mosaicstack/stack
25
0
Fork 1
Code Issues 340 Pull Requests 13 Actions Packages Projects Releases 15 Wiki Activity

docs(records): Jason's walkthrough rulings, Sage moved to SetSpark, CHAT-02 go

Browse Source 
Jason ruled on seven open items (20:27Z-20:45Z): seat Gitea tokens read in
place, one Discord restart after 6b with row 25 live, row 8 limited to the
dev seats, DYOR in dyor-stack-v4 with Sage moved to SetSpark, skills/aws-*
excluded locally, no second WebUI return defect, and go on CHAT-02 only.

Sage persona files name SetSpark as its business work. Darkwing's SOUL drops
harness names that were wrong for T3. DEFERRED adds the slash-prefix paste
hazard and the board Host/Origin gap, and moves the ledger T3 item to Done.
Dewey's approved CHAT-02 brief (636b0fac) and Filbert's review are recorded.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
jason.woltje
2026-09-26 15:35:15 -05:00
co-authored by Claude Opus 5.5
parent ef0020ad85
commit 993673865a
23 changed files with 1756 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files
agents/dewey/work/chat-02/BRIEF-r1-314da8b0.md
+201
View File
@@ -0,0 +1,201 @@
# CHAT-02 brief: read-only histories and Age (#1507, row 5)
Author: Dewey, 2026-09-26. Draft for Sage, then Filbert. No source edits.
Plan row: `docs/plans/2026-09-13_webui-session-chat.md` line 214. Depends on
CHAT-01 (`28d4e98a`) and uses the CHAT-01C companion (`b023841c`).
## 1. Is there a second defect in the return path?
Short answer: no second defect in the return path shows up for repository Pi
seats. The answers reach the transcript, the board reads them, and the Console
shows them. What Jason hit on 09-13 is best explained by the product gap: the
Console offered one "Last assistant text" field, clipped at 240 characters, in
an inspector, with no reply thread and no pending signal. 42c08d52 fixed the
pending display. The clip and the missing thread are CHAT-02's job.
I found one real defect on the send side, not the return side (§1.3).
### 1.1 Evidence so far
1. **Transcripts.** I scanned every `.pi/state/*/sessions` file (darkwing,
dewey, filbert, researcher) for board sends. The script is
`evidence/sends.mjs` and the output is `evidence/board-sends-repo-pi.jsonl`.
There are 30 sends and 29 have a final answer in the same file. Latency is
1.5 s minimum, 14.6 s median and 1019 s maximum. In 16 of the 29 answers
the text exceeds 240 characters, so the Console showed them clipped.
2. **The unanswered send.** Filbert, 2026-09-12T16:33:17Z. The seat started
working on it: it read files until 16:35:44Z, the last entry is an
`aborted` assistant turn, and a new filbert session began at 16:36:26Z. The
seat was relaunched mid-turn. That lost the answer, but the loss is in the
seat, not in the return path.
3. **Jason's report window.** At 2026-09-13T00:49:59Z he asked dewey "What
are the Gate E criteria?". The answer landed at 00:50:07Z with 365
characters, clipped to 240 in the Console. He wrote the report at 00:56:51Z.
The report says the sessions "are all cards within the project dashboard and
not available as independent chat interfaces". That describes the missing
thread, not a missing answer.
4. **The 09-13 Console, replayed.** I extracted `ea00ec66` into a scratch
directory and ran the return-flow test with the pending and Age
assertions removed. It passed: the new answer arrived through the 10 s
poll, once, in the open inspector. That page did not drop answers.
5. **Jason's live send today.** Researcher, user entry at
2026-09-26T20:10:57.429Z, answer "pong" at 20:11:06.173Z (8.7 s). At
20:15:18Z `/api/board` showed the researcher row as `idle` with
`lastAssistantText: "pong"`, `lastActivity` 20:11:06.173Z, the same
`sessionFile`, and a live registration (`evidence/board-researcher-*.json`).
The live WebUI (pid 1266267, port 7330) serves `app.js` byte-identical to
HEAD (`d1a51646…`), so the 42c08d52 pending notice is live. The WebUI
server code has not changed since that process started on 09-13 16:19 CDT.
The board (pid 3977979, port 7331) started today at 15:03 CDT.
### 1.2 What is still unverified
- **What Jason's screen showed.** For today's send I have the transcript and
the board JSON, not the Console DOM or a screenshot. The one missing fact is
whether "pong" appeared in the open inspector without a manual refresh.
- **The 09-13 processes.** The board keeps no reply receipts and the 09-13
board and WebUI processes are gone. I cannot prove what those processes
served at 00:50Z. I can only show that the same code, replayed, works.
- **Fleet seats.** I did not scan `~/.mosaic` fleet transcripts. The rule for
this phase is to leave them alone, and CHAT-02 does not cover fleet
catalogues.
- **Clipping in a live send.** "pong" is 4 characters, so today's send does
not exercise the 240-character clip.
### 1.3 Send-side defect found in passing
Today's user entry starts with `/`: `/[dragon-lin:control-board ->
dragon-lin:researcher] ping`. `agent-send.sh` adds the header, so the `/` was
already sitting in the Pi editor when the paste arrived. `send-message.sh`
pastes into whatever is in the composer (`paste-buffer -p`, then Enter). It
does not clear it first. Here Pi treated the result as plain text. If the
composer had held a real command prefix, a board reply could have become a
slash command. This is the unmediated-ingress hazard that CHAT-01 assigns to
CHAT-03I (B3). `tools/tmux/**` is excluded from the WebUI plan, so I
record it and do not propose a fix here. Sage decides whether to note it on
#1507 for the CHAT-03I charter.
### 1.4 Evidence that settles it
One question for Jason settles the live case: **after today's ping, did
"pong" appear in the Console inspector without pressing Refresh?**
- If yes, there is no second defect. CHAT-02 proceeds as a product-gap fix.
- If no, `/api/board` had the answer, so the defect is in the Console or the
WebUI proxy. Then capture the Console DOM and the network log for
`/api/board` during one send.
- If `/api/board` had lacked it, the defect would be in the scanner (wrong
newest file). If the transcript had lacked it, the defect would be in the
transport or the seat. Neither happened today.
To make the check complete for the clip, one more live send can ask for an
answer over 240 characters. Every step above then repeats, and the Console
should show the text ending in "…". That proves the clip is what cut the
09-13 answer short.
## 2. Scope
CHAT-02 per the plan: both harness catalogues, safe full branch history with
pagination and cursors, separate timestamps, relative Age from last
activity, and fixtures for malformed, truncated, replaced and touched logs,
cross-project and symlink denial, and no log writes. Read-only: opening a
conversation never resumes, forks, launches or controls anything.
### 2.1 Backend: `packages/conversation/**`
The owner is not yet assigned. The plan proposes Darkwing; Sage now assigns.
- **Catalogue.** Approved source roots only: the board's repository specs
(`<repo>/.pi/state/<seat>/sessions`) and live seat registrations. There is
no global scan and no browser-supplied path. Each conversation gets an
opaque ID mapped server-side to a file. Catalogue creation time, engine
launch time and last activity are separate nullable fields.
- **No-write Pi parser.** Never `SessionManager.open`, which can migrate old
files (CHAT-00 line 67). Open read-only. Record size, mtime and inode
before and after each read, and the fixture asserts they are unchanged.
- **Branches.** Build the `id`/`parentId` tree and select a leaf explicitly.
The default leaf is the last appended entry, which the implementer must
confirm against the pinned Pi session docs. Other leaves are read-only
branches.
Compaction entries render as markers. Pi `get_entries` order is not a
branch transcript (CHAT-00 line 66), so the parser does not use it.
- **Pages.** CHAT-01 limits: at most 100 parts, 8 MiB serialized UTF-8, 64
blocks per part and 262144 characters per string. Oversize content splits
into continuation parts and is never clipped. The cursor binds actor,
purpose, conversation, branch, snapshot, source epoch and expiry. A
replaced file (new inode or a shorter length) is a new source epoch, so old
cursors refuse and the client keeps its view with a reconcile marker. It
never silently switches files.
- **Damaged input.** A malformed line becomes an unavailable part with its
position, and reading continues. A truncated trailing line counts as
incomplete, not as an error.
- **Denials.** A symlink anywhere under the root, a path that resolves
outside the root, a parent-session reference, or a conversation from
another project all refuse, with fixtures.
### 2.2 Console: `packages/webui/**` (Dewey)
This is the smallest piece that answers the 09-13 complaint: a read-only
conversation view per session, opened from the card, table or inspector. It
renders the selected branch in full, unclipped: user text, assistant text,
tool calls and results collapsed, thinking hidden by default, and Markdown as
untrusted text with no active HTML. Age stays as 42c08d52 shipped it. Reply
keeps the existing board path unchanged. The view gets the new answer through
polling, as the inspector does now. Streaming belongs to CHAT-03.
The full chat UI (sidebar, composer, queue, approvals, uploads) stays in
CHAT-05.
### 2.3 Return-flow regression (required by the plan)
Extend `packages/webui/tests/return-flow.test.mjs`, or add a sibling test.
Send from the conversation view. Then the seat appends user, toolCall,
toolResult and a final answer longer than 240 characters. Assert that the
whole answer appears once, unclipped, in the same open view, with no manual
refresh, and that the draft and caret survive. Add a delayed-result variant
where the toolResult lands after a poll. This covers the Pi engine only; see
D2.
## 3. Decisions needed from Sage
- **D1: deferred items.** CHAT-01 line 342 defers "the actual
execution/writer-claim record" to CHAT-02. CHAT-01C line 217 defers R3-1,
reconciling dispatched but unconsumed input, to "CHAT-02 adapter evidence".
A read-only reader needs neither. I recommend moving both to CHAT-03, which
owns binding and the single writer, and recording that on #1507.
- **D2: Claude catalogue.** B1 is open: Claude's persisted branch format and
leaf selection are unverified (CHAT-00 line 66). I recommend shipping Pi in
CHAT-02, with the Claude catalogue refusing `unsupported-harness` under a
fixture, and adding Claude once B1 evidence exists. Rocko is the only
Claude seat. The plan asks for both harnesses, so this is a scope change for
Sage to accept or refuse.
