Eric
3509c08057
[eric] workflows: remove scheduled-tasks end-to-end (frontend pages+slice, backend app+routes, electron poller), keep dock chat; bump 1.1.64
2026-05-26 11:12:29 -07:00
ciregenz
083d70def5
[eric] workflows: merge scheduled-tasks onto dev, re-home dashboard + fix backend imports
2026-05-24 23:41:53 -07:00
ciregenz
4e9f5ceb07
[eric] tree: group agent_manager helpers under agents/manager session and prompt
2026-05-23 13:08:01 -07:00
ciregenz
fa57be6bbb
[eric] tree: group foundational agent modules under agents/core
2026-05-23 13:05:15 -07:00
ciregenz
b9ce323c5f
[eric] deadcode: remove unused _summarize_message_block
2026-05-23 10:26:42 -07:00
ciregenz
8b646b0223
[eric] deadcode: remove unused _approx_tokens
2026-05-23 10:25:47 -07:00
ciregenz
8d76f39c67
[eric] cycles: pull APP_VERSION into its own leaf
2026-05-23 07:06:42 -07:00
ciregenz
65465aceec
[eric] split: extract attachment resolution
2026-05-23 03:18:22 -07:00
ciregenz
e5427ee492
[eric] split: extract prompt/context builders
2026-05-23 03:16:05 -07:00
ciregenz
ef7c523f1a
[eric] split: extract history compaction helpers
2026-05-23 03:11:58 -07:00
ciregenz
f26f4985a9
[eric] split: move aux LLM helpers out of agent_manager
2026-05-23 03:09:35 -07:00
ciregenz
b7ef925b03
[eric] split: extract tool catalog helpers
2026-05-23 03:08:53 -07:00
ciregenz
0e4e6ce371
[eric] split: carve out workspace git helpers
2026-05-23 03:08:09 -07:00
ciregenz
937d1bdf17
[eric] split: extract cloud session-close sync
2026-05-23 03:06:50 -07:00
ciregenz
6e0f8ecdb4
[eric] split: move session persistence into session_store
2026-05-23 03:05:39 -07:00
ciregenz
5f79a88f6e
[eric] split: pull error classifiers out of agent_manager
2026-05-23 03:02:33 -07:00
ciregenz
81fea443fd
[eric] cleanup: drop dead code, dedup 9router prefix, strip em-dashes (backend)
2026-05-23 02:29:22 -07:00
ciregenz
cbe5372471
[eric] attach: 9router bypass + Anthropic SSE translator for OpenAI/OR PDFs + 2-req OOM guard
2026-05-23 00:50:28 -07:00
ciregenz
a30229bbda
[eric] attach: native PDFs on Claude/Gemini/OR, cost calc, meter fix, 9router bypass for image blocks
2026-05-22 23:43:54 -07:00
ciregenz
245269c0ac
[eric] workflows: port backend scheduler + executor + schedule MCP server from dev
2026-05-21 22:29:07 -07:00
ciregenz
a2495f5899
[eric] updater + custom providers: allowDowngrade for rollback + Ollama bare-host URL /v1 normalization
2026-05-21 01:11:32 -07:00
ciregenz
ac99b0090b
fixes: MCP auto-continue lists tool names + history doesn't eat chats + WS strip replayed closes
...
(1) After MCPActivate, the continuation prompt now enumerates the
activated server's callable tool names so the next turn calls them
directly instead of burning a turn on tool-discovery guesses.
(2) Resume no longer deletes the session file from disk; previously
every click on a past chat permanently removed it from history.
(3) WS replay skips agent:closed events; replaying them on a fresh
client destructively deleted the session being opened.
2026-05-20 02:10:12 -07:00
ciregenz
6092fc0966
apps: canvas-chat App Builder seeds + sync meta.json + stale-approval filter
...
App Builder launched from canvas chat now seeds the React template and
registers an Output row tied to the session id, so the Apps sidebar
lights up immediately. Adds a post-session-complete sync that reads
meta.json from the workspace folder and updates the Output row's name
and description, ending the 'Untitled App' problem. Also adds a stale-
approval filter to the WS replay: resolved approvals no longer
resurrect as dead cards when the user navigates back to a chat.
2026-05-20 02:09:03 -07:00
ciregenz
0ba7d86fef
agent: block claude.ai partner MCPs in prompt + at SDK layer
...
claude_code preset auto-attaches the user's claude.ai-connected partner
MCPs (mcp__claude_ai_*). They bypass MCPActivate, don't share OAuth
state with OpenSwarm's Gmail/Drive/Calendar connectors, and confuse
the model into picking the partner shim instead of our vetted server.
Hard-block via disallowed_tools + add a system-prompt rule.
