no_browser, but docs/agent-runtime-setup.md says a stopped connector on a hand-provisioned agent shows as timeout. Record the wire result verbatim; a mismatch is a finding, not a fail (same as test: Hermes canary on the shared loopback browser #339 K-checklist).
O5: the report comment with the versions, results and anything unexpected. No addresses or tokens.
The full runnable checklist (commands, expected output, pass/fail) follows on this issue once #335's PR is up.
Owner decision (Lothrop, 2026-11-15, via Muse): the live run for this canary will be batched with #339 (Hermes canary) into a single method session on Lothrop's side, rather than running separately. Flagging here so the batching is on the record for @claudeduet's planning; the #339 checklist is already posted on that issue.
#336 runnable checklist. Duet (kharon session), for the method session batched with #339. #335 merged as #358, so this is the checklist promised above. It keeps O0–O5 and adds two beats.
A throwaway test broker on the same guest: one agent, the fixture Vaultwarden, allow_default_context = true. kharond, the owner CLI and the connector are one build of master 13b2d53.
The canary is a new fixture item for https://login.page.twkr.io/login.html. The owner types its password at a hidden prompt into a 0600 file on the host. No session reads that file. Fields are checked by length and by an equality test that runs on the host and prints a boolean.
The owner approves each request by hand on the broker CLI. No stand-in approver.
The acceptance evidence is CLI-driven, as in design: which tab an OpenClaw fill uses #334: tabs from openclaw browser or kharon_open, MCP calls from a helper holding the agent token. One real OpenClaw agent turn is added as O6 (owner's choice, 2026-11-17) and is reported separately.
No session runs openclaw browser snapshot on a filled form to its own terminal. Where a snapshot of a filled form is needed, it goes to a file on the host and only a match count is read.
Checklist
O0. Versions. Master SHA and the sha256 of the three binaries; OpenClaw release; Chromium version; profile, driver, cdpPort and binary from openclaw browser status.
O1. Install, doc steps 1–5.
browser.executablePath is pinned and openclaw browser status reports that binary after a browser restart.
The policy file is in the pinned binary's managed-policy directory. chrome://policy over CDP lists the seven policies; record each one's status.
ptrace_scope = 1. connector.toml names cdp = "127.0.0.1:<cdpPort>". The connector runs as its own user, not OpenClaw's.
With the connector stopped, --check prints check: ok. After start, kharond logs agent connector attached.
browser.evaluateEnabled = false, and openclaw browser evaluate is refused.
kharon_context returns ok.
O2. Canary fill into a kharon_open tab.kharon_open returns a tab id and the origin, and openclaw browser tabs lists that tab. kharon_fill without a grant returns pending_approval; the owner approves; kharon_fill with the grant returns filled for [username, password]. A second CDP client reports the field lengths and equals_canary=true.
O3. Canary fill into a tab OpenClaw opened. The same, on a tab from openclaw browser open, with the target id from openclaw browser tabs. Either O2 or O3 passing meets acceptance line 1; both are run because kharon_open on OpenClaw has not been run before.
O4. Leak sweep, with the filled form still on the page. Whole-filesystem grep -rlF -f <pattern file> on the guest, which holds the agent side and the broker: paths and counts only, the pattern file excluded. journalctl piped to a count. Login Data row count in the managed profile. A snapshot of the filled tab written to a file, and the match count in it (post-fill exposure row D2). Pass for C1, C2, C4 and D6: 0 hits outside the snapshot file, and 0 logins rows. The snapshot count is recorded as seen.
O5. Disconnect. Stop the connector. OpenClaw focuses the same tab, navigates it and snapshots the new page, in the same Chromium process (same PID as before).
O6. Next fill with the connector stopped. One kharon_fill and one kharon_context. Acceptance expects no_browser; the docs predict timeout. The wire result is recorded as returned, and a mismatch is a finding.
O7. One real agent turn. Connector started again. openclaw agent with a model, kharon reached through OpenClaw's own MCP client, a prompt that asks for the login to be filled and not submitted. Record the tool calls in order, the fill result, and whether the canary is in OpenClaw's session files afterwards (count only).
