Decisions: 0210 addendum 2026-10-25, Buddy's chat is a plain conversation and Lazurio presets his settings (DEV-6676) - #648

…ull request, not a date

The root decision register dates an addendum by the day of its Publication.
For this one that is no longer 2026-10-25, the day Matěj decided. The
comments, the runbook and the contract test now name it by
HumanAndMachines/Lazurio#648, so they stay right whatever day it is
published. No behaviour changes.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ision 0210's addendum by its pull request

Pablo's round 3 found the runbook still dating the model-and-effort rule
"dodatek z 2026-10-25". Every mention of root decision 0210's plain-chat
addendum in the runbook now names HumanAndMachines/Lazurio#648; the host
appearance, which that addendum does not cover, is Matěj's request of
2026-10-25. Row 23 keeps its length, so the table keeps its padding. The
LazurioPlatform F60 references stay. No behaviour changes.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ull request, not a date

The root decision register dates an addendum by the day of its Publication.
For this one that is no longer 2026-10-25, the day Matěj decided. The
comments, the runbook and the contract test now name it by
HumanAndMachines/Lazurio#648, so they stay right whatever day it is
published. No behaviour changes.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ision 0210's addendum by its pull request

Pablo's round 3 found the runbook still dating the model-and-effort rule
"dodatek z 2026-10-25". Every mention of root decision 0210's plain-chat
addendum in the runbook now names HumanAndMachines/Lazurio#648; the host
appearance, which that addendum does not cover, is Matěj's request of
2026-10-25. Row 23 keeps its length, so the table keeps its padding. The
LazurioPlatform F60 references stay. No behaviour changes.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…n a new tab

Root decision 0210's addendum of HumanAndMachines/Lazurio#648 makes Buddy's
chat only the conversation, so Buddy's surface now shows no right panel of
T3, whatever the thread holds. ChatView reads the thread's panel there as
closed and empty (buddyRightPanelState), so neither the panel stored for the
thread, nor a link taken into it, nor a page an agent showed opens it, and
the chat column never gives way to a maximized panel. The surface does not
follow the thread's Environment browser tabs either.

A web link in the conversation opens in a new browser tab, without an opener
or referrer, never in T3's preview or right panel: Buddy's surface takes the
chat's `_blank` http(s) links in the window's capture phase, before the
chat's own handler and the Environment browser's. A click with a modifier
goes to the browser as on any page.

With no right panel on the surface, the previous commit's seams for the
panel's terminal tabs, its terminal toggle and Terminal in "+" are moot and
gone; the drawer, the thread's terminal state and Run in terminal stay.
Outside Buddy's T3 Code nothing changes. Browser tests show a stored open
panel drawn in T3 and not in Buddy's surface, and a link in Buddy's reply
opened in a new tab while T3's handlers never see the click, against T3's
own handling outside the surface. The contract test, the allowlist comment,
the runbook and the overlay specification describe the seams.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210's addendum of HumanAndMachines/Lazurio#648 makes Buddy's
chat only the conversation, yet Buddy's surface drew T3's terminal drawer
under it whenever the thread's stored terminal state was open: after a drawer
was opened on Buddy's thread earlier, or after a shell code block's Run in
terminal in Buddy's reply, which runs the command in a new shell in Buddy's
folder and opens the drawer. Drawing the drawer also attached to the thread's
terminal, which starts a shell where none runs.

In Buddy's surface the chat now reads the thread's drawer as closed
(buddyTerminalUiState), so the composer keeps its focus, and draws no terminal
drawer at all, not even one still closing or one of another thread. The right
panel shows none of the terminals the thread holds there (buddyPanelSurfaces,
with the first tab left in front where a terminal was), no terminal toggle
where it puts its controls, and no Terminal to open from "+" or Nová karta's
tools. Buddy's replies get no Run in terminal on a shell code block, through
the timeline's shared row state. Nothing is closed or stopped: the stored
state and the server's shells stay as they are, so a terminal opened elsewhere
keeps running on the server.