- **D3: endpoint home.** The WebUI knows only the board URL, and the board
owns discovery and the approved roots. I recommend that
`packages/conversation` stay a library with no server, and that the board
add two read-only routes: catalogue and page. That is a board integration
(`packages/control-board/src/serve.mjs`, `scan.mjs`), which the plan says
needs approval and Darkwing's coordination. The alternative is for the
WebUI to read seat registrations itself, which duplicates discovery.
- **D4: backend author** for `packages/conversation/**`, and the sequencing:
backend first, then the Console against its fixtures.
- **D5: Jason's gate.** CHAT-02..08 were held pending Jason. This brief does
not lift that hold. Building needs Sage's go under whatever Jason has ruled.
## 4. Acceptance
- The new `packages/conversation` tests cover every fixture in §2.1, including
a before/after hash, mtime and inode check proving no log writes.
- The return-flow regression from §2.3 passes on the served WebUI.
- These still pass: `node docs/plans/chat-00/check.mjs`, `chat-01/check.mjs`,
`chat-01c/check.mjs`, and the control-board, webui and seat suites.
- Browser evidence: conversation view at 320 and 1440 in both themes, with a
long answer, a tool call, a malformed-line marker and a stale-cursor
reconcile marker. No horizontal overflow at 320.
- Filbert approves the exact candidate hashes. Live check: one board send
with a long answer, visible in full in the view.
## 5. Not in scope
Live adapters, control, streaming, queues, uploads, approvals, fleet seats,
Claude history until B1, any change to `tools/tmux/**`, `roles/**` or
session logs, and the `/` paste hazard (CHAT-03I).
agents/dewey/work/chat-02/BRIEF-r2-ed177bf6.md
+201
View File
@@ -0,0 +1,201 @@
# CHAT-02 brief: read-only histories and Age (#1507, row 5)
Author: Dewey, 2026-09-26. R2: Sage's decisions on D1-D5 are recorded in §3
(R1 frozen as `BRIEF-r1-314da8b0.md`). For Filbert's review. No source edits.
Plan row: `docs/plans/2026-09-13_webui-session-chat.md` line 214. Depends on
CHAT-01 (`28d4e98a`) and uses the CHAT-01C companion (`b023841c`).
## 1. Is there a second defect in the return path?
Short answer: no second defect in the return path shows up for repository Pi
seats. The answers reach the transcript, the board reads them, and the Console
shows them. What Jason hit on 09-13 is best explained by the product gap: the
Console offered one "Last assistant text" field, clipped at 240 characters, in
an inspector, with no reply thread and no pending signal. 42c08d52 fixed the
pending display. The clip and the missing thread are CHAT-02's job.
I found one real defect on the send side, not the return side (§1.3).
### 1.1 Evidence so far
1. **Transcripts.** I scanned every `.pi/state/*/sessions` file (darkwing,
dewey, filbert, researcher) for board sends. The script is
`evidence/sends.mjs` and the output is `evidence/board-sends-repo-pi.jsonl`.
There are 30 sends and 29 have a final answer in the same file. Latency is
1.5 s minimum, 14.6 s median and 1019 s maximum. In 16 of the 29 answers
the text exceeds 240 characters, so the Console showed them clipped.
2. **The unanswered send.** Filbert, 2026-09-12T16:33:17Z. The seat started
working on it: it read files until 16:35:44Z, the last entry is an
`aborted` assistant turn, and a new filbert session began at 16:36:26Z. The
seat was relaunched mid-turn. That lost the answer, but the loss is in the
seat, not in the return path.
3. **Jason's report window.** At 2026-09-13T00:49:59Z he asked dewey "What
are the Gate E criteria?". The answer landed at 00:50:07Z with 365
characters, clipped to 240 in the Console. He wrote the report at 00:56:51Z.
The report says the sessions "are all cards within the project dashboard and
not available as independent chat interfaces". That describes the missing
thread, not a missing answer.
4. **The 09-13 Console, replayed.** I extracted `ea00ec66` into a scratch
directory and ran the return-flow test with the pending and Age
assertions removed. It passed: the new answer arrived through the 10 s
poll, once, in the open inspector. That page did not drop answers.
5. **Jason's live send today.** Researcher, user entry at
2026-09-26T20:10:57.429Z, answer "pong" at 20:11:06.173Z (8.7 s). At
20:15:18Z `/api/board` showed the researcher row as `idle` with
`lastAssistantText: "pong"`, `lastActivity` 20:11:06.173Z, the same
`sessionFile`, and a live registration (`evidence/board-researcher-*.json`).
The live WebUI (pid 1266267, port 7330) serves `app.js` byte-identical to
HEAD (`d1a51646…`), so the 42c08d52 pending notice is live. The WebUI
server code has not changed since that process started on 09-13 16:19 CDT.
The board (pid 3977979, port 7331) started today at 15:03 CDT.
### 1.2 What is still unverified
- **What Jason's screen showed.** For today's send I have the transcript and
the board JSON, not the Console DOM or a screenshot. The one missing fact is
whether "pong" appeared in the open inspector without a manual refresh.
- **The 09-13 processes.** The board keeps no reply receipts and the 09-13
board and WebUI processes are gone. I cannot prove what those processes
served at 00:50Z. I can only show that the same code, replayed, works.
- **Fleet seats.** I did not scan `~/.mosaic` fleet transcripts. The rule for
this phase is to leave them alone, and CHAT-02 does not cover fleet
catalogues.
- **Clipping in a live send.** "pong" is 4 characters, so today's send does
not exercise the 240-character clip.
### 1.3 Send-side defect found in passing
Today's user entry starts with `/`: `/[dragon-lin:control-board ->
dragon-lin:researcher] ping`. `agent-send.sh` adds the header, so the `/` was
already sitting in the Pi editor when the paste arrived. `send-message.sh`
pastes into whatever is in the composer (`paste-buffer -p`, then Enter). It
does not clear it first. Here Pi treated the result as plain text. If the
composer had held a real command prefix, a board reply could have become a
slash command. This is the unmediated-ingress hazard that CHAT-01 assigns to
CHAT-03I (B3). `tools/tmux/**` is excluded from the WebUI plan, so I
record it and do not propose a fix here. Sage confirmed it as a safety gap
and is adding it to DEFERRED.md under CHAT-03I/B3. It gets one line on #1507.
There is no tools/tmux change now.
### 1.4 Evidence that settles it
One question for Jason settles the live case: **after today's ping, did
"pong" appear in the Console inspector without pressing Refresh?**
- If yes, there is no second defect. CHAT-02 proceeds as a product-gap fix.
- If no, `/api/board` had the answer, so the defect is in the Console or the
WebUI proxy. Then capture the Console DOM and the network log for
`/api/board` during one send.
- If `/api/board` had lacked it, the defect would be in the scanner (wrong
newest file). If the transcript had lacked it, the defect would be in the
transport or the seat. Neither happened today.
To make the check complete for the clip, one more live send can ask for an
answer over 240 characters. Every step above then repeats, and the Console
should show the text ending in "…". That proves the clip is what cut the
09-13 answer short.
## 2. Scope
CHAT-02 per the plan: both harness catalogues, safe full branch history with
pagination and cursors, separate timestamps, relative Age from last
activity, and fixtures for malformed, truncated, replaced and touched logs,
cross-project and symlink denial, and no log writes. Read-only: opening a
conversation never resumes, forks, launches or controls anything.
### 2.1 Backend: `packages/conversation/**`
Dewey authors it (D4).
- **Catalogue.** Approved source roots only: the board's repository specs
(`<repo>/.pi/state/<seat>/sessions`) and live seat registrations. There is
no global scan and no browser-supplied path. Each conversation gets an
opaque ID mapped server-side to a file. Catalogue creation time, engine
launch time and last activity are separate nullable fields.
- **No-write Pi parser.** Never `SessionManager.open`, which can migrate old
files (CHAT-00 line 67). Open read-only. Record size, mtime and inode
before and after each read, and the fixture asserts they are unchanged.
- **Branches.** Build the `id`/`parentId` tree and select a leaf explicitly.
The default leaf is the last appended entry, which the implementer must
confirm against the pinned Pi session docs. Other leaves are read-only
branches.
Compaction entries render as markers. Pi `get_entries` order is not a
branch transcript (CHAT-00 line 66), so the parser does not use it.
- **Pages.** CHAT-01 limits: at most 100 parts, 8 MiB serialized UTF-8, 64
blocks per part and 262144 characters per string. Oversize content splits
into continuation parts and is never clipped. The cursor binds actor,
purpose, conversation, branch, snapshot, source epoch and expiry. A
replaced file (new inode or a shorter length) is a new source epoch, so old
cursors refuse and the client keeps its view with a reconcile marker. It
never silently switches files.
- **Damaged input.** A malformed line becomes an unavailable part with its
position, and reading continues. A truncated trailing line counts as
incomplete, not as an error.
- **Denials.** A symlink anywhere under the root, a path that resolves
outside the root, a parent-session reference, or a conversation from
another project all refuse, with fixtures.
### 2.2 Console: `packages/webui/**` (Dewey)
This is the smallest piece that answers the 09-13 complaint: a read-only
conversation view per session, opened from the card, table or inspector. It
renders the selected branch in full, unclipped: user text, assistant text,
tool calls and results collapsed, thinking hidden by default, and Markdown as
untrusted text with no active HTML. Age stays as 42c08d52 shipped it. Reply
keeps the existing board path unchanged. The view gets the new answer through
polling, as the inspector does now. Streaming belongs to CHAT-03.
The full chat UI (sidebar, composer, queue, approvals, uploads) stays in
CHAT-05.
### 2.3 Return-flow regression (required by the plan)
Extend `packages/webui/tests/return-flow.test.mjs`, or add a sibling test.
Send from the conversation view. Then the seat appends user, toolCall,
toolResult and a final answer longer than 240 characters. Assert that the
whole answer appears once, unclipped, in the same open view, with no manual
refresh, and that the draft and caret survive. Add a delayed-result variant
where the toolResult lands after a poll. This covers the Pi engine only; see
D2.