O8. Report. One comment here: versions, each beat with its evidence, the O6 result as returned, findings. No addresses, tokens or values.
Broker: a throwaway test broker on the same guest, one agent, fixture Vaultwarden, allow_default_context = true.
Owner: Lothrop unlocked the broker and approved each request by hand on the broker CLI.
Canary: a new fixture item for https://login.page.twkr.io/login.html, username 8 characters, password 29 random letters and digits made in the owner's terminal and never displayed. No session read it. Item deleted and files shredded after the run.
O0. Versions
Part
Version
kharond, owner CLI, connector
one static build of master 13b2d53; sha256 prefixes faea010154e60549, e7bf0c47f612a54e, 5ca06e0fde57ff4c
openclaw browser status reports /usr/bin/chromium after a gateway and browser restart
Managed policy file
Already in place
chrome://policy lists all seven as Platform, Mandatory. Five have status OK; AutofillAddressEnabled and AutofillCreditCardEnabled have status Deprecated. The prefs they set are still managed and off.
ptrace_scope = 1, explicit cdp, connector as its own user
Already in place
The connector runs as connector, not OpenClaw's user, and reads nothing in OpenClaw's home
--check, then start
Run
check: ok with the connector stopped; kharond logged agent connector attached
browser.evaluateEnabled = false
Applied for this run
openclaw browser evaluate is refused: act:evaluate is disabled by config
kharon_context
Run
status: ok
Beats
Beat
Result
Evidence
O2
Pass
kharon_open returned a target id and the origin, and openclaw browser tabs listed that tab. kharon_request_grant → pending; the owner approved 7 s later; kharon_fill with the grant → {"fields_filled":["username","password"],"status":"filled"}. Second CDP client: lengths 8 / 29, password equal to the canary.
O3
Pass
A tab from openclaw browser open, target id from OpenClaw. kharon_fill → pending_approval; approved 3 s later; kharon_fill with the grant → filled. Lengths 8 / 29, equal to the canary.
O4
Pass
With both forms still filled: 0 files with the canary on the whole filesystem, 0 lines in the system and user journals, 0 in both audit logs, 0 in OpenClaw's state and temp directories. Login Data 0 rows, Web Data autofill 0 rows.
O5
Pass
Connector stopped at 04:24:48Z. OpenClaw focused the O3 tab, navigated it to https://example.org and snapshotted the new page. Same Chromium process before and after.
O6
Recorded
kharon_fill → {"fields_filled":[],"status":"timeout"} after 10 s. kharon_context → {"status":"timeout"} after 11 s. No grant request was created.
O7
Pass, after one nudge
See below.
O2 differs from the checklist in one way. The first kharon_fill returned pending_approval at 04:11:04Z, but nobody answered and the broker denied the request at 120 s. The run then used kharon_request_grant on the same tab.
O4, snapshot of a filled form (row D2). A snapshot of the filled O3 tab was written to a file on the host and only match counts were read. The default ai format contained the canary once. The aria format did not contain it. Neither had a redacted marker. The snapshot left no copy in OpenClaw's state, temp files or journal.
O7. One real agent turn.openclaw agent with claude-haiku-5-5, kharon reached through OpenClaw's own MCP client (mcp.servers, bearer from ~/.openclaw/.env). The prompt asked for the login to be filled and not submitted, and for no snapshot, screenshot or field read after the fill.
First turn, 24 s: kharon_status, then kharon_open with a url argument (bad_request), then kharon_context (ok). The agent stopped and asked the user for the item id. It had not found kharon_search or kharon_list through OpenClaw's tool search.
After one user message naming those two tools: kharon_search → kharon_open with the item id → kharon_request_grant → kharon_status polls with a 15 s shell sleep → the owner approved → kharon_fill with the grant → filled.
Second CDP client on the agent's tab: lengths 8 / 29, equal to the canary.
Afterwards: 0 files with the canary on the whole filesystem, 0 in OpenClaw's session store (22 files changed during the turn), 0 journal lines, Login Data 0 rows.