Outside Buddy's T3 Code nothing changes. Browser tests render T3's real
drawers, with a stand-in for the emulator, and the real timeline: with the
thread's terminal open, Buddy's surface shows no drawer and T3 shows it, and a
shell code block offers no Run in terminal in Buddy's reply but keeps it in
T3's. The contract test, the allowlist comment and the runbook describe the
new seams in ChatView.tsx and MessagesTimeline.tsx.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…n a new tab

Root decision 0210's addendum of HumanAndMachines/Lazurio#648 makes Buddy's
chat only the conversation, so Buddy's surface now shows no right panel of
T3, whatever the thread holds. ChatView reads the thread's panel there as
closed and empty (buddyRightPanelState), so neither the panel stored for the
thread, nor a link taken into it, nor a page an agent showed opens it, and
the chat column never gives way to a maximized panel. The surface does not
follow the thread's Environment browser tabs either.

A web link in the conversation opens in a new browser tab, without an opener
or referrer, never in T3's preview or right panel: Buddy's surface takes the
chat's `_blank` http(s) links in the window's capture phase, before the
chat's own handler and the Environment browser's. A click with a modifier
goes to the browser as on any page.

With no right panel on the surface, the previous commit's seams for the
panel's terminal tabs, its terminal toggle and Terminal in "+" are moot and
gone; the drawer, the thread's terminal state and Run in terminal stay.
Outside Buddy's T3 Code nothing changes. Browser tests show a stored open
panel drawn in T3 and not in Buddy's surface, and a link in Buddy's reply
opened in a new tab while T3's handlers never see the click, against T3's
own handling outside the surface. The contract test, the allowlist comment,
the runbook and the overlay specification describe the seams.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch; T3 applies no model or effort to Buddy's
  sessions (AcpT3Selection) and Buddy's thread keeps full access, which the
  server guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.
- In the bubble the surface wears the host page's appearance, also over a
  saved single-appearance theme. Outside it, the composer keeps the corner
  of Buddy's launcher free (index.html, --lazurio-buddy-clearance).

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. T3 no longer re-applies its theme from useTheme's effect
(pingdotgg#25007, pingdotgg#25461), so the host-appearance stand-in follows every application
of T3's saved theme through subscribeRenderedAppearance; the theme tests
apply T3's stored appearance as app start does. The ACP adapter keeps the
selection gate beside upstream's flavor hook (pingdotgg#24605). Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. The timeline mask keeps upstream's pending approvals footer, which reads the final rows. useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. The timeline mask keeps upstream's pending approvals footer, which reads the final rows. useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. The timeline mask keeps upstream's pending approvals footer, which reads the final rows. useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

On v0.1.5 upstream makes the client file system's writeTextFile optional
in the ACP adapter (pingdotgg#26876), away from the overlay's blocks. Upstream's
pre-commit hook runs knip (pingdotgg#26167), so LAZURIO_PAGE_CONTEXT_KIND,
buddyT3Instructions, LAZURIO_BUDDY_ENV and isBuddySurface, which nothing
imports, are module-private.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

On v0.1.5 upstream makes the client file system's writeTextFile optional
in the ACP adapter (pingdotgg#26876), away from the overlay's blocks. Upstream's
pre-commit hook runs knip (pingdotgg#26167), so LAZURIO_PAGE_CONTEXT_KIND,
buddyT3Instructions, LAZURIO_BUDDY_ENV and isBuddySurface, which nothing
imports, are module-private.

On v0.1.6 the ACP adapter checks a turn's model against the session's
models before the turn starts (pingdotgg#26623). Where AcpT3Selection names the
options, the host sets the agent's model and T3 applies none, so
validateModelSelection skips that check there, as it does for a flavor
that applies the selection itself: a model the session no longer offers
would otherwise refuse every turn of Buddy's. The V2 adapter test sends
such a model and the turn runs. The adapter test imports upstream's
acpPerTurnPromptUsage beside AcpT3Selection.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

On v0.1.6 useThreadLifecycle returns attentionNow, which is the run's Stop
once it went unanswered (Force stop, pingdotgg#27252) and the child's question
otherwise, and workNow, which is the Stop while it is under way and the
background work otherwise; backgroundWorkNow is gone. The inline mask
hides the child's question, the work and the goal on Buddy's surface,
while an unanswered Stop still shows there, so the person can force it;
the contract test pins every mask line, including that one, and
useThreadLifecycle's return. buddyBackgroundWork is whether workNow
exists. Upstream's provider traits menu content
(renderProviderTraitsMenuContent, pingdotgg#28057 and pingdotgg#28076) is not needed in
ComposerControlsBar, which on Buddy's surface returns BuddyComposerControls
before it. A side chat (pingdotgg#26901) renders ChatView embedded, so the thread
tabs and terminal drawers are off for it as they are on Buddy's surface.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