## 3. Decisions (Sage, 2026-09-26)
- **D1: moved.** CHAT-01 line 342 had deferred "the actual
execution/writer-claim record" to CHAT-02. CHAT-01C line 217 had deferred
R3-1, reconciling dispatched but unconsumed input, to "CHAT-02 adapter
evidence". A read-only reader needs neither, so both go to CHAT-03, which
owns binding and the single writer. This is noted on #1507.
- **D2: accepted.** Pi ships in CHAT-02. The Claude catalogue refuses
`unsupported-harness` under a fixture until B1 has evidence (Claude's
persisted branch format and leaf selection, CHAT-00 line 66). This narrows
the plan's "both harnesses". Sage records the scope change in the lead
decisions file.
- **D3: accepted.** `packages/conversation` is a library with no server. The
board adds two read-only routes, catalogue and page, in
`packages/control-board/src/serve.mjs` and `scan.mjs`. Darkwing reviews
that change before it lands. The coordination note goes to Darkwing when
the backend reaches review, not before.
- **D4: Dewey authors both.** The backend comes first, then the Console
against its fixtures. Filbert reviews this brief now and the code after.
- **D5: stays with Jason.** Sage set the live reply test as the condition,
and it passed. Sage is asking Jason for the go on CHAT-02. No code goes
under `packages/conversation` until Sage relays his answer.
## 4. Acceptance
- The new `packages/conversation` tests cover every fixture in §2.1, including
a before/after hash, mtime and inode check proving no log writes.
- The return-flow regression from §2.3 passes on the served WebUI.
- These still pass: `node docs/plans/chat-00/check.mjs`, `chat-01/check.mjs`,
`chat-01c/check.mjs`, and the control-board, webui and seat suites.
- Browser evidence: conversation view at 320 and 1440 in both themes, with a
long answer, a tool call, a malformed-line marker and a stale-cursor
reconcile marker. No horizontal overflow at 320.
- Filbert approves the exact candidate hashes. Live check: one board send
with a long answer, visible in full in the view.
## 5. Not in scope
Live adapters, control, streaming, queues, uploads, approvals, fleet seats,
Claude history until B1, any change to `tools/tmux/**`, `roles/**` or
session logs, and the `/` paste hazard (CHAT-03I).
agents/dewey/work/chat-02/BRIEF-r3-3b81a3f2.md
+379
View File
@@ -0,0 +1,379 @@
# CHAT-02 brief: read-only histories and Age (#1507, row 5)
Author: Dewey, 2026-09-26. R3, for Filbert's delta review. It answers his R2
verdict (revise), `agents/filbert/work/chat-02-brief-r2-review-2026-09-26.md`
(`0f0154b7…7fdf`). Earlier revisions are frozen as `BRIEF-r1-314da8b0.md` and
`BRIEF-r2-ed177bf6.md`. §6 maps each finding to its change. No source edits.
Plan row: `docs/plans/2026-09-13_webui-session-chat.md` line 214. Depends on
CHAT-01 (`28d4e98a`) and uses the CHAT-01C companion (`b023841c`).
## 1. Is there a second defect in the return path?
Short answer: no second return-path defect has shown up for repository Pi
seats. Two legs are shown directly: answers reach the transcript, and the
board serves them. The Console leg is shown only by replaying the 09-13
code (item 4), until Jason answers the §1.4 question about today's send.
The best explanation for what Jason hit on 09-13 is the product gap. The
board collapses the last answer to 240 characters
(`packages/control-board/src/scan.mjs`, `TEXT_LIMIT`, line 23 at ea00ec66
and line 25 at HEAD). The Console showed that one clipped field in an
inspector, with no conversation view and no pending signal. 42c08d52 fixed
the pending display. CHAT-02 covers the clip and the missing view, which means
the new history routes must not go through the board's summary text.
I found one real defect on the send side (§1.3). While reviewing the new
routes, I found a missing Host check on the board (§1.5).
### 1.1 Evidence so far
1. **Transcripts.** `evidence/sends.mjs` walks every `.pi/state/*/sessions`
file. That is five seat directories: darkwing, dewey, filbert, researcher
and sage, and sage has no board sends. For each board send, the script
records the *first* later assistant entry with `stopReason: stop`. The
output is `evidence/board-sends-repo-pi.jsonl`.
- Of 30 sends, 29 are followed by a stop answer in the same file.
- Latency is 1.5 s minimum, 14.6 s median and 1019 s maximum.
- 16 of the 29 answers exceed 240 characters, so the board clipped them.
- The attribution is by file order only. In 7 of the 29, another
user-role entry lands between the send and the answer, so the answer may
also cover that later input. By my count, the first such entry in all 7
is a peer agent-send from dewey, darkwing, filbert or rocko. Filbert
classified them as two peer agent-sends plus five entries carrying other
content. Either way, Jason's 09-13 question (item 3) is not one of the 7.
- Filbert confirmed that none of the nine files involved branches, so file
order equals branch order.
2. **The unanswered send.** Filbert, 2026-09-12T16:33:17Z. The seat started
working on it and read files until 16:35:44Z. The last entry is an
`aborted` assistant turn, and a new filbert session began at 16:36:26Z.
The seat was relaunched mid-turn, so the answer was lost in the seat, not
in the return path. §2.3 point 5 turns this into a test.
3. **Jason's report window.** At 2026-09-13T00:49:59Z he asked dewey "What
are the Gate E criteria?". The answer landed at 00:50:07Z: 365 characters,
which the board clipped to 240. He wrote the report at 00:56:51Z. It says
the sessions "are all cards within the project dashboard and not available
as independent chat interfaces". That describes the missing view, not a
missing answer.
4. **The 09-13 Console, replayed.** The pinned files are in
`evidence/replay-0913/`: the test, the diff against 42c08d52, the TAP
output and a README.
- The scratch extract of `ea00ec66` is byte-identical to that commit (45
files checked).
- The test is the 42c08d52 return-flow test with the Age, pending and
clear-once assertions removed, since ea00ec66 has none of those.
- It passed (1/1, 20.7 s): the new answer arrived through the 10 s poll,
once, in the open inspector.
- The replay's answer is short, so it does not exercise the clip.
5. **Jason's live send today.** Researcher, user entry at
2026-09-26T20:10:57.429Z, answer "pong" at 20:11:06.173Z (8.7 s).
- At 20:15:18Z, `/api/board` showed the row `idle`, with
`lastAssistantText: "pong"`, the same `sessionFile` and a live
registration (`evidence/board-researcher-*.json`).
- The live WebUI (pid 1266267, port 7330) serves `app.js` byte-identical
to HEAD (`d1a51646…`). Its server code has not changed since that
process started on 09-13 at 16:19 CDT.
- The board (pid 3977979, port 7331) started today at 15:03 CDT.
### 1.2 What is still unverified
- **What Jason's screen showed.** I have the transcript and the board JSON
for today's send, but not the Console DOM. The Console leg for a live send
is unproven until Jason answers §1.4.
- **The 09-13 processes.** The board keeps no reply receipts, and the 09-13
processes are gone. Item 4 shows that the same code works. It cannot show
what those processes served.
- **Fleet seats.** I did not scan `~/.mosaic` transcripts. They are out of
scope for CHAT-02.
- **The clip in a live send.** "pong" is 4 characters, so today's send
doesn't exercise the clip.
### 1.3 Send-side defect found in passing
Today's user entry starts with `/`:
/[dragon-lin:control-board -> dragon-lin:researcher] ping
`agent-send.sh` adds the header, so the `/` was already in the Pi composer
when the paste arrived. `send-message.sh` pastes onto whatever the composer
holds, then presses Enter. Here Pi treated the result as plain text. If the
composer had held a real command prefix, a board reply could have become a
Pi slash command.
Sage confirmed this as a safety gap under CHAT-03I/B3 and recorded it in
DEFERRED.md. It is on #1507 (comment 26538). There is no `tools/tmux` change
now.
### 1.4 Evidence that settles it
Sage is putting one question to Jason: **after today's ping, did "pong"
appear in the Console inspector without pressing Refresh?**
- **Yes:** there is no second defect, and CHAT-02 proceeds as a
product-gap fix.
- **No:** `/api/board` had the answer, so the defect is in the Console or the
WebUI proxy. Capture the Console DOM and the `/api/board` network log during
one send.
- **Missing from `/api/board`:** that would point at the scanner. **Missing
from the transcript:** that would point at transport or the seat. Neither
happened today.
One more live send, asking for an answer over 240 characters, would show
the clip ending in "…".
### 1.5 Board Host check (found while reviewing D3)
The Console server checks `Host` and `Origin`
(`packages/webui/src/serve.mjs` lines 54–59). The board server does not. It
checks only the bind address.
A DNS-rebinding page that reaches port 7331 could:
- read `/api/board`: 240 characters per row, plus task and cwd;
- `POST /api/reply` with `application/json`. The board requires that content
type but not a same-origin `Host`, so the text would be pasted into a live
seat pane.
Modern browsers restrict some local-network requests, but I have not tested
any browser against this. That makes it a finding, not a demonstrated
exploit.
The new D3 routes must carry the guard (§2.1). Whether the same guard should
be applied to the existing board routes in that `serve.mjs` change is Sage's
decision. I recommend doing it.
## 2. Scope
CHAT-02 per the plan, narrowed by D2:
- a Pi catalogue;
- safe, full branch history, with pagination and cursors;
- separate timestamps;
- relative Age from last activity;
- no writes to logs.
It is read-only. Opening a conversation never resumes, forks, launches or
controls anything.
### 2.1 Backend: `packages/conversation/**` (Dewey, D4)
**Catalogue sources.** Only approved source roots count: the board's
repository specs (`<repo>/.pi/state/<seat>/sessions`). There is no global
scan, and no path comes from the browser. A seat registration is
seat-written, so it is a hint, not authority (CHAT-01 line 62). Its
`sessionFile` is accepted only when the file is under an approved root for
the same project. Each conversation gets an opaque ID, which the server maps
to a file. Catalogue creation time, engine launch time and last activity are
separate nullable fields.
**Opening a file safely.**
- Check every path component with `lstat`: no symlinks, and it stays inside
the root.
- Open with `O_RDONLY | O_NOFOLLOW`, then `fstat` the descriptor. The
descriptor's (dev, ino) must match the checked path.