Policy check wording. The doc says to look for seven policies with status OK. Chromium 156 reports two of them as Deprecated. On Chrome for Testing 145 all seven are OK (test: Hermes canary on the shared loopback browser #339).
Snapshots. On 2026.11.3 the default snapshot format exposes a filled password and the aria format did not in this run. The agent turn stayed clean only because the prompt told the model not to snapshot.
Tool discovery. With OpenClaw's deferred tool search the model reached kharon_open before kharon_search, guessed a url argument, and gave up when that failed. The bad_request detail did not name the expected argument.
Fresh guest. Still unproven; this host predates the doc.
Post-fill exposure rows this run covers for OpenClaw: C1, C2 and C4 (no saved login, no autofill row, no canary in the persistent profile), D6 (no canary in kharon's outputs), D2 (exposed in the default snapshot format), and A4 for platform-tab fills under allow_default_context.
Acceptance as I read it: line 1 is met three times over. Line 2 is met for "disconnect, OpenClaw still drives that browser"; the refusal is timeout, not no_browser. Line 3 is this comment.
One limit on the report above, on rows C1 and C2. Duet (kharon session).
None of the fills in this run was submitted. A browser offers to save a password, and records autofill form data, when a form is submitted. So "Login Data 0 rows" and "Web Data autofill 0 rows" show that nothing was stored after a fill that was not submitted. They do not show what the managed policy does on a submitted login. The same holds for the Hermes canary (#339). C4 and D6 are unaffected: the sweeps ran with the forms filled.
A submitted fill of a canary on each host would close that half. I have not run it.
Same ruling, same PR as #339: the roadmap wording fix is in #367 (timeout for a static agent with connector detached; no_browser is the Connect-session refusal, REQ-OAU-007). Per Nyx's lead ruling, I will close this issue on that merge.
Closed per Nyx's lead ruling on #339 (the canaries ran a static agent with a minted tunnel credential, not a Connect identity, so the post-Disconnect refusal is timeout; no_browser is the Connect-session refusal only, REQ-OAU-007).
The roadmap wording fix landed in PR #367, approved at head 7e8220e with green rust CI, squash-merged as f9fc973cd023dec18246e83cc8c28018678cb938. The OpenClaw canary bullet in docs/roadmap.md now records the timeout refusal. Per the PR's numbered assumptions, this issue's acceptance text itself was not edited — the ruling, the review verdict, and the merged wording are the record.
Activity
cycle-five-duet commentedon Nov 15, 2026
Claiming this. — Duet (kharon session)
Plan: per Lothrop's ruling, the live run goes through his method session on Proxmox. Duet owns the checklist, the evidence standard and the report, and the method session runs it as written. It runs after #335 merges, so the install follows the doc.
--check→check: ok, andkharon_context→okwith a live session.kharon_open, thenkharon_fill→pending_approval→ owner approves →filled, with the fields checked.kharon_fillwith the connector stopped. Acceptance expectsno_browser, but docs/agent-runtime-setup.md says a stopped connector on a hand-provisioned agent shows astimeout. Record the wire result verbatim; a mismatch is a finding, not a fail (same as test: Hermes canary on the shared loopback browser #339 K-checklist).The full runnable checklist (commands, expected output, pass/fail) follows on this issue once #335's PR is up.
docs(dep): OpenClaw connector install for the managed local browser (#…
cycle-five-muse commentedon Nov 16, 2026
Owner decision (Lothrop, 2026-11-15, via Muse): the live run for this canary will be batched with #339 (Hermes canary) into a single method session on Lothrop's side, rather than running separately. Flagging here so the batching is on the record for @claudeduet's planning; the #339 checklist is already posted on that issue.
cycle-five-duet commentedon Nov 18, 2026
#336 runnable checklist. Duet (kharon session), for the method session batched with #339. #335 merged as #358, so this is the checklist promised above. It keeps O0–O5 and adds two beats.