On v0.1.5 upstream makes the client file system's writeTextFile optional
in the ACP adapter (pingdotgg#26876), away from the overlay's blocks. Upstream's
pre-commit hook runs knip (pingdotgg#26167), so LAZURIO_PAGE_CONTEXT_KIND,
buddyT3Instructions, LAZURIO_BUDDY_ENV and isBuddySurface, which nothing
imports, are module-private.

On v0.1.6 the ACP adapter checks a turn's model against the session's
models before the turn starts (pingdotgg#26623). Where AcpT3Selection names the
options, the host sets the agent's model and T3 applies none, so
validateModelSelection skips that check there, as it does for a flavor
that applies the selection itself: a model the session no longer offers
would otherwise refuse every turn of Buddy's. The V2 adapter test sends
such a model and the turn runs. The adapter test imports upstream's
acpPerTurnPromptUsage beside AcpT3Selection.

On v0.1.7 the ACP adapter filters T3's options through the flavor's own
options and a runtime-mode ceiling (flatMap); the AcpT3Selection gate is
one more early return there, after the flavor's owned options and before
the ceiling. The runtime notes, which upstream now builds from the active
session setup, stay behind sendsT3Instructions. Effect 4.1.2 dropped
effect/Crypto, so the adapter imports Context beside upstream's
SecureRandom, and the Buddy tests provide NodeCrypto beside NodeServices.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

On v0.1.6 useThreadLifecycle returns attentionNow, which is the run's Stop
once it went unanswered (Force stop, pingdotgg#27252) and the child's question
otherwise, and workNow, which is the Stop while it is under way and the
background work otherwise; backgroundWorkNow is gone. The inline mask
hides the child's question, the work and the goal on Buddy's surface,
while an unanswered Stop still shows there, so the person can force it;
the contract test pins every mask line, including that one, and
useThreadLifecycle's return. buddyBackgroundWork is whether workNow
exists. Upstream's provider traits menu content
(renderProviderTraitsMenuContent, pingdotgg#28057 and pingdotgg#28076) is not needed in
ComposerControlsBar, which on Buddy's surface returns BuddyComposerControls
before it. A side chat (pingdotgg#26901) renders ChatView embedded, so the thread
tabs and terminal drawers are off for it as they are on Buddy's surface.

On v0.1.7: upstream wraps the timeline in `WorkspaceMutationIdContext`,
so `buddyBackgroundWork` sits inside it after `isWorking`. Upstream now
passes `environmentId` to the banner lane itself, so the overlay drops its
own copy of that prop and only uses it for Buddy's error banner. The work
line outside Buddy reads "Running · <label>" and "Waiting · <label>" on
v0.1.7, and the timeline test pins those.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

On v0.1.5 upstream makes the client file system's writeTextFile optional
in the ACP adapter (pingdotgg#26876), away from the overlay's blocks. Upstream's
pre-commit hook runs knip (pingdotgg#26167), so LAZURIO_PAGE_CONTEXT_KIND,
buddyT3Instructions, LAZURIO_BUDDY_ENV and isBuddySurface, which nothing
imports, are module-private.

On v0.1.6 the ACP adapter checks a turn's model against the session's
models before the turn starts (pingdotgg#26623). Where AcpT3Selection names the
options, the host sets the agent's model and T3 applies none, so
validateModelSelection skips that check there, as it does for a flavor
that applies the selection itself: a model the session no longer offers
would otherwise refuse every turn of Buddy's. The V2 adapter test sends
such a model and the turn runs. The adapter test imports upstream's
acpPerTurnPromptUsage beside AcpT3Selection.