- Read only from that descriptor.
- Never use `SessionManager.open`, which can migrate files (CHAT-00 line 67).
**Parser.**
- Build the `id`/`parentId` tree and select a leaf explicitly. The default is
the last appended entry, which the implementer confirms against the pinned
Pi session docs. Other leaves are read-only branches.
- Compaction entries render as markers.
- Pi `get_entries` order is not a branch transcript (CHAT-00 line 66), so it
is not used.
- The parser never follows `parentSession`. The conversation still renders,
with a "forked from an earlier session" marker, and the parent file is never
opened.
- If the Pi header's `cwd` names another project, the conversation is refused.
- A malformed line becomes an unavailable part at its position, and reading
continues. A truncated trailing line is incomplete, not an error.
**Pages.**
- CHAT-01 limits: at most 100 parts, at most 8 MiB of serialized UTF-8 bytes
(enforced on bytes, not characters), 64 blocks per part, and 262144
characters per string.
- Oversize content splits into continuation parts and is never clipped.
**Snapshots and epochs.**
- The page reads up to the snapshot length that its cursor pins, so growth
during a read is cut there.
- A source epoch is (dev, ino) plus a SHA-256 of the prefix the snapshot
covers. Growth past that prefix is the same epoch.
- A different inode, a shorter file, or a changed prefix digest (an in-place
rewrite with the same inode) is a new epoch.
**Cursors.**
- A cursor binds actor, purpose, conversation, branch, snapshot, source epoch
and expiry.
- These all refuse, keep the old view and show a reconcile marker: an
unknown, foreign, expired or source-replaced cursor.
- Nothing ever switches files silently.
- On this unauthenticated loopback route there is one actor,
`local-operator`, and cursors bind to it. That is not multi-actor safety.
Authenticated actors come with CHAT-04R and must not be claimed here.
**Board routes (D3).** Two read-only `GET` routes, catalogue and page.
- `Host` must be the loopback name and the board's own port.
- A cross-origin `Origin` is refused.
- No CORS headers are sent.
- Responses are `application/json` with `nosniff` and `no-store`.
**Fixtures.** Each one names its expected refusal or result.
| # | Fixture | Expected |
|---|---|---|
| F1 | Malformed line | Unavailable part at its position, reading continues |
| F2 | Truncated trailing line | Incomplete marker |
| F3 | Replaced file (new inode) | Old cursors refuse, reconcile |
| F4 | Same-inode prefix rewrite | Old cursors refuse, reconcile |
| F5 | Touched: growth between two pages and during one read | Same epoch, page cut at the pinned length |
| F6 | Unknown, foreign (actor, purpose, conversation or branch) and expired cursor | Each refuses and keeps the old view |
| F7 | Symlink at the file and at a directory component | Refused, never opened |
| F8 | File swapped for a symlink between catalogue and read | Refused (O_NOFOLLOW or a dev/ino mismatch) |
| F9 | Registration naming a file outside the roots, a symlink, or another project's file | Refused, never opened |
| F10 | Pi header `cwd` naming another project | Refused |
| F11 | `parentSession` pointing outside the root | Renders with a marker, and the parent is never opened |
| F12 | Branched file with two leaves | Default leaf shown, other branch readable, no merge |
| F13 | Compaction | Marker, then retained content |
| F14 | A string over 262144 characters, and a multibyte page reaching 8 MiB before 100 parts | Continuation parts, reassembled exactly, byte cap enforced |
| F15 | Claude harness | `unsupported-harness` refusal (D2) |
| F16 | Foreign `Host` and a cross-origin `Origin` on both routes | 403, no CORS headers |
| F17 | No writes | Before and after every fixture: size, SHA-256, mtime, (dev, ino), and the session directory listing (no new files) are unchanged. Atime is excluded because relatime can update it on read. |
### 2.2 Console: `packages/webui/**` (Dewey)
This is the smallest thing that answers the 09-13 complaint: a read-only
conversation view per session, opened from the card, the table or the
inspector.
- It renders the selected branch in full, with nothing clipped: user text,
assistant text, and tool calls and results collapsed.
- Thinking is hidden by default.
- Markdown is untrusted, so it has no active HTML, no unsafe URLs and no
terminal escapes.
- Age stays as 42c08d52 shipped it.
- Reply keeps the existing board path. The view gets new answers through
polling. Streaming belongs to CHAT-03.
The full chat UI (sidebar, composer, queue, approvals and uploads) stays in
CHAT-05.
**Hostile-render fixture (R1).** Assistant text and tool output contain:
- HTML, including `<script>` and `<img onerror>`;
- a `javascript:` link;
- ANSI and OSC terminal escapes.
All of it renders as inert text. The test asserts that no element, handler or
navigation was created.
### 2.3 Return-flow regression (required by the plan)
The regression runs on the real board, the real D3 routes and the real
WebUI, the way the existing test does. Nothing is injected into the WebUI.
1. **Path.** Send from the conversation view. The seat then appends a user
entry, a toolCall, a toolResult and a final answer.
2. **Exactness.** The answer has a sentinel after character 240 and another
at the very end. The view shows the exact text, with no "…", once.
3. **Continuation.** A second answer is long enough to split into
continuation parts. The test checks that it reassembles exactly and in
order.
4. **Thread order.** In the view, the sent message comes first, then the
collapsed tool call and result, then the answer.
5. **Interleaving.** A peer agent-send lands before the final answer, as in
§1.1 item 1. Both entries show, in file order.
6. **Relaunch mid-turn,** modelled on the 09-12 filbert case. A new session
file appears. The open view keeps its file, shows the reconcile marker and
never switches silently.
7. **Timing.** A delayed-result variant has the toolResult land after a poll.
The draft and caret survive, and no manual refresh is used.
This covers Pi only (D2).
## 3. Decisions (Sage, 2026-09-26)
- **D1: moved.**
- `docs/plans/chat-01/README.md:342` defers "the actual execution/writer-claim
record" to CHAT-02.
- `docs/plans/chat-01c/README.md:217–218` puts R3-1 (reconciling dispatched
but unconsumed input) in "CHAT-02 adapter evidence".
- A read-only reader needs neither, so both move to CHAT-03, which owns
binding and the single writer.
- The published CHAT-01 and CHAT-01C text stays as it is. The move is
recorded on #1507 (comment 26538) and in
`docs/plans/2026-09-26_lead-decisions.md` item 8, so a reader of line
342 can find it.
- **D2: accepted.**
- Pi ships in CHAT-02. Claude's catalogue waits for B1, which is defined at
`docs/plans/chat-00/README.md:193` and restated at
`chat-01/README.md:382`. Line 66 of CHAT-00 is the capability row that
shows the gap: Claude's persisted branch format and leaf selection.
- `unsupported-harness` is a **new CHAT-02 reason value**, not an existing
contract code. The CHAT-01 schema has only a nullable `unsupportedReason`
field, and this value fills it.
- This narrows the plan's "both harnesses". Sage records it in the lead
decisions file.
- Owner after B1 (proposed; Sage confirms): CHAT-03 supplies the Claude
catalogue and history. It already owns Claude engine integration and is
gated by B1. That gives CHAT-06's both-harness gate an owner.
- **D3: accepted.** `packages/conversation` is a library with no server. The
board adds the two read-only routes, with the §2.1 guard, in
`packages/control-board/src/serve.mjs` and `scan.mjs`. Darkwing reviews
that change before it lands. The coordination note goes to him when the
backend reaches review. §1.5 asks Sage whether the guard should also cover
the existing routes.
- **D4: Dewey authors both.** Backend first, then the Console against its
fixtures. Filbert reviews the brief now and the code after.
- **D5: stays with Jason.** Sage's live reply test passed on the transcript
and board legs. The Console leg waits for Jason's §1.4 answer. Sage is
asking him for the go on CHAT-02. No code goes under
`packages/conversation` until Sage relays his answer.
## 4. Acceptance
- Every fixture in §2.1 (F1–F17) and the §2.2 hostile-render fixture is
covered by a test, and those tests pass.
- The §2.3 regression passes on the served WebUI, through the real board
routes.
- These still pass: `node docs/plans/chat-00/check.mjs`, `chat-01/check.mjs`,
`chat-01c/check.mjs`, and the control-board, webui and seat suites.
- Browser evidence: the conversation view at 320 and 1440, in both themes,
showing:
- a long answer;
- a tool call;
- the hostile-content fixture rendered inert;
- a malformed-line marker;
- a reconcile marker.
There is no horizontal overflow at 320.
- Filbert approves the exact candidate hashes, and Darkwing reviews the
board routes.
- Live check: one board send with a long answer, shown in full in the view.
## 5. Not in scope
- live adapters, control, streaming, queues, uploads and approvals;
- fleet seats;
- Claude history until B1;
- changes to `tools/tmux/**`, `roles/**` or session logs;
- the `/` paste hazard (CHAT-03I);
- authenticated multi-actor cursors (CHAT-04R).
## 6. R2 findings and where R3 answers them
| Filbert R2 | R3 |
|---|---|
| §1 finding 1: Console leg overclaimed; D5 "passed" | §1 opening; §1.2; D5 |
| §1 finding 2: order-only attribution, 7 interleaved | §1.1 item 1; §2.3 point 5 |
| §1 finding 3: the clip is in the board | §1 opening; §2.3 point 2 |
| §1 finding 4: item 4 unpinned | `evidence/replay-0913/`; §1.1 item 4 |
| §1 finding 5: five directories scanned | §1.1 item 1 |
| §2 finding 1: cursor refusals | F6 |
| §2 finding 2: touched logs | F5 |
| §2 finding 3: same-inode rewrite | Epoch rule; F4 |
| §2 finding 4: registrations, cwd | Catalogue sources; F9; F10 |
| §2 finding 5: parentSession | Parser; F11 |
| §2 finding 6: symlink race | Opening a file safely; F8 |
| §2 finding 7: no-write check | F17 |
| §2 finding 8: Host check, actor | Board routes; Cursors; F16; §1.5 |
| §2 finding 9: byte cap, renderer | F14; §2.2 hostile-render fixture |
| §3 points 1–5 | §2.3 points 1–6 |
| §4: D1 line; D2 citations, reason value, owner | §3 D1, D2 |
agents/dewey/work/chat-02/BRIEF.md
+382
View File
@@ -0,0 +1,382 @@
# CHAT-02 brief: read-only histories and Age (#1507, row 5)
Author: Dewey, 2026-09-26. R4. Filbert approved R3 (`3b81a3f2…`). R4
applies his two non-blocking nits: F17 and §1.1 item 1. His review, with the
R2 verdict and the R3 approval, is
`agents/filbert/work/chat-02-brief-r2-review-2026-09-26.md`. Earlier revisions
are frozen as `BRIEF-r1-314da8b0.md`, `BRIEF-r2-ed177bf6.md` and
`BRIEF-r3-3b81a3f2.md`. §6 maps his R2 findings to their changes. No source
edits.