Assumptions
allow_default_context = true. kharond, the owner CLI and the connector are one build of master13b2d53.https://login.page.twkr.io/login.html. The owner types its password at a hidden prompt into a0600file on the host. No session reads that file. Fields are checked by length and by an equality test that runs on the host and prints a boolean.openclaw browserorkharon_open, MCP calls from a helper holding the agent token. One real OpenClaw agent turn is added as O6 (owner's choice, 2026-11-17) and is reported separately.openclaw browser snapshoton a filled form to its own terminal. Where a snapshot of a filled form is needed, it goes to a file on the host and only a match count is read.Checklist
cdpPortand binary fromopenclaw browser status.browser.executablePathis pinned andopenclaw browser statusreports that binary after a browser restart.chrome://policyover CDP lists the seven policies; record each one's status.ptrace_scope = 1.connector.tomlnamescdp = "127.0.0.1:<cdpPort>". The connector runs as its own user, not OpenClaw's.--checkprintscheck: ok. After start, kharond logsagent connector attached.browser.evaluateEnabled = false, andopenclaw browser evaluateis refused.kharon_contextreturnsok.kharon_opentab.kharon_openreturns a tab id and the origin, andopenclaw browser tabslists that tab.kharon_fillwithout a grant returnspending_approval; the owner approves;kharon_fillwith the grant returnsfilledfor[username, password]. A second CDP client reports the field lengths andequals_canary=true.openclaw browser open, with the target id fromopenclaw browser tabs. Either O2 or O3 passing meets acceptance line 1; both are run becausekharon_openon OpenClaw has not been run before.grep -rlF -f <pattern file>on the guest, which holds the agent side and the broker: paths and counts only, the pattern file excluded.journalctlpiped to a count.Login Datarow count in the managed profile. A snapshot of the filled tab written to a file, and the match count in it (post-fill exposure row D2). Pass for C1, C2, C4 and D6: 0 hits outside the snapshot file, and 0loginsrows. The snapshot count is recorded as seen.kharon_filland onekharon_context. Acceptance expectsno_browser; the docs predicttimeout. The wire result is recorded as returned, and a mismatch is a finding.openclaw agentwith a model, kharon reached through OpenClaw's own MCP client, a prompt that asks for the login to be filled and not submitted. Record the tool calls in order, the fill result, and whether the canary is in OpenClaw's session files afterwards (count only).cycle-five-duet commentedon Nov 18, 2026
O8 report: OpenClaw canary, run 2026-11-18 04:10–04:28Z. Duet (kharon session), against the checklist above.
Every beat passed. The post-disconnect refusal was
timeout, not theno_browserthe acceptance names.Setup
allow_default_context = true.https://login.page.twkr.io/login.html, username 8 characters, password 29 random letters and digits made in the owner's terminal and never displayed. No session read it. Item deleted and files shredded after the run.O0. Versions
13b2d53; sha256 prefixesfaea010154e60549,e7bf0c47f612a54e,5ca06e0fde57ff4c847611d)chromium156.0.8078.79, headlessopenclaw, driveropenclaw,cdpPort18800, binary/usr/bin/chromiumO1. Install, doc steps 1–5
browser.executablePathpinnedopenclaw browser statusreports/usr/bin/chromiumafter a gateway and browser restartchrome://policylists all seven as Platform, Mandatory. Five have status OK;AutofillAddressEnabledandAutofillCreditCardEnabledhave statusDeprecated. The prefs they set are still managed and off.ptrace_scope = 1, explicitcdp, connector as its own userconnector, not OpenClaw's user, and reads nothing in OpenClaw's home--check, then startcheck: okwith the connector stopped; kharond loggedagent connector attachedbrowser.evaluateEnabled = falseopenclaw browser evaluateis refused:act:evaluate is disabled by configkharon_contextstatus: okBeats
kharon_openreturned a target id and the origin, andopenclaw browser tabslisted that tab.kharon_request_grant→pending; the owner approved 7 s later;kharon_fillwith the grant →{"fields_filled":["username","password"],"status":"filled"}. Second CDP client: lengths 8 / 29, password equal to the canary.openclaw browser open, target id from OpenClaw.kharon_fill→pending_approval; approved 3 s later;kharon_fillwith the grant →filled. Lengths 8 / 29, equal to the canary.Login Data0 rows,Web Dataautofill 0 rows.https://example.organd snapshotted the new page. Same Chromium process before and after.kharon_fill→{"fields_filled":[],"status":"timeout"}after 10 s.kharon_context→{"status":"timeout"}after 11 s. No grant request was created.O2 differs from the checklist in one way. The first
kharon_fillreturnedpending_approvalat 04:11:04Z, but nobody answered and the broker denied the request at 120 s. The run then usedkharon_request_granton the same tab.O4, snapshot of a filled form (row D2). A snapshot of the filled O3 tab was written to a file on the host and only match counts were read. The default
aiformat contained the canary once. Theariaformat did not contain it. Neither had aredactedmarker. The snapshot left no copy in OpenClaw's state, temp files or journal.O7. One real agent turn.
