ZacharyZhang-NY/AgentCompany
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity
1,381 Commits 46 Branches 7 Tags
93c5eb2d7185fe2db87da78a2442df7bfecdaf77
Commit Graph
118 Commits
Author SHA1 Message Date
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 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 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 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 fe45cd4d46 Q131: remove review agents and eval suites whose pass only counted configuration rows 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 21:33:03 -04:00
ZacharyZhang-NYandClaude Opus 5.5 074a1fc8e3 Q130: every open task says why it is not moving, when it resumes, and who must act 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 21:27:29 -04:00
ZacharyZhang-NYandClaude Opus 5.5 271a83a7bc Q129: a run with failed actions it never redid does not count as completed 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 21:15:47 -04:00
ZacharyZhang-NYandClaude Opus 5.5 6afd7bef2a Q128: every model call of a run is recorded with its purpose and listed in the run 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 20:55:18 -04:00
ZacharyZhang-NYandClaude Opus 5.5 69b83d6b77 Q122: reading a recorded file checks its bytes against the recorded hash 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 19:44:51 -04:00
ZacharyZhang-NYandClaude Opus 5.5 abfcbf4824 Q114: goal audits use the org's own auditor model and see pointers, not the executor's account 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 18:35:39 -04:00
ZacharyZhang-NYandClaude Opus 5.5 7eef3d459f Q88: a sign-in is saved only if a run can use and renew it 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 15:02:12 -04:00
ZacharyZhang-NYandClaude Opus 5.5 4668396f25 Q87: provider errors keep status and provider code; text never decides recovery 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 14:52:31 -04:00
ZacharyZhang-NYandClaude Opus 5.5 665bf3cae1 Q83: a model passes an agent check before it does agent work 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 14:19:48 -04:00
ZacharyZhang-NYandClaude Opus 5.5 d557e42676 Q77: a session keeps the model and account it started with 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 13:03:11 -04:00
ZacharyZhang-NYandClaude Opus 5.5 8fcdd61bc5 Q76: runs call the agent's own model, or fail plainly where the provider cannot 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 12:53:25 -04:00
ZacharyZhang-NYandClaude Opus 5.5 4325dfa874 Q68: sessions are bounded in time, tool calls per turn and goal audits 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 11:50:26 -04:00
ZacharyZhang-NYandClaude Opus 5.5 168572dd76 Q63: model calls are priced and agent and department budgets limit real spend 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 11:08:38 -04:00
ZacharyZhang-NYandClaude Opus 5.5 88463e4396 Q60: step limits end sessions as checkpoints; only sessions without progress spend the budget 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 10:33:57 -04:00
ZacharyZhang-NYandClaude Opus 5.5 d72333a04c Q56: disconnecting a provider stops the sessions using it 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 10:02:46 -04:00
ZacharyZhang-NYandClaude Opus 5.5 9e1f8da11c Q55: the operator can stop in-flight runs; pause stops them too 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 09:59:03 -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 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 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 b164677ea7 Q46: parents wait for their subtasks and cannot close while any are open 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 08:13:35 -04:00
ZacharyZhang-NYandClaude Opus 5.5 8b521ef5d9 Q44: queued runs re-check their task and are superseded when it changed 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 07:59:14 -04:00
ZacharyZhang-NYandClaude Opus 5.5 9be5ad06c1 Q42: claimed runs that fail in preparation close cleanly and are logged 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 07:42:16 -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 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 8c70111c93 Q25: runs leave outcomes and failure causes as searchable memory 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 05:34:17 -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 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 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 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 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 31ab919334 Q10: wake tasks no longer carry a truncated copy of the message 
Manual re-runs of a chat wake answer the same thread.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 03:36:22 -04:00
ZacharyZhang-NYandClaude Opus 5.5 abe9534350 Q9: chat wakes carry every new message and the latest history 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 03:29:59 -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 46dd77ddda Q5: give chat wakes timed, attributed history apart from the new ask 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 02:48:15 -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 77505aab8d Q1: keep other work's chat mentions out of task prompts 
Every mention already wakes the agent through its own chat-wake task, so
ordinary tasks no longer inject the org-wide mention inbox.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-08 02:19:48 -04:00
ZacharyZhang-NY 7de378b41c A chat-wake reply is delivered by the system, not by prompt compliance 
A wake run whose model answered in plain final text (the coding-tuned
Kimi family does this instead of calling send_message) completed
'successfully', closed its vehicle task, and left the founder staring
at a silent conversation — the reply lived only in provider_requests.
deliverChatReplyIfMissing now runs before a chat-wake run may complete:
when the run never posted into the source thread (run-start watermark,
so a send_message it did make suppresses the fallback), its final text
is delivered as the agent's reply. A delivery failure fails the run
loudly instead of closing it on silence.
 2026-07-16 11:46:53 -04:00
ZacharyZhang-NY 75c73ce6f0 The founder probes through provider cooldowns; a served request lifts the park 
A single transient failure from a background run used to silence the whole
company — founder included — for the full ten-minute cooldown. The
interactive lane now claims one probe per park window: the founder's
message tries the provider immediately, a success lifts the cooldown for
everyone (a served request is proof of health), and a failed probe re-arms
the park with the probe spent, so a real outage is never hammered.
Autonomous work still waits cooldowns out unconditionally.
 2026-07-14 21:19:14 -04:00
ZacharyZhang-NY 9246e7e312 The founder gets a dedicated execution lane, not just queue priority 
Claim priority alone still left the founder waiting behind whatever long
autonomous run held the single execution slot. The worker now runs two
slots: autonomous grinds the queue one run at a time as before, while
the interactive slot claims only human-triggered wakes and executes them
concurrently — a founder message answers in seconds regardless of what
the company is building in the background. Housekeeping (wake expiry,
goal reviews, heartbeat enqueue) now runs every tick instead of pausing
during long runs. Integration test pins the concurrency: the CEO's reply
lands while a gated autonomous run is still in flight.
 2026-07-14 21:15:19 -04:00