ZacharyZhang-NY/AgentCompany
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity
1,275 Commits 46 Branches 7 Tags
a3aee1940a85869c93dbbbc1ed0ea8048e2bb3c6
Commit Graph
284 Commits
Author SHA1 Message Date
ZacharyZhang-NYandClaude Opus 5.5 a3aee1940a Q58: command timeouts and stops kill the whole process tree 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 10:18:28 -04:00
ZacharyZhang-NYandClaude Opus 5.5 3bc0d811cb Q57: quitting stops running sessions and waits for them to record their end 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 10:09:16 -04:00
ZacharyZhang-NYandClaude Opus 5.5 e809cfefea Q54: later sessions see what earlier ones already did and where they failed 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 09:35:27 -04:00
ZacharyZhang-NYandClaude Opus 5.5 ec2698575d Q53: stalled goal reviews leave a visible state and a resume path 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 09:25:46 -04:00
ZacharyZhang-NYandClaude Opus 5.5 69e991ff93 Q52: goal closures stop linked work, and running sessions hear goal changes 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 09:16:48 -04:00
ZacharyZhang-NYandClaude Opus 5.5 d9cb86a999 Q51: agents may only move work they own, manage or review; done needs evidence and sign-off 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 09:04:34 -04:00
ZacharyZhang-NYandClaude Opus 5.5 ddc8b485e9 Q50: work moved to review gets a reviewer; review closes with the verdict 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 08:50:02 -04:00
ZacharyZhang-NYandClaude Opus 5.5 7659adbbdd Q49: a task that spends its run budget shows as stalled; edits start a fresh budget 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 08:38:02 -04:00
ZacharyZhang-NYandClaude Opus 5.5 090c37abb8 Q48: each agent's heartbeat interval paces its queued work 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 08:25:06 -04:00
ZacharyZhang-NYandClaude Opus 5.5 d5d68ad358 Q47: task parents cannot form a cycle 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 08:19:41 -04:00
ZacharyZhang-NYandClaude Opus 5.5 3bc341d757 Q45: the queue claims higher-priority work first 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 08:02:43 -04:00
ZacharyZhang-NYandClaude Opus 5.5 5698e61e5a Q43: manual runs refuse done tasks and tasks with a session in flight 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 07:47:17 -04:00
ZacharyZhang-NYandClaude Opus 5.5 6a4843a983 Q41: one first-hire rule, and leaders get guidance that fits their rank 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 07:37:02 -04:00
ZacharyZhang-NYandClaude Opus 5.5 7be072f8c5 Q40: tasks choose a writing mode; house style applies to conversational work only 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 07:28:47 -04:00
ZacharyZhang-NYandClaude Opus 5.5 645ce686bb Q39: runs load only model-compatible skills and state each skill's contract 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 07:22:08 -04:00
ZacharyZhang-NYandClaude Opus 5.5 f7530ba65b Q38: the prompt names skill tools the run cannot call, not a fake allowlist 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 07:14:41 -04:00
ZacharyZhang-NYandClaude Opus 5.5 e726c36bac Q37: skill tool text tells the CEO the truth about grants 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 07:11:43 -04:00
ZacharyZhang-NYandClaude Opus 5.5 25d054d954 Q36: retired skills stop loading into runs, cached snapshots included 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 07:06:50 -04:00
ZacharyZhang-NYandClaude Opus 5.5 bbc60cd56a Q35: retired built-in skills come back when the bundle ships them again 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 07:00:57 -04:00
ZacharyZhang-NYandClaude Opus 5.5 da072f9a9b Q34: built-in skill updates reach existing orgs and their bindings 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 06:57:52 -04:00
ZacharyZhang-NYandClaude Opus 5.5 66de4ef015 Q33: document edits and content deletions leave attributed audit records 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 06:45:51 -04:00
ZacharyZhang-NYandClaude Opus 5.5 cb464c3ee4 Q32: documents and knowledge appear in global search 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 06:33:00 -04:00
ZacharyZhang-NYandClaude Opus 5.5 4c475e5ceb Q30: documents keep every version 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 06:10:25 -04:00
ZacharyZhang-NYandClaude Opus 5.5 794fa372c9 Q29: documents record the task that produced them 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 06:02:02 -04:00
ZacharyZhang-NYandClaude Opus 5.5 84fed8e2f2 Q28: agents list, read, and update company documents 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 05:56:55 -04:00
ZacharyZhang-NYandClaude Opus 5.5 ec9d74d128 Q27: knowledge corrections keep a revision history 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 05:51:32 -04:00
ZacharyZhang-NYandClaude Opus 5.5 18128b5ad4 Q26: knowledge has scope, expiry, and supersession 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 05:47:03 -04:00
ZacharyZhang-NYandClaude Opus 5.5 95e607bea7 Q24: knowledge enters the run: search and record tools, relevant entries in prompts 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 05:20:03 -04:00
ZacharyZhang-NYandClaude Opus 5.5 0fea8a9159 Q23: command output is bounded while it streams, not after 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 05:11:21 -04:00
