ZacharyZhang-NY/AgentCompany
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity
1,404 Commits 46 Branches 7 Tags
6bedba850c3f5013a03812937b6f1907fcdcbe86
Commit Graph
72 Commits
Author SHA1 Message Date
ZacharyZhang-NYandClaude Opus 5.5 6bedba850c Q187: a search hit opens the object itself and marks it 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 08:10:22 -04:00
ZacharyZhang-NYandClaude Opus 5.5 6f6ed48549 Q186: data that can no longer be updated says how old it is and why 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 07:55:58 -04:00
ZacharyZhang-NYandClaude Opus 5.5 f5526b075c Q185: switching company carries no focus, search or form from the previous company 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 07:51:39 -04:00
ZacharyZhang-NYandClaude Opus 5.5 72cf57ce3a Q184: the page, its sections, filters and selections survive page switches and restarts 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 07:46:21 -04:00
ZacharyZhang-NYandClaude Opus 5.5 2790d88186 Q183: unsaved input is kept across pages, and leaving or closing asks before losing it 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 07:30:13 -04:00
ZacharyZhang-NYandClaude Opus 5.5 3f8832702e Q182: dialogs stay busy while their request runs and ignore repeat submits 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 06:03:09 -04:00
ZacharyZhang-NYandClaude Opus 5.5 3039835644 Q181: a render error stays inside its page and says what failed 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 05:56:11 -04:00
ZacharyZhang-NYandClaude Opus 5.5 fd91832bc4 Q180: a failure no screen handles is shown instead of lost 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 05:51:33 -04:00
ZacharyZhang-NYandClaude Opus 5.5 7a4d986344 Q179: a failed first load says why and keeps retrying visibly 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 05:46:55 -04:00
ZacharyZhang-NYandClaude Opus 5.5 1cc67c244e Q178: the Chinese UI labels stored values and sign-in prompts, and shortcuts follow the platform 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 05:42:45 -04:00
ZacharyZhang-NYandClaude Opus 5.5 f79e3d4d7c Q177: conversation types and visibility say what they change 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 05:32:14 -04:00
ZacharyZhang-NYandClaude Opus 5.5 fd79f059ca Q176: onboarding progress survives a restart, and an unfinished setup reopens 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 05:25:01 -04:00
ZacharyZhang-NYandClaude Opus 5.5 43dcb1e7d3 Q175: onboarding shows what each mode allows and the amounts a company starts with 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 05:02:32 -04:00
ZacharyZhang-NYandClaude Opus 5.5 dc3127c26f Q174: choosing a language no longer restarts the app; the restart waits for the user 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 04:53:25 -04:00
ZacharyZhang-NYandClaude Opus 5.5 3f14e3f706 Q173: agents work in the company's or task's language, not the display language 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 04:40:52 -04:00
ZacharyZhang-NYandClaude Opus 5.5 538d834647 Q172: disconnecting a provider shows what it stops, then the outcome 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 04:25:31 -04:00
ZacharyZhang-NYandClaude Opus 5.5 059970e7e1 Q171: provider policy fields say what they govern and show pending and saved state 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 04:20:13 -04:00
ZacharyZhang-NYandClaude Opus 5.5 7c291cf7a7 Q170: agent model suggestions and choices follow the picked provider 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 04:08:17 -04:00
ZacharyZhang-NYandClaude Opus 5.5 a8fbc08df6 Q169: saved cloud and custom endpoints refill their form and keep the saved key 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 04:02:08 -04:00
ZacharyZhang-NYandClaude Opus 5.5 5cd413ffcf Q168: a connected provider's default model changes without its credential 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 03:55:55 -04:00
ZacharyZhang-NYandClaude Opus 5.5 26c3365896 Q167: the model in effect and what a default change reaches are shown 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 03:44:23 -04:00
ZacharyZhang-NYandClaude Opus 5.5 e8722cd815 Q166: workspaces can be edited, made primary and removed 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 03:32:03 -04:00
ZacharyZhang-NYandClaude Opus 5.5 20c37362f3 Q165: the company's profile and how it runs can be changed after onboarding 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 03:20:39 -04:00
ZacharyZhang-NYandClaude Opus 5.5 93c5eb2d71 Q164: every settings section says whether it affects this company, every company, or this computer 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 03:13:44 -04:00
ZacharyZhang-NYandClaude Opus 5.5 9826b163a9 Q163: the goal progress view is called Progress, not Timeline 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 03:08:57 -04:00
ZacharyZhang-NYandClaude Opus 5.5 c9117fe46d Q160: a goal's pace is measured against its target date, and claimed only when it has one 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 02:44:20 -04:00
ZacharyZhang-NYandClaude Opus 5.5 9d166e3fc9 Q158: run history and run output come from the database, not the snapshot window 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 02:31:43 -04:00
ZacharyZhang-NYandClaude Opus 5.5 a075f931d5 Q157: a run can be cancelled before it starts, and a failed or stopped one retried or resumed 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 02:11:11 -04:00
ZacharyZhang-NYandClaude Opus 5.5 71ac5085cd Q156: approval history pages back and opens each decision in full 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 02:01:21 -04:00
ZacharyZhang-NYandClaude Opus 5.5 41359e268a Q155: batch approval decides one request at a time and reports each result 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 01:43:41 -04:00
ZacharyZhang-NYandClaude Opus 5.5 ec183ec60e Q154: decision notes belong to one request and reset on close or switch 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 01:34:59 -04:00
ZacharyZhang-NYandClaude Opus 5.5 af831abd53 Q153: the approval button that reviews a request is called Review, and leads to where the request can change 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 01:32:09 -04:00
ZacharyZhang-NYandClaude Opus 5.5 e8634afb82 Q152: chat replies and goal checkpoints stay out of work lists, load and progress 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 01:26:15 -04:00
ZacharyZhang-NYandClaude Opus 5.5 18f1e1fcc3 Q151: deleting a task first shows what goes with it, then waits for the result 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 01:21:31 -04:00
ZacharyZhang-NYandClaude Opus 5.5 809c67a54a Q150: work can be sent back, reopened, moved to backlog, or blocked with a reason 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 01:12:17 -04:00
ZacharyZhang-NYandClaude Opus 5.5 7ab46bb2de Q149: editing a task can change everything creating it can 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 01:04:26 -04:00
ZacharyZhang-NYandClaude Opus 5.5 766d4ab8cd Q148: a task's goal, project, workspace, runs, approvals and subtasks open with one click, and lead back 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 00:58:34 -04:00
ZacharyZhang-NYandClaude Opus 5.5 983d37937d Q147: the conversation header lists its real members, how each agent replies, and who can read 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 00:45:05 -04:00
ZacharyZhang-NYandClaude Opus 5.5 02309546dc Q146: the message editor stays open until the edit is saved, and says why it was not 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 00:35:28 -04:00
ZacharyZhang-NYandClaude Opus 5.5 2a89d1e883 Q144: each message says where the reply it asked for stands 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-09 00:08:32 -04:00
ZacharyZhang-NYandClaude Opus 5.5 075dea725a Q143: earlier messages come from the database, page by page, back to the first one 
Review limit (5) reached; the last finding (exhaustion latched) is fixed
by taking it from each latest hasMore.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 23:52:22 -04:00
ZacharyZhang-NYandClaude Opus 5.5 b18eb9ad14 Q142: a conversation is read only up to the message the reader actually saw 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 23:18:06 -04:00
ZacharyZhang-NYandClaude Opus 5.5 87c297dd45 Q141: reply to a specific message in its thread, and see what each reply answers 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 23:01:57 -04:00
ZacharyZhang-NYandClaude Opus 5.5 46f7561f77 Q139: each conversation keeps its own draft text and attachment 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 22:26:38 -04:00
ZacharyZhang-NYandClaude Opus 5.5 c5b011ce80 Q138: a refused send keeps the draft and says why 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 22:15:18 -04:00
ZacharyZhang-NYandClaude Opus 5.5 5c8233d258 Q31: a Library page to read and manage documents and knowledge 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 06:26:15 -04:00
ZacharyZhang-NY c7eafb2836 Founder-CEO chat round trip proven end to end; agents see the founder 
loadChatContext labels human senders "[Name (founder)]" so a woken agent
knows it answers its boss, not a teammate. New integration test drives
the whole loop — founder DM wakes the CEO, the prompt names the founder,
the reply lands in the same pinned conversation and thread, the wake
task closes — and a Playwright spec pins the UI contract: badged CEO row
first, selected by default, message queues the wake run, channel recency
never displaces the pin. AGENTS.md documents the feature contracts.
 2026-07-14 00:23:49 -04:00
ZacharyZhang-NY 177e25aab5 The Kimi family is visible end-to-end: e2e asserts onboarding and Settings, AGENTS.md learns the provider recipe 
- desktop.spec.ts verifies Kimi / Kimi CN / Kimi Code cards in the onboarding provider step, the device-flow sign-in button on Kimi Code, and all three under Settings -> Providers
- AGENTS.md documents the catalog-driven provider architecture and the Kimi endpoints so the doc stays truthful
- Full gate green: typecheck, lint, unit (269), contract, integration, replay-eval, Playwright e2e (3)
 2026-07-10 17:21:37 -04:00
ZacharyZhang-NY eaaf36f859 Language-aware house style and a resizable chat split 
House style now follows the app language: Chinese UI forces the new
bundled humanizer-zh skill into every run, English forces humanizer -
one variant per run, picked by preference with cross-language fallback
so an older catalogue never silently loses house style. Both variants
are protected from grant/revoke, list_skills labels each with its
language, the bundle guard requires both, and startup sync imports the
new skill into existing orgs on next launch. Covered by a unit test
that flips app_state.language and asserts which humanizer compiles.