On v0.1.7 the ACP adapter filters T3's options through the flavor's own
options and a runtime-mode ceiling (flatMap); the AcpT3Selection gate is
one more early return there, after the flavor's owned options and before
the ceiling. The runtime notes, which upstream now builds from the active
session setup, stay behind sendsT3Instructions. Effect 4.1.2 dropped
effect/Crypto, so the adapter imports Context beside upstream's
SecureRandom, and the Buddy tests provide NodeCrypto beside NodeServices.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

On v0.1.6 useThreadLifecycle returns attentionNow, which is the run's Stop
once it went unanswered (Force stop, pingdotgg#27252) and the child's question
otherwise, and workNow, which is the Stop while it is under way and the
background work otherwise; backgroundWorkNow is gone. The inline mask
hides the child's question, the work and the goal on Buddy's surface,
while an unanswered Stop still shows there, so the person can force it;
the contract test pins every mask line, including that one, and
useThreadLifecycle's return. buddyBackgroundWork is whether workNow
exists. Upstream's provider traits menu content
(renderProviderTraitsMenuContent, pingdotgg#28057 and pingdotgg#28076) is not needed in
ComposerControlsBar, which on Buddy's surface returns BuddyComposerControls
before it. A side chat (pingdotgg#26901) renders ChatView embedded, so the thread
tabs and terminal drawers are off for it as they are on Buddy's surface.

On v0.1.7: upstream wraps the timeline in `WorkspaceMutationIdContext`,
so `buddyBackgroundWork` sits inside it after `isWorking`. Upstream now
passes `environmentId` to the banner lane itself, so the overlay drops its
own copy of that prop and only uses it for Buddy's error banner. The work
line outside Buddy reads "Running · <label>" and "Waiting · <label>" on
v0.1.7, and the timeline test pins those.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

On v0.1.5 upstream makes the client file system's writeTextFile optional
in the ACP adapter (pingdotgg#26876), away from the overlay's blocks. Upstream's
pre-commit hook runs knip (pingdotgg#26167), so LAZURIO_PAGE_CONTEXT_KIND,
buddyT3Instructions, LAZURIO_BUDDY_ENV and isBuddySurface, which nothing
imports, are module-private.

On v0.1.6 the ACP adapter checks a turn's model against the session's
models before the turn starts (pingdotgg#26623). Where AcpT3Selection names the
options, the host sets the agent's model and T3 applies none, so
validateModelSelection skips that check there, as it does for a flavor
that applies the selection itself: a model the session no longer offers
would otherwise refuse every turn of Buddy's. The V2 adapter test sends
such a model and the turn runs. The adapter test imports upstream's
acpPerTurnPromptUsage beside AcpT3Selection.

On v0.1.7 the ACP adapter filters T3's options through the flavor's own
options and a runtime-mode ceiling (flatMap); the AcpT3Selection gate is
one more early return there, after the flavor's owned options and before
the ceiling. The runtime notes, which upstream now builds from the active
session setup, stay behind sendsT3Instructions. Effect 4.1.2 dropped
effect/Crypto, so the adapter imports Context beside upstream's
SecureRandom, and the Buddy tests provide NodeCrypto beside NodeServices.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

On v0.1.6 useThreadLifecycle returns attentionNow, which is the run's Stop
once it went unanswered (Force stop, pingdotgg#27252) and the child's question
otherwise, and workNow, which is the Stop while it is under way and the
background work otherwise; backgroundWorkNow is gone. The inline mask
hides the child's question, the work and the goal on Buddy's surface,
while an unanswered Stop still shows there, so the person can force it;
the contract test pins every mask line, including that one, and
useThreadLifecycle's return. buddyBackgroundWork is whether workNow
exists. Upstream's provider traits menu content
(renderProviderTraitsMenuContent, pingdotgg#28057 and pingdotgg#28076) is not needed in
ComposerControlsBar, which on Buddy's surface returns BuddyComposerControls
before it. A side chat (pingdotgg#26901) renders ChatView embedded, so the thread
tabs and terminal drawers are off for it as they are on Buddy's surface.

On v0.1.7: upstream wraps the timeline in `WorkspaceMutationIdContext`,
so `buddyBackgroundWork` sits inside it after `isWorking`. Upstream now
passes `environmentId` to the banner lane itself, so the overlay drops its
own copy of that prop and only uses it for Buddy's error banner. The work
line outside Buddy reads "Running · <label>" and "Waiting · <label>" on
v0.1.7, and the timeline test pins those.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

On v0.1.5 upstream makes the client file system's writeTextFile optional
in the ACP adapter (pingdotgg#26876), away from the overlay's blocks. Upstream's
pre-commit hook runs knip (pingdotgg#26167), so LAZURIO_PAGE_CONTEXT_KIND,
buddyT3Instructions, LAZURIO_BUDDY_ENV and isBuddySurface, which nothing
imports, are module-private.