ZacharyZhang-NYandClaude Opus 5.5 8e8b66fed4 Q22: cap every tool result and bound connector responses 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 05:04:59 -04:00
ZacharyZhang-NYandClaude Opus 5.5 4d6c74a21e Q21: fetch_url pages long pages and continues where it stopped 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 05:01:28 -04:00
ZacharyZhang-NYandClaude Opus 5.5 1a0da25202 Q20: read_file and read_attachment page by lines, columns, and search 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 04:58:40 -04:00
ZacharyZhang-NYandClaude Opus 5.5 b32e784469 Q19: pack the skills most relevant to the task first 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 04:48:44 -04:00
ZacharyZhang-NYandClaude Opus 5.5 d79fd87077 Q18: every skill, the first included, must fit the skill budget 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 04:42:06 -04:00
ZacharyZhang-NYandClaude Opus 5.5 f4d16eb46a Q17: budget every model request against the provider's context window 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 04:40:02 -04:00
ZacharyZhang-NYandClaude Opus 5.5 f42ab62dbd Q16: compact older tool results inside a run 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 04:26:09 -04:00
ZacharyZhang-NYandClaude Opus 5.5 469f2f2c35 Q15: show which messages each agent actually read 
Runs record a context manifest once a model turn succeeds; the chat
marks each human message with the agents that read its current version.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 04:21:57 -04:00
ZacharyZhang-NYandClaude Opus 5.5 592ce69219 Q14: every human sender shows their own kind and role, board included 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 04:08:21 -04:00
ZacharyZhang-NYandClaude Opus 5.5 31bf0a1497 Q13: messages carry their attachments; agents read them by file_id 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 04:05:11 -04:00
ZacharyZhang-NYandClaude Opus 5.5 f15e47eda1 Q12: read_messages reads threads, pages back, and searches 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 03:59:00 -04:00
ZacharyZhang-NYandClaude Opus 5.5 22632a4695 Q11: deleted messages and withdrawn commands never reach the model 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 03:47:57 -04:00
ZacharyZhang-NYandClaude Opus 5.5 2a7b17a47a Q8: one writing run per workspace directory 
Write-granted runs whose directories overlap (same folder, symlink or
junction, or nested) wait for each other, at claim time and for manual
runs.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 03:25:39 -04:00
ZacharyZhang-NYandClaude Opus 5.5 72eb645067 Q7: an agent runs one session at a time 
Claims skip agents that already have a running run, manual runs refuse a
busy agent, a run whose task was reassigned fails before executing, and
tasks with a run in progress cannot be deleted.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 03:11:39 -04:00
ZacharyZhang-NYandClaude Opus 5.5 0fb4ca9ae6 Q6: feed messages that arrive mid-run into the next model turn 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 02:58:54 -04:00
ZacharyZhang-NYandClaude Opus 5.5 fe76f0bc52 Q4: delegated tasks become subtasks of the work that created them 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 02:40:46 -04:00
ZacharyZhang-NYandClaude Opus 5.5 6570492daa Q3: record a structured handoff on every delegated task 
create_task now pins upstream files by content hash and carries the
source task, source thread, verified facts, open questions and
acceptance criteria into the assignee's prompt.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 02:35:12 -04:00
ZacharyZhang-NYandClaude Opus 5.5 9f2adce7b3 Q2: read_messages lists only mentions the agent has not answered 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 02:25:31 -04:00
ZacharyZhang-NYandClaude Opus 5.5 56b0594f91 Move Composio, logo.dev and Antigravity keys into Settings 
The three third-party keys were hardcoded or read from the environment.
Operators now enter them in Settings > Integrations; they are stored
encrypted in the app-wide integration_keys table (migration 058).
An agent holding connector grants fails loudly when no Composio key is
saved. The goal-review test no longer depends on absolute dates.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 01:34:14 -04:00
ZacharyZhang-NY aa4cfc056d Human-triggered wakes claim before queued autonomous work 
Wake runs stamp sourceSenderType into their secret scope, and the claim
query orders interactive-first: a wake born from an employee or board
message means a person is waiting at the keyboard, so it outranks any
autonomous backlog; within each lane FIFO holds. Non-chat runs carry no
stamp and stay in the autonomous lane. With wake expiry this closes the
live incident: the founder's CEO DM now claims on the next tick instead
of 13th in line. Red-green tested.
 2026-07-14 20:46:51 -04:00
ZacharyZhang-NY 39aa292d09 Stale chat wakes expire instead of resuming days later 
Live incident: the founder DMed the CEO and got silence — the reply run
sat 13th in a FIFO queue behind chat wakes from four days ago, which the
reopened app was faithfully executing (necro-replies that woke yet more
agents). A wake run is a conversation reply; past one hour the moment is
gone. expireStaleChatWakes (chat-agent-wake-service) fails queued
chat_mention runs older than the TTL and closes their vehicle tasks;
the worker tick runs it before claiming, with one log line. Real work
(heartbeat/kickoff triggers) never expires. Red-green tested.
 2026-07-14 20:44:37 -04:00