The chat split is now adjustable: drag the conversation list's right
edge (200-480px, persisted in localStorage) and the composer textarea
grew a native vertical resize grip capped at 40vh.
 2026-07-09 01:14:05 -04:00
ZacharyZhang-NY cb71afa6b7 Avatar photo uploads and a global handbrake for the agent engine 
Two operator asks, one review gate:

Avatar portraits (migration 052): the avatar editor gains "Upload
photo" - the renderer downscales the chosen picture to a ~96px cover
crop and stores it as a small data URL (PNG keeps transparency, the
rest compresses to JPEG), so the snapshot stays light and the CSP needs
nothing new. The portrait wins over emoji and initials everywhere the
shared Avatar renders (chat, org chart, office card, sidebar), and
"Remove photo" falls back cleanly. The main process validates scheme
and size (base64 image data URL, <=300k chars) so a rogue caller cannot
re-bloat the snapshot. e2e uploads a real PNG through the profile
dialog and sees the portrait land in the sidebar.

Global pause (migration 053): when agents start talking in circles,
one topbar toggle - visible on every page - pulls the handbrake.
app_state.autorun_paused survives restarts; the queue worker checks it
each tick and neither enqueues nor claims while set (the run already in
flight finishes). Queued work simply waits and the paused state renders
as an amber "resume" pill. A unit test drives the real worker: paused
leaves a queued run untouched through many ticks, resuming claims it
within moments; e2e flips the toggle in the live shell.
 2026-07-09 00:09:02 -04:00