On v0.1.6 the ACP adapter checks a turn's model against the session's
models before the turn starts (pingdotgg#26623). Where AcpT3Selection names the
options, the host sets the agent's model and T3 applies none, so
validateModelSelection skips that check there, as it does for a flavor
that applies the selection itself: a model the session no longer offers
would otherwise refuse every turn of Buddy's. The V2 adapter test sends
such a model and the turn runs. The adapter test imports upstream's
acpPerTurnPromptUsage beside AcpT3Selection.

On v0.1.7 the ACP adapter filters T3's options through the flavor's own
options and a runtime-mode ceiling (flatMap); the AcpT3Selection gate is
one more early return there, after the flavor's owned options and before
the ceiling. The runtime notes, which upstream now builds from the active
session setup, stay behind sendsT3Instructions. Effect 4.1.2 dropped
effect/Crypto, so the adapter imports Context beside upstream's
SecureRandom, and the Buddy tests provide NodeCrypto beside NodeServices.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

On v0.1.6 useThreadLifecycle returns attentionNow, which is the run's Stop
once it went unanswered (Force stop, pingdotgg#27252) and the child's question
otherwise, and workNow, which is the Stop while it is under way and the
background work otherwise; backgroundWorkNow is gone. The inline mask
hides the child's question, the work and the goal on Buddy's surface,
while an unanswered Stop still shows there, so the person can force it;
the contract test pins every mask line, including that one, and
useThreadLifecycle's return. buddyBackgroundWork is whether workNow
exists. Upstream's provider traits menu content
(renderProviderTraitsMenuContent, pingdotgg#28057 and pingdotgg#28076) is not needed in
ComposerControlsBar, which on Buddy's surface returns BuddyComposerControls
before it. A side chat (pingdotgg#26901) renders ChatView embedded, so the thread
tabs and terminal drawers are off for it as they are on Buddy's surface.

On v0.1.7: upstream wraps the timeline in `WorkspaceMutationIdContext`,
so `buddyBackgroundWork` sits inside it after `isWorking`. Upstream now
passes `environmentId` to the banner lane itself, so the overlay drops its
own copy of that prop and only uses it for Buddy's error banner. The work
line outside Buddy reads "Running · <label>" and "Waiting · <label>" on
v0.1.7, and the timeline test pins those.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

On v0.1.5 upstream makes the client file system's writeTextFile optional
in the ACP adapter (pingdotgg#26876), away from the overlay's blocks. Upstream's
pre-commit hook runs knip (pingdotgg#26167), so LAZURIO_PAGE_CONTEXT_KIND,
buddyT3Instructions, LAZURIO_BUDDY_ENV and isBuddySurface, which nothing
imports, are module-private.

On v0.1.6 the ACP adapter checks a turn's model against the session's
models before the turn starts (pingdotgg#26623). Where AcpT3Selection names the
options, the host sets the agent's model and T3 applies none, so
validateModelSelection skips that check there, as it does for a flavor
that applies the selection itself: a model the session no longer offers
would otherwise refuse every turn of Buddy's. The V2 adapter test sends
such a model and the turn runs. The adapter test imports upstream's
acpPerTurnPromptUsage beside AcpT3Selection.

On v0.1.7 the ACP adapter filters T3's options through the flavor's own
options and a runtime-mode ceiling (flatMap); the AcpT3Selection gate is
one more early return there, after the flavor's owned options and before
the ceiling. The runtime notes, which upstream now builds from the active
session setup, stay behind sendsT3Instructions. Effect 4.1.2 dropped
effect/Crypto, so the adapter imports Context beside upstream's
SecureRandom, and the Buddy tests provide NodeCrypto beside NodeServices.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