Plan row: `docs/plans/2026-09-13_webui-session-chat.md` line 214. Depends on
CHAT-01 (`28d4e98a`) and uses the CHAT-01C companion (`b023841c`).
## 1. Is there a second defect in the return path?
Short answer: no second return-path defect has shown up for repository Pi
seats. Two legs are shown directly: answers reach the transcript, and the
board serves them. The Console leg is shown only by replaying the 09-13
code (item 4), until Jason answers the §1.4 question about today's send.
The best explanation for what Jason hit on 09-13 is the product gap. The
board collapses the last answer to 240 characters
(`packages/control-board/src/scan.mjs`, `TEXT_LIMIT`, line 23 at ea00ec66
and line 25 at HEAD). The Console showed that one clipped field in an
inspector, with no conversation view and no pending signal. 42c08d52 fixed
the pending display. CHAT-02 covers the clip and the missing view, which means
the new history routes must not go through the board's summary text.
I found one real defect on the send side (§1.3). While reviewing the new
routes, I found a missing Host check on the board (§1.5).
### 1.1 Evidence so far
1. **Transcripts.** `evidence/sends.mjs` walks every `.pi/state/*/sessions`
file. That is five seat directories: darkwing, dewey, filbert, researcher
and sage, and sage has no board sends. For each board send, the script
records the *first* later assistant entry with `stopReason: stop`. The
output is `evidence/board-sends-repo-pi.jsonl`.
- Of 30 sends, 29 are followed by a stop answer in the same file.
- Latency is 1.5 s minimum, 14.6 s median and 1019 s maximum.
- 16 of the 29 answers exceed 240 characters, so the board clipped them.
- The attribution is by file order only. In 7 of the 29, another
user-role entry lands between the send and the answer, so the answer may
also cover that later input. Filbert rechecked: all 7 are peer
agent-sends (dewey to darkwing three times, rocko to darkwing, darkwing
to dewey twice, filbert to dewey). Jason's 09-13 question (item 3) is not
one of the 7.
- Filbert confirmed that none of the nine files involved branches, so file
order equals branch order.
2. **The unanswered send.** Filbert, 2026-09-12T16:33:17Z. The seat started
working on it and read files until 16:35:44Z. The last entry is an
`aborted` assistant turn, and a new filbert session began at 16:36:26Z.
The seat was relaunched mid-turn, so the answer was lost in the seat, not
in the return path. §2.3 point 5 turns this into a test.
3. **Jason's report window.** At 2026-09-13T00:49:59Z he asked dewey "What
are the Gate E criteria?". The answer landed at 00:50:07Z: 365 characters,
which the board clipped to 240. He wrote the report at 00:56:51Z. It says
the sessions "are all cards within the project dashboard and not available
as independent chat interfaces". That describes the missing view, not a
missing answer.
4. **The 09-13 Console, replayed.** The pinned files are in
`evidence/replay-0913/`: the test, the diff against 42c08d52, the TAP
output and a README.
- The scratch extract of `ea00ec66` is byte-identical to that commit (45
files checked).
- The test is the 42c08d52 return-flow test with the Age, pending and
clear-once assertions removed, since ea00ec66 has none of those.
- It passed (1/1, 20.7 s): the new answer arrived through the 10 s poll,
once, in the open inspector.
- The replay's answer is short, so it does not exercise the clip.
5. **Jason's live send today.** Researcher, user entry at
2026-09-26T20:10:57.429Z, answer "pong" at 20:11:06.173Z (8.7 s).
- At 20:15:18Z, `/api/board` showed the row `idle`, with
`lastAssistantText: "pong"`, the same `sessionFile` and a live
registration (`evidence/board-researcher-*.json`).
- The live WebUI (pid 1266267, port 7330) serves `app.js` byte-identical
to HEAD (`d1a51646…`). Its server code has not changed since that
process started on 09-13 at 16:19 CDT.
- The board (pid 3977979, port 7331) started today at 15:03 CDT.
### 1.2 What is still unverified
- **What Jason's screen showed.** I have the transcript and the board JSON
for today's send, but not the Console DOM. The Console leg for a live send
is unproven until Jason answers §1.4.
- **The 09-13 processes.** The board keeps no reply receipts, and the 09-13
processes are gone. Item 4 shows that the same code works. It cannot show
what those processes served.
- **Fleet seats.** I did not scan `~/.mosaic` transcripts. They are out of
scope for CHAT-02.
- **The clip in a live send.** "pong" is 4 characters, so today's send
doesn't exercise the clip.
### 1.3 Send-side defect found in passing
Today's user entry starts with `/`:
/[dragon-lin:control-board -> dragon-lin:researcher] ping
`agent-send.sh` adds the header, so the `/` was already in the Pi composer
when the paste arrived. `send-message.sh` pastes onto whatever the composer
holds, then presses Enter. Here Pi treated the result as plain text. If the
composer had held a real command prefix, a board reply could have become a
Pi slash command.
Sage confirmed this as a safety gap under CHAT-03I/B3 and recorded it in
DEFERRED.md. It is on #1507 (comment 26538). There is no `tools/tmux` change
now.
### 1.4 Evidence that settles it
Sage is putting one question to Jason: **after today's ping, did "pong"
appear in the Console inspector without pressing Refresh?**
- **Yes:** there is no second defect, and CHAT-02 proceeds as a
product-gap fix.
- **No:** `/api/board` had the answer, so the defect is in the Console or the
WebUI proxy. Capture the Console DOM and the `/api/board` network log during
one send.
- **Missing from `/api/board`:** that would point at the scanner. **Missing
from the transcript:** that would point at transport or the seat. Neither
happened today.
One more live send, asking for an answer over 240 characters, would show
the clip ending in "…".
### 1.5 Board Host check (found while reviewing D3)
The Console server checks `Host` and `Origin`
(`packages/webui/src/serve.mjs` lines 54–59). The board server does not. It
checks only the bind address.
A DNS-rebinding page that reaches port 7331 could:
- read `/api/board`: 240 characters per row, plus task and cwd;
- `POST /api/reply` with `application/json`. The board requires that content
type but not a same-origin `Host`, so the text would be pasted into a live
seat pane.
Modern browsers restrict some local-network requests, but I have not tested
any browser against this. That makes it a finding, not a demonstrated
exploit.
The new D3 routes must carry the guard (§2.1). Whether the same guard should
be applied to the existing board routes in that `serve.mjs` change is Sage's
decision. I recommend doing it.
## 2. Scope
CHAT-02 per the plan, narrowed by D2:
- a Pi catalogue;
- safe, full branch history, with pagination and cursors;
- separate timestamps;
- relative Age from last activity;
- no writes to logs.
It is read-only. Opening a conversation never resumes, forks, launches or
controls anything.
### 2.1 Backend: `packages/conversation/**` (Dewey, D4)
**Catalogue sources.** Only approved source roots count: the board's
repository specs (`<repo>/.pi/state/<seat>/sessions`). There is no global
scan, and no path comes from the browser. A seat registration is
seat-written, so it is a hint, not authority (CHAT-01 line 62). Its
`sessionFile` is accepted only when the file is under an approved root for
the same project. Each conversation gets an opaque ID, which the server maps
to a file. Catalogue creation time, engine launch time and last activity are
separate nullable fields.
**Opening a file safely.**
- Check every path component with `lstat`: no symlinks, and it stays inside
the root.
- Open with `O_RDONLY | O_NOFOLLOW`, then `fstat` the descriptor. The
descriptor's (dev, ino) must match the checked path.
- Read only from that descriptor.
- Never use `SessionManager.open`, which can migrate files (CHAT-00 line 67).
**Parser.**
- Build the `id`/`parentId` tree and select a leaf explicitly. The default is
the last appended entry, which the implementer confirms against the pinned
Pi session docs. Other leaves are read-only branches.
- Compaction entries render as markers.
- Pi `get_entries` order is not a branch transcript (CHAT-00 line 66), so it
is not used.
- The parser never follows `parentSession`. The conversation still renders,
with a "forked from an earlier session" marker, and the parent file is never
opened.
- If the Pi header's `cwd` names another project, the conversation is refused.
- A malformed line becomes an unavailable part at its position, and reading
continues. A truncated trailing line is incomplete, not an error.
**Pages.**
- CHAT-01 limits: at most 100 parts, at most 8 MiB of serialized UTF-8 bytes
(enforced on bytes, not characters), 64 blocks per part, and 262144
characters per string.
- Oversize content splits into continuation parts and is never clipped.
**Snapshots and epochs.**
- The page reads up to the snapshot length that its cursor pins, so growth
during a read is cut there.
- A source epoch is (dev, ino) plus a SHA-256 of the prefix the snapshot
covers. Growth past that prefix is the same epoch.
- A different inode, a shorter file, or a changed prefix digest (an in-place
rewrite with the same inode) is a new epoch.
**Cursors.**
- A cursor binds actor, purpose, conversation, branch, snapshot, source epoch
and expiry.
- These all refuse, keep the old view and show a reconcile marker: an
unknown, foreign, expired or source-replaced cursor.
- Nothing ever switches files silently.
- On this unauthenticated loopback route there is one actor,
`local-operator`, and cursors bind to it. That is not multi-actor safety.
Authenticated actors come with CHAT-04R and must not be claimed here.
**Board routes (D3).** Two read-only `GET` routes, catalogue and page.
- `Host` must be the loopback name and the board's own port.