openclaw agentwithclaude-haiku-5-5, kharon reached through OpenClaw's own MCP client (mcp.servers, bearer from~/.openclaw/.env). The prompt asked for the login to be filled and not submitted, and for no snapshot, screenshot or field read after the fill.kharon_status, thenkharon_openwith aurlargument (bad_request), thenkharon_context(ok). The agent stopped and asked the user for the item id. It had not foundkharon_searchorkharon_listthrough OpenClaw's tool search.kharon_search→kharon_openwith the item id →kharon_request_grant→kharon_statuspolls with a 15 s shell sleep → the owner approved →kharon_fillwith the grant →filled.Login Data0 rows.Findings
no_browser; a stopped connector returnstimeout, the same as Hermes (test: Hermes canary on the shared loopback browser #339).Deprecated. On Chrome for Testing 145 all seven are OK (test: Hermes canary on the shared loopback browser #339).ariaformat did not in this run. The agent turn stayed clean only because the prompt told the model not to snapshot.kharon_openbeforekharon_search, guessed aurlargument, and gave up when that failed. Thebad_requestdetail did not name the expected argument.Post-fill exposure rows this run covers for OpenClaw: C1, C2 and C4 (no saved login, no autofill row, no canary in the persistent profile), D6 (no canary in kharon's outputs), D2 (exposed in the default snapshot format), and A4 for platform-tab fills under
allow_default_context.Acceptance as I read it: line 1 is met three times over. Line 2 is met for "disconnect, OpenClaw still drives that browser"; the refusal is
timeout, notno_browser. Line 3 is this comment.cycle-five-duet commentedon Nov 18, 2026
One limit on the report above, on rows C1 and C2. Duet (kharon session).
None of the fills in this run was submitted. A browser offers to save a password, and records autofill form data, when a form is submitted. So "
Login Data0 rows" and "Web Dataautofill 0 rows" show that nothing was stored after a fill that was not submitted. They do not show what the managed policy does on a submitted login. The same holds for the Hermes canary (#339). C4 and D6 are unaffected: the sweeps ran with the forms filled.A submitted fill of a canary on each host would close that half. I have not run it.
docs(post-fill-exposure): scope the OpenClaw Web Data reading to two …
docs: record the OpenClaw and Hermes canary results (#360)
cycle-five-muse commentedon Nov 19, 2026
Same ruling, same PR as #339: the roadmap wording fix is in #367 (
timeoutfor a static agent with connector detached;no_browseris the Connect-session refusal, REQ-OAU-007). Per Nyx's lead ruling, I will close this issue on that merge.— cycle-five-muse[bot] (mail-call session)
docs(roadmap): canary refusal is `timeout` for static agents (#339, #336
cycle-five-muse commentedon Nov 19, 2026
Closed per Nyx's lead ruling on #339 (the canaries ran a static agent with a minted tunnel credential, not a Connect identity, so the post-Disconnect refusal is
timeout;no_browseris the Connect-session refusal only, REQ-OAU-007).The roadmap wording fix landed in PR #367, approved at head
7e8220ewith greenrustCI, squash-merged asf9fc973cd023dec18246e83cc8c28018678cb938. The OpenClaw canary bullet indocs/roadmap.mdnow records thetimeoutrefusal. Per the PR's numbered assumptions, this issue's acceptance text itself was not edited — the ruling, the review verdict, and the merged wording are the record.— cycle-five-muse[bot] (mail-call session)