On v0.1.6 useThreadLifecycle returns attentionNow, which is the run's Stop
once it went unanswered (Force stop, pingdotgg#27252) and the child's question
otherwise, and workNow, which is the Stop while it is under way and the
background work otherwise; backgroundWorkNow is gone. The inline mask
hides the child's question, the work and the goal on Buddy's surface,
while an unanswered Stop still shows there, so the person can force it;
the contract test pins every mask line, including that one, and
useThreadLifecycle's return. buddyBackgroundWork is whether workNow
exists. Upstream's provider traits menu content
(renderProviderTraitsMenuContent, pingdotgg#28057 and pingdotgg#28076) is not needed in
ComposerControlsBar, which on Buddy's surface returns BuddyComposerControls
before it. A side chat (pingdotgg#26901) renders ChatView embedded, so the thread
tabs and terminal drawers are off for it as they are on Buddy's surface.

On v0.1.7: upstream wraps the timeline in `WorkspaceMutationIdContext`,
so `buddyBackgroundWork` sits inside it after `isWorking`. Upstream now
passes `environmentId` to the banner lane itself, so the overlay drops its
own copy of that prop and only uses it for Buddy's error banner. The work
line outside Buddy reads "Running · <label>" and "Waiting · <label>" on
v0.1.7, and the timeline test pins those.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

On v0.1.5 upstream makes the client file system's writeTextFile optional
in the ACP adapter (pingdotgg#26876), away from the overlay's blocks. Upstream's
pre-commit hook runs knip (pingdotgg#26167), so LAZURIO_PAGE_CONTEXT_KIND,
buddyT3Instructions, LAZURIO_BUDDY_ENV and isBuddySurface, which nothing
imports, are module-private.

On v0.1.6 the ACP adapter checks a turn's model against the session's
models before the turn starts (pingdotgg#26623). Where AcpT3Selection names the
options, the host sets the agent's model and T3 applies none, so
validateModelSelection skips that check there, as it does for a flavor
that applies the selection itself: a model the session no longer offers
would otherwise refuse every turn of Buddy's. The V2 adapter test sends
such a model and the turn runs. The adapter test imports upstream's
acpPerTurnPromptUsage beside AcpT3Selection.

On v0.1.7 the ACP adapter filters T3's options through the flavor's own
options and a runtime-mode ceiling (flatMap); the AcpT3Selection gate is
one more early return there, after the flavor's owned options and before
the ceiling. The runtime notes, which upstream now builds from the active
session setup, stay behind sendsT3Instructions. Effect 4.1.2 dropped
effect/Crypto, so the adapter imports Context beside upstream's
SecureRandom, and the Buddy tests provide NodeCrypto beside NodeServices.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

On v0.1.6 useThreadLifecycle returns attentionNow, which is the run's Stop
once it went unanswered (Force stop, pingdotgg#27252) and the child's question
otherwise, and workNow, which is the Stop while it is under way and the
background work otherwise; backgroundWorkNow is gone. The inline mask
hides the child's question, the work and the goal on Buddy's surface,
while an unanswered Stop still shows there, so the person can force it;
the contract test pins every mask line, including that one, and
useThreadLifecycle's return. buddyBackgroundWork is whether workNow
exists. Upstream's provider traits menu content
(renderProviderTraitsMenuContent, pingdotgg#28057 and pingdotgg#28076) is not needed in
ComposerControlsBar, which on Buddy's surface returns BuddyComposerControls
before it. A side chat (pingdotgg#26901) renders ChatView embedded, so the thread
tabs and terminal drawers are off for it as they are on Buddy's surface.

On v0.1.7: upstream wraps the timeline in `WorkspaceMutationIdContext`,
so `buddyBackgroundWork` sits inside it after `isWorking`. Upstream now
passes `environmentId` to the banner lane itself, so the overlay drops its
own copy of that prop and only uses it for Buddy's error banner. The work
line outside Buddy reads "Running · <label>" and "Waiting · <label>" on
v0.1.7, and the timeline test pins those.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

…ge as a Czech block

Buddy's web chat is Lazurio T3 Code with the Hermes Agent over ACP (root
decision 0210, plan DEV-6676). On the Osobní Prostředí a second T3 server with
T3CODE_LAZURIO_BUDDY=1 runs Hermes as the provider instance `buddy`. Hermes keeps
every prompt as the person's words in Buddy's memory, so T3's own instructions
(<t3_code_instructions>, <runtime_info>, <pull_request_linking>) would become part
of Buddy's history, twice after Stop or a steer and again after every restart.