- A cross-origin `Origin` is refused.
- No CORS headers are sent.
- Responses are `application/json` with `nosniff` and `no-store`.
**Fixtures.** Each one names its expected refusal or result.
| # | Fixture | Expected |
|---|---|---|
| F1 | Malformed line | Unavailable part at its position, reading continues |
| F2 | Truncated trailing line | Incomplete marker |
| F3 | Replaced file (new inode) | Old cursors refuse, reconcile |
| F4 | Same-inode prefix rewrite | Old cursors refuse, reconcile |
| F5 | Touched: growth between two pages and during one read | Same epoch, page cut at the pinned length |
| F6 | Unknown, foreign (actor, purpose, conversation or branch) and expired cursor | Each refuses and keeps the old view |
| F7 | Symlink at the file and at a directory component | Refused, never opened |
| F8 | File swapped for a symlink between catalogue and read | Refused (O_NOFOLLOW or a dev/ino mismatch) |
| F9 | Registration naming a file outside the roots, a symlink, or another project's file | Refused, never opened |
| F10 | Pi header `cwd` naming another project | Refused |
| F11 | `parentSession` pointing outside the root | Renders with a marker, and the parent is never opened |
| F12 | Branched file with two leaves | Default leaf shown, other branch readable, no merge |
| F13 | Compaction | Marker, then retained content |
| F14 | A string over 262144 characters, and a multibyte page reaching 8 MiB before 100 parts | Continuation parts, reassembled exactly, byte cap enforced |
| F15 | Claude harness | `unsupported-harness` refusal (D2) |
| F16 | Foreign `Host` and a cross-origin `Origin` on both routes | 403, no CORS headers |
| F17 | No writes | Before and after every reader operation (catalogue, open, page), in every fixture, including the ones that mutate files on purpose between reads (F3, F4, F5, §2.3 point 6): size, SHA-256, mtime, (dev, ino), and the session directory listing (no new files) are unchanged. Atime is excluded because relatime can update it on read. |
### 2.2 Console: `packages/webui/**` (Dewey)
This is the smallest thing that answers the 09-13 complaint: a read-only
conversation view per session, opened from the card, the table or the
inspector.
- It renders the selected branch in full, with nothing clipped: user text,
assistant text, and tool calls and results collapsed.
- Thinking is hidden by default.
- Markdown is untrusted, so it has no active HTML, no unsafe URLs and no
terminal escapes.
- Age stays as 42c08d52 shipped it.
- Reply keeps the existing board path. The view gets new answers through
polling. Streaming belongs to CHAT-03.
The full chat UI (sidebar, composer, queue, approvals and uploads) stays in
CHAT-05.
**Hostile-render fixture (R1).** Assistant text and tool output contain:
- HTML, including `<script>` and `<img onerror>`;
- a `javascript:` link;
- ANSI and OSC terminal escapes.
All of it renders as inert text. The test asserts that no element, handler or
navigation was created.
### 2.3 Return-flow regression (required by the plan)
The regression runs on the real board, the real D3 routes and the real
WebUI, the way the existing test does. Nothing is injected into the WebUI.
1. **Path.** Send from the conversation view. The seat then appends a user
entry, a toolCall, a toolResult and a final answer.
2. **Exactness.** The answer has a sentinel after character 240 and another
at the very end. The view shows the exact text, with no "…", once.
3. **Continuation.** A second answer is long enough to split into
continuation parts. The test checks that it reassembles exactly and in
order.
4. **Thread order.** In the view, the sent message comes first, then the
collapsed tool call and result, then the answer.
5. **Interleaving.** A peer agent-send lands before the final answer, as in
§1.1 item 1. Both entries show, in file order.
6. **Relaunch mid-turn,** modelled on the 09-12 filbert case. A new session
file appears. The open view keeps its file, shows the reconcile marker and
never switches silently.
7. **Timing.** A delayed-result variant has the toolResult land after a poll.
The draft and caret survive, and no manual refresh is used.
This covers Pi only (D2).
## 3. Decisions (Sage, 2026-09-26)
- **D1: moved.**
- `docs/plans/chat-01/README.md:342` defers "the actual execution/writer-claim
record" to CHAT-02.
- `docs/plans/chat-01c/README.md:217–218` puts R3-1 (reconciling dispatched
but unconsumed input) in "CHAT-02 adapter evidence".
- A read-only reader needs neither, so both move to CHAT-03, which owns
binding and the single writer.
- The published CHAT-01 and CHAT-01C text stays as it is. The move is
recorded on #1507 (comment 26538) and in
`docs/plans/2026-09-26_lead-decisions.md` item 8, so a reader of line
342 can find it.
- **D2: accepted.**
- Pi ships in CHAT-02. Claude's catalogue waits for B1, which is defined at
`docs/plans/chat-00/README.md:193` and restated at
`chat-01/README.md:382`. Line 66 of CHAT-00 is the capability row that
shows the gap: Claude's persisted branch format and leaf selection.
- `unsupported-harness` is a **new CHAT-02 reason value**, not an existing
contract code. The CHAT-01 schema has only a nullable `unsupportedReason`
field, and this value fills it.
- This narrows the plan's "both harnesses". Sage records it in the lead
decisions file.
- Owner after B1 (proposed; Sage confirms): CHAT-03 supplies the Claude
catalogue and history. It already owns Claude engine integration and is
gated by B1. That gives CHAT-06's both-harness gate an owner.
- **D3: accepted.** `packages/conversation` is a library with no server. The
board adds the two read-only routes, with the §2.1 guard, in
`packages/control-board/src/serve.mjs` and `scan.mjs`. Darkwing reviews
that change before it lands. The coordination note goes to him when the
backend reaches review. §1.5 asks Sage whether the guard should also cover
the existing routes.
- **D4: Dewey authors both.** Backend first, then the Console against its
fixtures. Filbert reviews the brief now and the code after.
- **D5: stays with Jason.** Sage's live reply test passed on the transcript
and board legs. The Console leg waits for Jason's §1.4 answer. Sage is
asking him for the go on CHAT-02. No code goes under
`packages/conversation` until Sage relays his answer.
## 4. Acceptance
- Every fixture in §2.1 (F1–F17) and the §2.2 hostile-render fixture is
covered by a test, and those tests pass.
- The §2.3 regression passes on the served WebUI, through the real board
routes.
- These still pass: `node docs/plans/chat-00/check.mjs`, `chat-01/check.mjs`,
`chat-01c/check.mjs`, and the control-board, webui and seat suites.
- Browser evidence: the conversation view at 320 and 1440, in both themes,
showing:
- a long answer;
- a tool call;
- the hostile-content fixture rendered inert;
- a malformed-line marker;
- a reconcile marker.
There is no horizontal overflow at 320.
- Filbert approves the exact candidate hashes, and Darkwing reviews the
board routes.
- Live check: one board send with a long answer, shown in full in the view.
## 5. Not in scope
- live adapters, control, streaming, queues, uploads and approvals;
- fleet seats;
- Claude history until B1;
- changes to `tools/tmux/**`, `roles/**` or session logs;
- the `/` paste hazard (CHAT-03I);
- authenticated multi-actor cursors (CHAT-04R).