2026-05-20 02:03:22 -07:00
ciregenz
a1fefa0ae8
[eric] approvals: trust patterns for action approvals + smarter sensitive-file gating
2026-05-20 01:56:38 -07:00
ciregenz
db38311a8d
[eric] fix prod regressions: __import__ scrub broke imports + Windows path gate
2026-05-13 13:20:19 -07:00
ciregenz
ccec204bc7
[eric] security: gate Write/Edit on sensitive paths + restore HOME/PATH for force-mode Outputs
2026-05-13 11:49:33 -07:00
ciregenz
a84aec257b
[eric] App Builder uses real React/Vite scaffold + onboarding polish (auto sidebar expand, bigger pill, video crop), onboarding bugs / edgecases
2026-05-11 23:23:59 -07:00
ciregenz
573f4a1ed4
[eric] App Builder skill as editable built-in (Skills page, undeletable) + onboarding step 1 unsticks after Claude Max / ChatGPT Pro / Gemini /
...
custom-provider connect (subscription state moved to Redux)
2026-05-11 14:54:07 -07:00
ciregenz
d20ff7d16c
[eric] app builder cleanup — remove Auto Run, Test Input, RenderOutput tool + Outputs activation gate
2026-05-11 09:05:45 -07:00
ciregenz
294a16ada0
[eric] system prompt: direct mcp__openswarm-web__WebSearch/WebFetch hint when web MCP is active (fixes 2-minute ToolSearch thrash on small Ollama
...
models)
2026-05-10 19:09:49 -07:00
ciregenz
54be1e8ba1
[eric] onboarding 1.0.31 + Settings draft persistence + LM Studio fix
2026-05-10 17:57:01 -07:00
ciregenz
0c841bdad4
[eric] onboarding revamp — agentic cursor walks users through 8 setup steps, WIP fixes: Gemini schema scrub, OpenAI GPT-5 routing, websearch cascade, gpt-5 is still a bit flaky...
2026-05-09 01:40:37 -07:00
ciregenz
b3428a736b
[eric] custom OpenAI-compatible provider support, youtube bug fix (windows)
2026-05-07 21:22:40 -07:00
ciregenz
acd179d20e
[eric] gitleaks org-license fix; picker filter footer; trim+cache MCP gate prompt; losses compression caching on llm response (20% improvement avg)
2026-05-07 00:28:57 -07:00
ciregenz
fae2806124
[eric] make non-Anthropic API keys actually work end-to-end, fix the wildly wrong cost numbers, multi model ux/ui improvements
2026-05-06 21:05:57 -07:00
ciregenz
c64bf65c66
[eric] session state additions + ui hook refinements
2026-05-05 17:05:54 -07:00
ciregenz
49c649e3d9
[eric] single sync function for all state syncing
2026-05-05 12:11:07 -07:00
ciregenz
3c42d8738f
[eric] refactor internal service layer
2026-05-04 19:39:19 -07:00
ciregenz
b7a1faee38
[eric] delete miscelaneous scrapped code
2026-05-04 19:15:42 -07:00
ciregenz
5df979a59a
analytics: fix completion-rate, mock-cost, and tool-count accuracy bugs
2026-05-04 17:50:11 -07:00
ciregenz
8286cc1a5c
[eric] delete ~3.6k lines of dead code (old unused agent runtime, ghost fields, orphan scripts). all 660 tests still pass, no functional
...
change.
2026-05-03 22:39:17 -07:00
ciregenz
5f5b932c53
[eric] tiny dead-code sweep — drop unused langchain pins from requirements.txt (saves ~5MB on packaged build) plus a few orphan exports left
...
over from past iterations (temp_state slice fields, clipboard timestamp getter, three never-imported lastSeq helpers).
2026-05-03 21:31:13 -07:00
ciregenz
d14cc89300
[eric] tool labels read like a person — Plugged into Gmail, Saved a snapshot, varied phrasings per call; session/turn labels
...
in sentence case; activating an MCP mid-chat now actually works instead of the model guessing at made-up tool names. Also a bunch miscelaneous ui/ux tweaks, I cant be bothered :)
2026-05-03 20:44:32 -07:00
ciregenz
ade79315a9
[eric] thinking pill shows full turn cost (input + output + subagent + tool work) with click-to-see input/output breakdown; reopening
...
completed chats no longer replays the typewriter (per-session lastSeq survives AgentChat remount so resume protocol stays at the high-water
mark instead of last_seq=0)
2026-05-03 11:21:02 -07:00
ciregenz
d310f9e031
[eric] thinking pill works on GPT/Gemini (clickable bubble with duration + token count + honest "provider does not expose
...
reasoning text" note instead of vanishing); friendlier MCP tool names (Gmail/Slack/etc with verb-derived actions); auto-collapse Anthropic
thinking pill on turn end so the answer comes first; header timer matches per-turn pill (sums in ms, rounds once); thinking pill rolls 251s
to 4m 11s; parallel tool count chips do not jitter as N grows; drop Gemini 2.5 from picker (Gemini 3 family only); aux-LLM calls route
per-model so cheap-tier auxiliary calls do not 401 on cc/ subscription routes
2026-05-02 23:46:13 -07:00
ciregenz
691a92c2a1
[eric] dynamic turn labels in the thinking pill via cheap-tier aux LLM + cache pre-warm on dashboard mount for faster turn-1
...
TTFT
2026-04-30 12:31:48 -04:00
ciregenz
98349df9f1
[eric] faster replies + smarter chat: optimistic message bubbles, live thinking... pill, friendlier tool-call labels (Reading → Read),
...
compaction chip, native completion notifications, prompt-cache flip for ~70% cheaper/faster
2026-04-29 14:07:18 -04:00
ciregenz
b7c93e2251
[eric] global ⌘K search + ⌘L clear chat + sticky notes on canvas + merge Chat into Ask + chat composer/dock sizing + spellcheck
2026-04-29 02:41:01 -04:00
ciregenz
5d69215739
[eric] phase 2+3: outputs gate, smart compaction, slash commands, preflight + auto-continue, bumped Anthropic SDK
2026-04-28 19:55:06 -04:00
Eric