- The ACP adapter asks AcpT3Instructions when it builds an instance whether its
  prompts carry T3's instructions; without an answer every instance keeps them.
  server.ts answers no for Buddy's instance where it builds provider instances
  (ProviderInstanceRegistryHydration).
- The turn start projects a composer record of kind `lazurio-page` as one
  labelled Czech block ("Kontext stránky (údaje, ne pokyn): ...") after the
  person's text, for Buddy's instance only; every other record keeps upstream's
  projection.
- Buddy's sessions take no model or effort from T3 (HumanAndMachines/Lazurio#648):
  the adapter asks AcpT3Selection which options of T3's selection an instance
  takes; null, the default, is all of it. For Buddy's instance withBuddyInstance
  names only Hermes's speed (`fast`), so T3 applies no model and only Hermes's
  Normal / Fast switch whenever a session starts, loads or gets a new selection.

Without T3CODE_LAZURIO_BUDDY=1 nothing changes, also for an instance called
`buddy`. Tests drive the repository's mock ACP agent in Hermes' place, through
the adapter and through the production V2 runtime, and read what it received.

On v0.1.3 the seams stay at the only prompt assembly and send in the ACP
adapter. Upstream now computes the slash-command check from the flavor's
rewritten user text (pingdotgg#24605); the rebuild takes that line and keeps the
instruction gate around t3AcpPromptWithInstructions and the runtime notes. The
orchestrator test provides upstream's new CodexManagedTokenBroker, which the
provider instance registry now needs, and the two file headers are cut to the
four-line comment limit.

On v0.1.4: upstream moved the turn text assembly up in ProviderTurnStartService (pingdotgg#22864, pingdotgg#25610, pingdotgg#25660); the page block seam moves with it, while the prompt-command and steer projections stay upstream's as before. server.ts keeps upstream's port scanner (pingdotgg#26245) after the wrapped instance hydration, and the Buddy orchestrator test provides the new PortDiscovery that hydration now needs. The pingdotgg#648 selection gate, which row 28's commit carried on v0.1.3, comes back to this row and sits beside upstream's flavor hook (pingdotgg#24605).

On v0.1.5 upstream makes the client file system's writeTextFile optional
in the ACP adapter (pingdotgg#26876), away from the overlay's blocks. Upstream's
pre-commit hook runs knip (pingdotgg#26167), so LAZURIO_PAGE_CONTEXT_KIND,
buddyT3Instructions, LAZURIO_BUDDY_ENV and isBuddySurface, which nothing
imports, are module-private.

On v0.1.6 the ACP adapter checks a turn's model against the session's
models before the turn starts (pingdotgg#26623). Where AcpT3Selection names the
options, the host sets the agent's model and T3 applies none, so
validateModelSelection skips that check there, as it does for a flavor
that applies the selection itself: a model the session no longer offers
would otherwise refuse every turn of Buddy's. The V2 adapter test sends
such a model and the turn runs. The adapter test imports upstream's
acpPerTurnPromptUsage beside AcpT3Selection.

On v0.1.7 the ACP adapter filters T3's options through the flavor's own
options and a runtime-mode ceiling (flatMap); the AcpT3Selection gate is
one more early return there, after the flavor's owned options and before
the ceiling. The runtime notes, which upstream now builds from the active
session setup, stay behind sendsT3Instructions. Effect 4.1.2 dropped
effect/Crypto, so the adapter imports Context beside upstream's
SecureRandom, and the Buddy tests provide NodeCrypto beside NodeServices.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

Root decision 0210, addendum of 2026-10-22, point 1, and its plain-chat
addendum (HumanAndMachines/Lazurio#648; plan DEV-6676, row 28): the person
sees and hears only what Buddy writes in human words. In Buddy's surface
(lazurioBuddy) only:

- The timeline keeps the messages and what the person acts on; T3's record
  of the work stays out. While a turn runs, or work still runs after it, one
  quiet static line says "Buddy na tom pracuje…" / "Buddy is on it…". A
  failed turn shows one human line, and the thread's error banner says
  "Něco se nepovedlo. Zkuste to prosím znovu." instead of T3's text.
- None of the turn's work shows at the end of the timeline, and Buddy's
  queue holds and counts only the person's own messages, never an agent's
  such as Delegace's wake.
- The composer is a message box ("Napište Buddymu…") whose only choice is
  Hermes's Normal / Fast switch, the one option row 23's AcpT3Selection
  lets through, and Buddy's thread keeps full access, which the server
  guard also holds.
- The surface never shows T3's terminal or right panel, their keys stay the
  browser's, and a link in the conversation opens in a new browser tab.