## 6. R2 findings and where R3 answers them
| Filbert R2 | R3 |
|---|---|
| §1 finding 1: Console leg overclaimed; D5 "passed" | §1 opening; §1.2; D5 |
| §1 finding 2: order-only attribution, 7 interleaved | §1.1 item 1; §2.3 point 5 |
| §1 finding 3: the clip is in the board | §1 opening; §2.3 point 2 |
| §1 finding 4: item 4 unpinned | `evidence/replay-0913/`; §1.1 item 4 |
| §1 finding 5: five directories scanned | §1.1 item 1 |
| §2 finding 1: cursor refusals | F6 |
| §2 finding 2: touched logs | F5 |
| §2 finding 3: same-inode rewrite | Epoch rule; F4 |
| §2 finding 4: registrations, cwd | Catalogue sources; F9; F10 |
| §2 finding 5: parentSession | Parser; F11 |
| §2 finding 6: symlink race | Opening a file safely; F8 |
| §2 finding 7: no-write check | F17 |
| §2 finding 8: Host check, actor | Board routes; Cursors; F16; §1.5 |
| §2 finding 9: byte cap, renderer | F14; §2.2 hostile-render fixture |
| §3 points 1–5 | §2.3 points 1–6 |
| §4: D1 line; D2 citations, reason value, owner | §3 D1, D2 |
agents/dewey/work/chat-02/evidence/board-researcher-2026-09-26T20-15-18Z.json
+18
View File
@@ -0,0 +1,18 @@
{
"generatedAt": "2026-09-26T20:15:18.304Z",
"row": {
"agent": "researcher",
"project": "mosaic-stack",
"state": "idle",
"alive": true,
"sessionFile": "/mnt/storage/src/mosaic-stack/.pi/state/researcher/sessions/2026-09-13T19-52-28-745Z_01a09c54-0b48-7154-addd-8fdce875aa4a.jsonl",
"lastActivity": "2026-09-26T20:11:06.173Z",
"ageSeconds": 251,
"lastAssistantText": "pong",
"waitingOnYou": false,
"tmux": {
"socket": null,
"session": "researcher"
}
}
}
agents/dewey/work/chat-02/evidence/board-sends-repo-pi.jsonl
+30
View File
@@ -0,0 +1,30 @@
{"file":".pi/state/darkwing/sessions/2026-09-12T16-06-52-940Z_01a0965f-250c-70de-88f4-ac12e3669367.jsonl","sent":"2026-09-12T16:23:39.405Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] pizza?","firstStopAnswer":"2026-09-12T16:23:54.910Z","answerChars":74,"nextUser":"2026-09-12T16:38:39.266Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-06-52-940Z_01a0965f-250c-70de-88f4-ac12e3669367.jsonl","sent":"2026-09-12T16:38:39.266Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] tacos? (control-board: answer ","firstStopAnswer":"2026-09-12T16:38:42.476Z","answerChars":13,"nextUser":null}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-12T16:45:06.894Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] Read docs/plans/CURRENT.md and","firstStopAnswer":"2026-09-12T16:55:26.610Z","answerChars":161,"nextUser":"2026-09-12T17:02:40.313Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T00:17:17.246Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] Gate D is written in CURRENT.m","firstStopAnswer":"2026-09-13T00:19:04.273Z","answerChars":170,"nextUser":"2026-09-13T00:17:56.026Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T01:20:00.056Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] I do NOT want to clobber the w","firstStopAnswer":"2026-09-13T01:20:14.688Z","answerChars":588,"nextUser":"2026-09-13T01:20:40.591Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T01:28:29.259Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] I just relaunched the rocko se","firstStopAnswer":"2026-09-13T01:40:52.276Z","answerChars":299,"nextUser":"2026-09-13T01:28:43.425Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T02:28:05.633Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] I stepped away for a bit. What","firstStopAnswer":"2026-09-13T02:28:20.119Z","answerChars":720,"nextUser":"2026-09-13T02:30:23.812Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T02:30:23.812Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] approved (control-board: answe","firstStopAnswer":"2026-09-13T02:47:22.844Z","answerChars":195,"nextUser":"2026-09-13T02:32:08.207Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T04:10:18.210Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] Status? (control-board: answer","firstStopAnswer":"2026-09-13T04:10:24.562Z","answerChars":310,"nextUser":"2026-09-13T04:10:57.319Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T04:10:57.319Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] Is this actively moving? Which","firstStopAnswer":"2026-09-13T04:11:03.773Z","answerChars":262,"nextUser":"2026-09-13T04:11:40.327Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T04:11:40.327Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] Keep moving. DO NOT STOP FOR R","firstStopAnswer":"2026-09-13T04:26:18.709Z","answerChars":277,"nextUser":"2026-09-13T04:25:22.317Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T04:50:50.715Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] Need anything from me? (contro","firstStopAnswer":"2026-09-13T04:51:01.486Z","answerChars":223,"nextUser":"2026-09-13T04:53:09.729Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T19:51:30.379Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] What is needed from me? (contr","firstStopAnswer":"2026-09-13T19:51:36.688Z","answerChars":276,"nextUser":"2026-09-13T19:51:52.410Z"}
{"file":".pi/state/darkwing/sessions/2026-09-12T16-44-19-503Z_01a09681-6cae-7141-89d6-723da6a23794.jsonl","sent":"2026-09-13T19:51:52.410Z","head":"[dragon-lin:control-board -> dragon-lin:darkwing] proceed (control-board: answer","firstStopAnswer":"2026-09-13T19:57:38.104Z","answerChars":323,"nextUser":"2026-09-13T20:01:37.928Z"}
{"file":".pi/state/dewey/sessions/2026-09-13T00-10-59-217Z_01a0981a-5b11-7235-873b-7babccdc1cab.jsonl","sent":"2026-09-13T00:17:04.404Z","head":"[dragon-lin:control-board -> dragon-lin:dewey] Read docs/plans/CURRENT.md and ex","firstStopAnswer":"2026-09-13T00:32:56.857Z","answerChars":256,"nextUser":"2026-09-13T00:18:15.838Z"}
{"file":".pi/state/dewey/sessions/2026-09-13T00-10-59-217Z_01a0981a-5b11-7235-873b-7babccdc1cab.jsonl","sent":"2026-09-13T00:49:59.771Z","head":"[dragon-lin:control-board -> dragon-lin:dewey] What are the Gate E criteria? (co","firstStopAnswer":"2026-09-13T00:50:07.519Z","answerChars":365,"nextUser":"2026-09-13T00:56:51.198Z"}
{"file":".pi/state/dewey/sessions/2026-09-13T00-10-59-217Z_01a0981a-5b11-7235-873b-7babccdc1cab.jsonl","sent":"2026-09-13T01:03:12.462Z","head":"[dragon-lin:control-board -> dragon-lin:dewey] Q4: agreed Q5: yes Q6: agreed. We","firstStopAnswer":"2026-09-13T01:03:42.772Z","answerChars":1626,"nextUser":"2026-09-13T01:03:42.772Z"}
{"file":".pi/state/dewey/sessions/2026-09-13T00-10-59-217Z_01a0981a-5b11-7235-873b-7babccdc1cab.jsonl","sent":"2026-09-13T01:06:15.824Z","head":"[dragon-lin:control-board -> dragon-lin:dewey] Q8: agreed Q9: agreed Q10: agreed","firstStopAnswer":"2026-09-13T01:07:02.468Z","answerChars":420,"nextUser":"2026-09-13T01:07:40.783Z"}
{"file":".pi/state/dewey/sessions/2026-09-13T00-10-59-217Z_01a0981a-5b11-7235-873b-7babccdc1cab.jsonl","sent":"2026-09-13T01:10:23.469Z","head":"[dragon-lin:control-board -> dragon-lin:dewey] Q12: agreed Q13: agreed Q14: agre","firstStopAnswer":"2026-09-13T01:11:18.147Z","answerChars":1699,"nextUser":"2026-09-13T01:12:45.940Z"}
{"file":".pi/state/dewey/sessions/2026-09-13T00-10-59-217Z_01a0981a-5b11-7235-873b-7babccdc1cab.jsonl","sent":"2026-09-13T01:12:45.940Z","head":"[dragon-lin:control-board -> dragon-lin:dewey] Q17: agreed Q18: agreed Q19: agre","firstStopAnswer":"2026-09-13T01:21:42.659Z","answerChars":1365,"nextUser":"2026-09-13T01:18:40.502Z"}
{"file":".pi/state/dewey/sessions/2026-09-13T00-10-59-217Z_01a0981a-5b11-7235-873b-7babccdc1cab.jsonl","sent":"2026-09-13T01:22:57.512Z","head":"[dragon-lin:control-board -> dragon-lin:dewey] Q20: agreed Q21: yes Q22: agreed ","firstStopAnswer":"2026-09-13T01:24:20.818Z","answerChars":1418,"nextUser":"2026-09-13T01:24:05.743Z"}
{"file":".pi/state/filbert/sessions/2026-09-12T16-26-47-117Z_01a09671-5dcd-720a-853d-b9dc5ff30872.jsonl","sent":"2026-09-12T16:28:52.615Z","head":"[dragon-lin:control-board -> dragon-lin:filbert] pizza?","firstStopAnswer":"2026-09-12T16:29:06.948Z","answerChars":74,"nextUser":null}
{"file":".pi/state/filbert/sessions/2026-09-12T16-30-08-084Z_01a09674-6ed4-724b-a9c6-ed2e9a9f9b15.jsonl","sent":"2026-09-12T16:30:27.068Z","head":"[dragon-lin:control-board -> dragon-lin:filbert] pizza?","firstStopAnswer":"2026-09-12T16:30:28.611Z","answerChars":42,"nextUser":null}
{"file":".pi/state/filbert/sessions/2026-09-12T16-32-47-764Z_01a09676-de94-71fe-b9fb-f2705b57f346.jsonl","sent":"2026-09-12T16:33:17.505Z","head":"[dragon-lin:control-board -> dragon-lin:filbert] pizza?","firstStopAnswer":null,"answerChars":null,"nextUser":null}
{"file":".pi/state/filbert/sessions/2026-09-12T16-36-26-218Z_01a0967a-33e9-72f4-b511-9264d71b000e.jsonl","sent":"2026-09-12T16:36:36.722Z","head":"[dragon-lin:control-board -> dragon-lin:filbert] pizza? (control-board: answer i","firstStopAnswer":"2026-09-12T16:36:39.912Z","answerChars":15,"nextUser":null}
{"file":".pi/state/filbert/sessions/2026-09-12T16-38-58-597Z_01a0967c-8724-7151-a812-ca70dc1b24cd.jsonl","sent":"2026-09-12T16:39:21.527Z","head":"[dragon-lin:control-board -> dragon-lin:filbert] chocolate? (control-board: answ","firstStopAnswer":"2026-09-12T16:39:57.717Z","answerChars":552,"nextUser":"2026-09-12T16:52:58.831Z"}
{"file":".pi/state/researcher/sessions/2026-09-13T19-52-28-745Z_01a09c54-0b48-7154-addd-8fdce875aa4a.jsonl","sent":"2026-09-13T21:19:50.889Z","head":"[dragon-lin:control-board -> dragon-lin:researcher] Reply exactly BOARD_REPLY_OK","firstStopAnswer":"2026-09-13T21:19:57.102Z","answerChars":14,"nextUser":"2026-09-14T00:40:03.263Z"}
{"file":".pi/state/researcher/sessions/2026-09-13T19-52-28-745Z_01a09c54-0b48-7154-addd-8fdce875aa4a.jsonl","sent":"2026-09-14T00:40:03.263Z","head":"[dragon-lin:control-board -> dragon-lin:researcher] Reply exactly: Input needed:","firstStopAnswer":"2026-09-14T00:40:10.107Z","answerChars":39,"nextUser":"2026-09-14T00:41:14.949Z"}
{"file":".pi/state/researcher/sessions/2026-09-13T19-52-28-745Z_01a09c54-0b48-7154-addd-8fdce875aa4a.jsonl","sent":"2026-09-14T00:41:14.949Z","head":"[dragon-lin:control-board -> dragon-lin:researcher] Confirmed. Reply exactly TES","firstStopAnswer":"2026-09-14T00:41:20.185Z","answerChars":13,"nextUser":"2026-09-26T20:10:57.429Z"}
{"file":".pi/state/researcher/sessions/2026-09-13T19-52-28-745Z_01a09c54-0b48-7154-addd-8fdce875aa4a.jsonl","sent":"2026-09-26T20:10:57.429Z","head":"/[dragon-lin:control-board -> dragon-lin:researcher] ping (control-board: answer","firstStopAnswer":"2026-09-26T20:11:06.173Z","answerChars":4,"nextUser":null}
agents/dewey/work/chat-02/evidence/replay-0913/README.md
+17
View File
@@ -0,0 +1,17 @@
# 09-13 Console replay (brief §1.1 item 4)
Source: `git archive ea00ec66` of `packages/webui`, `packages/control-board`,
`packages/seat`, `tools/tmux` and `package.json`, extracted to a scratch
directory, with `node_modules` symlinked from the checkout. All 45 extracted
files were checked byte-identical to `ea00ec66` on 2026-09-26.