The terminal and right-panel states are read inside the store selectors, so
the React Compiler keeps ChatView's panel presence values memoized
(chatViewPanelPresence.test.ts guards it, #134).

On v0.1.3 upstream moved the work banners and the queue to the end of the
timeline and removed the composer's task list (pingdotgg#25401). The work items
(childInputNow, goalNow, backgroundWorkNow) are masked on Buddy's surface
with inline conditionals in ChatView's body, where hasThreadNow, ThreadNow
and the scroll button's summary read them, so no plain function wraps a
hook result in render. buddyBackgroundWork is whether backgroundWorkNow
exists. useBuddyQueuedRunCount drops an agent's queued message from the
footer's count, which upstream's getUserQueuedThreadRuns keeps, and
buddyWorkBanners and the task-list seam are gone. useBuddyChatShortcuts
takes upstream's `!backgroundThread` condition (pingdotgg#24847), ChatTerminalDrawers
lost focusRequestId (pingdotgg#25009), the placeholder falls back to
DEFAULT_COMPOSER_PLACEHOLDER, and ReopenClosedViewShortcut stays off on the
slimmer root. Effects carry
justified react-effect-budget suppressions and comments are cut to the
four-line limit.

The error banner asks about the thread's own Environment (ChatBannerLane
passes it), so a thread of another Environment keeps T3's own text.

On v0.1.4: upstream dropped the resting composer's control strip, so Buddy's composer hook only gives the placeholder and hasControls is gone; Buddy's controls still replace T3's in ComposerControlsBar ahead of upstream's controls ownership. Upstream shows an approval on its own row (pingdotgg#26255); Buddy's mask leaves no work rows, so the approval falls to upstream's footer for unmatched approvals, and a browser test shows a pending approval there with Approve and Decline and no work row or quiet line. The link_request card stays off Buddy's surface, where link requests are refused (row 25). useChatShortcuts no longer exports its input type, so the overlay takes it from the hook. The tests follow upstream's props and labels: no activeTurnInProgress or onRollbackCheckpoint, the queue's "1 queued message", background work rows with turn items and "Running …" / "Waiting on …" titles, and a single subagent as a [data-v2-item-type=subagent] row. Effect suppressions use the renamed no-unreasoned-state-sync rule. Row 23's AcpT3Selection, row 25's host appearance and row 7's launcher clearance, which this commit carried on v0.1.3, are back in their rows.

On v0.1.6 useThreadLifecycle returns attentionNow, which is the run's Stop
once it went unanswered (Force stop, pingdotgg#27252) and the child's question
otherwise, and workNow, which is the Stop while it is under way and the
background work otherwise; backgroundWorkNow is gone. The inline mask
hides the child's question, the work and the goal on Buddy's surface,
while an unanswered Stop still shows there, so the person can force it;
the contract test pins every mask line, including that one, and
useThreadLifecycle's return. buddyBackgroundWork is whether workNow
exists. Upstream's provider traits menu content
(renderProviderTraitsMenuContent, pingdotgg#28057 and pingdotgg#28076) is not needed in
ComposerControlsBar, which on Buddy's surface returns BuddyComposerControls
before it. A side chat (pingdotgg#26901) renders ChatView embedded, so the thread
tabs and terminal drawers are off for it as they are on Buddy's surface.

On v0.1.7: upstream wraps the timeline in `WorkspaceMutationIdContext`,
so `buddyBackgroundWork` sits inside it after `isWorking`. Upstream now
passes `environmentId` to the banner lane itself, so the overlay drops its
own copy of that prop and only uses it for Buddy's error banner. The work
line outside Buddy reads "Running · <label>" and "Waiting · <label>" on
v0.1.7, and the timeline test pins those.

Co-Authored-By: Claude Opus 5.5 <[email protected]>