Test: `return-flow-0913.test.mjs` is the 42c08d52 `return-flow.test.mjs`
with the Age, pending-notice and clear-once assertions removed, because ea00ec66 has
neither feature. `removed-vs-42c08d52.diff` is the whole difference.
Run: `node --test --test-reporter=tap packages/webui/tests/return-flow-0913.test.mjs`
from the scratch root. Output: `replay.tap` (1 pass, 20.7 s).
What it shows: at ea00ec66 the new answer arrives in the open inspector
through the 10 s poll, once. The answer is short, so this replay does not
exercise the board's 240-character clip.
agents/dewey/work/chat-02/evidence/replay-0913/removed-vs-42c08d52.diff
+16
View File
@@ -0,0 +1,16 @@
40d39
< assert.match(await b.evaluate('document.querySelector("table.sessions tbody td:last-child").textContent'), /^1m ago\d{4}-\d\d-\d\dT/);
43d41
< assert.match(await inspection(), /Last activity1m ago \(\d{4}-/);
54,56d51
< const pending = await inspection();
< assert.match(pending, /Waiting for a reply/, 'the page says a reply is pending');
< assert.doesNotMatch(pending, /Last assistant text/, 'the previous answer is not presented as the latest reply');
68,74d62
< // The notice clears once. Later work with no new send must not bring back the old sentAt (Filbert R1 item 2).
< appendFileSync(file, message(at(4), { role: 'user', content: [{ type: 'text', text: 'typed in the seat terminal' }] }));
< await b.evaluate('document.querySelector("#refresh").click()');
< await wait('[...document.querySelectorAll("#inspection dt")].find(d => d.textContent === "State")?.nextElementSibling.textContent === "working"');
< const later = await inspection();
< assert.doesNotMatch(later, /Waiting for a reply|before your message/);
< assert.match(later, /Last assistant text/);
agents/dewey/work/chat-02/evidence/replay-0913/replay.tap
+16
View File
@@ -0,0 +1,16 @@
TAP version 13
# Subtest: reported return flow and relative Age: reply sent from the inspector, then the new answer appears there without manual refresh
ok 1 - reported return flow and relative Age: reply sent from the inspector, then the new answer appears there without manual refresh
---
duration_ms: 20653.73802
type: 'test'
...
1..1
# tests 1
# suites 0
# pass 1
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 20715.39878
agents/dewey/work/chat-02/evidence/replay-0913/return-flow-0913.test.mjs
+64
View File
@@ -0,0 +1,64 @@
// Jason's 2026-09-13 report (#1507 comment 26082): sending works, the return
// flow does not. This replays his sequence against the real board scanner and
// WebUI: send, then the seat appends user, toolCall, toolResult and a new final
// answer. The answer must appear in the SAME open inspector through auto-refresh
// alone, once, without the previous answer passing as the reply, and without
// losing a draft typed meanwhile. Session-file polling only: the live adapters
// and streaming belong to CHAT-03, not this test.
import { test } from 'node:test';
import assert from 'node:assert/strict';
import { mkdtempSync, mkdirSync, writeFileSync, appendFileSync, rmSync } from 'node:fs';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { startServer as startBoard } from '../../control-board/src/serve.mjs';
import { makeRegistration, writeRegistration } from '../../seat/src/seat.mjs';
import { startServer } from '../src/serve.mjs';
import { browser } from './browser.mjs';
import { close } from './fixture.mjs';
const at = s => new Date(Date.now() + s * 1000).toISOString();
const message = (timestamp, m) => JSON.stringify({ type: 'message', timestamp, message: m }) + '\n';
const assistant = (timestamp, text) => message(timestamp, { role: 'assistant', stopReason: 'stop', content: [{ type: 'text', text }] });
test('reported return flow and relative Age: reply sent from the inspector, then the new answer appears there without manual refresh', { timeout: 90000 }, async () => {
const root = mkdtempSync(join(tmpdir(), 'webui-return-'));
let board, web, b;
try {
const sessionsDir = join(root, 'sessions'); mkdirSync(sessionsDir);
const file = join(sessionsDir, 's.jsonl');
writeFileSync(file, message(at(-120), { role: 'user', content: [{ type: 'text', text: 'Start' }] }) + assistant(at(-90), 'Input needed: OLD_ANSWER'));
const seatsDir = join(root, 'seats'), captures = [];
writeRegistration(seatsDir, makeRegistration({ resolved: { seat: 'fixture', project: 'repo', sessionsDir, seatDir: root, launchScript: join(root, 'unused.sh'), layout: 'repo', defaultWorkspace: root }, task: 'Fixed task', tmux: { session: 'fixture', socket: null }, pid: process.pid, now: () => new Date(Date.now() - 300000) }));
board = await startBoard({ port: 0, specs: [{ agent: 'fixture', project: 'repo', sessionsDir, tmux: {} }], boardDir: join(root, 'board'), seatsDir, isAlive: () => true, isPidAlive: () => true,
exec: (f, args) => { captures.push(args); return { status: 0, stdout: '', stderr: '' }; } });
web = await startServer({ port: 0, board: `http://127.0.0.1:${board.address().port}` });
b = await browser(); await b.viewport(1440, 1000);
const wait = (expression, ms = 20000) => b.evaluate(`(async()=>{for(const end=Date.now()+${ms};Date.now()<end;){if(${expression})return true;await new Promise(r=>setTimeout(r,100))}throw Error('timeout: '+${JSON.stringify(expression)})})()`);
const inspection = () => b.evaluate('document.querySelector("#inspection").textContent');
await b.navigate(`http://127.0.0.1:${web.address().port}`); await wait('document.querySelector("table.sessions [data-open]")');
// Relative Age (#1507): the board's ageSeconds, labelled as time since last activity, with the timestamp kept.
await b.evaluate('document.querySelector("table.sessions [data-open]").click()');
assert.match(await inspection(), /OLD_ANSWER/);
await b.evaluate('(() => { const t = document.querySelector("#reply"); t.value = "REPLY_FROM_JASON"; t.dispatchEvent(new Event("input", { bubbles: true })); document.querySelector(".reply-form").requestSubmit(); })()');
await wait('document.querySelector(".receipt")?.textContent.includes("delivered")');
assert.ok(captures.some(args => args.some(a => a.startsWith('REPLY_FROM_JASON\n'))), 'reply reached the transport');
assert.equal(await b.evaluate('document.querySelector("#reply").value'), '', 'delivered draft cleared');
// The seat takes the message and starts a tool call. No answer yet.
appendFileSync(file, message(at(0), { role: 'user', content: [{ type: 'text', text: 'REPLY_FROM_JASON' }] })
+ message(at(1), { role: 'assistant', stopReason: 'toolUse', content: [{ type: 'toolCall', id: 'call-1', name: 'read', arguments: { path: 'x' } }] }));
await wait('[...document.querySelectorAll("#inspection dt")].find(d => d.textContent === "State")?.nextElementSibling.textContent === "working"');
// Typed while the seat works; auto-refresh must keep it and the caret.
await b.evaluate('(() => { const t = document.querySelector("#reply"); t.focus(); t.value = "NEXT_DRAFT"; t.setSelectionRange(4, 4); t.dispatchEvent(new Event("input", { bubbles: true })); })()');
appendFileSync(file, message(at(2), { role: 'toolResult', toolCallId: 'call-1', toolName: 'read', content: [{ type: 'text', text: 'file body' }], isError: false })
+ assistant(at(3), 'Input needed: NEW_ANSWER'));
await wait('document.querySelector("#inspection").textContent.includes("NEW_ANSWER")');
const answered = await inspection();
assert.equal(answered.split('NEW_ANSWER').length, 2, 'answer shown once in the inspector');
assert.doesNotMatch(answered, /OLD_ANSWER|Waiting for a reply/);
assert.equal(await b.evaluate('document.querySelector("#inspector-title").textContent'), 'fixture', 'same conversation still open');
assert.deepEqual(await b.evaluate('(() => { const t = document.querySelector("#reply"); return [t.value, t.selectionStart, document.activeElement === t]; })()'), ['NEXT_DRAFT', 4, true]);
} finally { if (b) await b.close(); if (web) await close(web); if (board) await close(board); rmSync(root, { recursive: true, force: true }); }
});
agents/dewey/work/chat-02/evidence/researcher-pane-2026-09-26.txt
+7
View File
@@ -0,0 +1,7 @@
/[dragon-lin:control-board -> dragon-lin:researcher] ping
(control-board: answer in your own session as usual; the board reads your transcript. Do not agent-send to control-board.)
Thinking...
pong
agents/dewey/work/chat-02/evidence/sends.mjs
+16
View File
@@ -0,0 +1,16 @@
// Board-originated sends in pi session files: timestamps/roles only, no content beyond 80 chars of the send.
import { readFileSync, readdirSync, statSync } from 'node:fs'; import { join } from 'node:path';
const roots = process.argv.slice(2);
const walk = d => readdirSync(d).flatMap(n => { const p = join(d, n); const s = statSync(p); return s.isDirectory() ? walk(p) : n.endsWith('.jsonl') ? [p] : []; });
for (const root of roots) for (const f of walk(root)) {
const E = readFileSync(f, 'utf8').split('\n').filter(Boolean).map(l => { try { return JSON.parse(l); } catch { return null; } }).filter(Boolean);
E.forEach((e, i) => {
if (e.type !== 'message' || e.message.role !== 'user') return;
const c = e.message.content; const t = typeof c === 'string' ? c : (c || []).filter(x => x.type === 'text').map(x => x.text).join('\n');
if (!/control-board ->/.test(t)) return;
const after = E.slice(i + 1).filter(x => x.type === 'message');
const firstA = after.find(x => x.message.role === 'assistant' && x.message.stopReason === 'stop');
const nextUser = after.find(x => x.message.role === 'user');
console.log(JSON.stringify({ file: f.replace(process.env.HOME, '~'), sent: e.timestamp, head: t.slice(0, 80).replace(/\n/g, ' '), firstStopAnswer: firstA?.timestamp ?? null, answerChars: firstA ? firstA.message.content.filter(x => x.type === 'text').map(x => x.text).join('\n').length : null, nextUser: nextUser?.timestamp ?? null }));
});
}