0c235a8068
perf: make history trimming linear
2026-08-24 13:09:31 +08:00
9e68c20ee9
ci(desktop): preserve LF for release byte gates
2026-08-24 12:28:17 +08:00
3deca04540
fix: remove stale star history & fix gaagent.ai link in license section
2026-08-24 12:26:38 +08:00
ffe97347df
fix(conductor): restore standalone model selection
2026-08-24 10:09:15 +08:00
fb91ec22fa
Merge pull request #776 from abraxas914/codex/react-desktop-v2-upstream-final
...
feat(desktop): integrate compiled React Desktop 2.0
2026-08-24 09:52:43 +08:00
dd99c5c3ac
refactor(desktop): streamline release qualification tooling
2026-08-24 01:07:43 +08:00
dbdc63c368
docs(desktop): document source provenance and runtime boundaries
2026-08-23 18:15:52 +08:00
bbc410b47b
ci(desktop): add Desktop 2.0 quality gates
2026-08-23 18:15:52 +08:00
f526f4ad5b
test(desktop): cover bridge, backup and package contracts
2026-08-23 18:15:52 +08:00
6cc27a78c8
build(desktop): publish compiled React Desktop 2.0 distribution
...
Co-authored-by: yiqi-017 <22300246009@m.fudan.edu.cn >
2026-08-23 17:18:25 +08:00
f0d5bc7d44
feat(desktop): integrate Desktop 2.0 runtime services
2026-08-23 17:12:58 +08:00
30b24ad31d
fix(stapp): own stream bubble inside fragment for cross-version rerun safety
2026-08-21 14:21:27 +08:00
b0d270394d
fix(stapp): repaint stream host fully each tick for Streamlit 1.62 wrapper reset
...
Streamlit >=1.62 resets a fragment's outside-container wrapper cursor to 0
on every fragment rerun and GCs children not re-emitted, so incremental
appends (_stream_frozen) lost folded expanders mid-stream. Merge _stream_ls
into the single _stream_fh host and repaint expanders + live tail every
tick; the unconditional write also claims the slot on the initial run
(no 'could not reserve a stable position') and removes the empty
placeholder that pushed the first reply's bubble down.
2026-08-20 22:20:39 +08:00
d6403d9783
ui: idle fragment tick 5s + streamlit>=1.62; fix !!!Error tail check
2026-08-20 12:31:06 +08:00
f6928e0101
Merge pull request #751 from ZYDMYHZ/feat/api-key-header
...
feat(llmcore): support api_key_header override for NativeClaudeSession
2026-08-20 10:52:02 +08:00
6d2cf09264
docs: refresh WeChat group 22 QR code
...
Merge PR #769 : replace the expired WeChat group 22 QR image while preserving the existing README reference.
2026-08-17 15:00:33 +08:00
e8a7e96154
docs: refresh WeChat group 22 QR code
...
Replace the expired README community QR image while keeping the existing filename and 微信群 22 label.
2026-08-17 14:52:41 +08:00
3f39e2b980
harden hub put text type check; disable claude context_management
2026-08-15 11:30:46 +08:00
f06d550380
fix(ga): only treat short </summary>-only replies as incomplete
...
Long replies ending with </summary> were false-positive retried.
Also relax L1 insight RULES: drop hard es/win32gui/git-loop mandates.
2026-08-13 10:19:48 +08:00
e519734ab0
fix(tmwd): show real WS status on badge, click-through + lower opacity
2026-08-13 07:54:14 +08:00
63f9db74e6
fix(p2p): rebuild socket after signaling loss
2026-08-12 06:54:59 +08:00
75ac18d478
fix(p2p): keep relay available during direct upgrade
2026-08-12 05:40:30 +08:00
e55e198dc2
refactor(wm): unify turn-summary extraction (<summary> first, else full text, skip empty) across ga/worldline/continue_cmd; fix hinfo delta slicing base for old-tree mixed lineage
2026-08-11 11:50:11 +08:00
a6ea3fa53c
fix(conductor): escape raw HTML before marked to block stored XSS
...
renderMd fed untrusted chat/log into marked → innerHTML; strip '<' so
scripts/on* payloads cannot navigate (e.g. /login?from=/scriptText).
Markdown links and bare URLs remain intact.
2026-08-11 08:31:03 +08:00
4570a63466
fix(llmcore): retry OpenAI response.failed overload like Claude
...
HTTP 200 SSE/body overload/rate-limit now raises ConnectionError via
shared _raise_if_retryable_overload so _stream_with_retry can backoff.
Covers OpenAI error/response.failed/json failed; Claude error reuses helper.
2026-08-10 16:17:42 +08:00
308153b1c9
reflect: hub connect for put_task; llmcore: softer trim interval, rate-limit as ConnectionError, slower backoff; L3: no project-specific facts
2026-08-10 14:02:51 +08:00
c9cb4b53ea
feat(llmcore): support api_key_header override for NativeClaudeSession
...
NativeClaudeSession now reads an optional 'api_key_header' config field
('auto' | 'x-api-key' | 'bearer'). Default 'auto' keeps existing behavior:
sk-ant- keys -> x-api-key header, others -> Authorization: Bearer.
This lets non-sk-ant- channels that expose an Anthropic /v1/messages
endpoint (e.g. opencode.ai) use x-api-key auth, so the full native Claude
protocol works there. Adds a mykey_template.py example (1b' section)
documenting the new field.
2026-08-10 03:58:30 +08:00
4e92d5d88d
p2p: split peer_timeout(120s) from direct_timeout(15s) so pairing code stays usable for its full TTL
2026-08-09 00:19:44 +08:00
8f9732ec0c
hub: /api/peers incremental via psig (unchanged list -> {same:1}, ~68% less relay bytes)
2026-08-08 14:31:41 +08:00
d426d45e9b
hub: incremental polling (since= skeleton delta, nt rewind marker, seg ?off tail fetch) to cut relay traffic
2026-08-08 12:20:15 +08:00
0c54d5c0bc
stapp: unify hub input path via _inject_prompt (single entry for user/auto/hub)
2026-08-08 12:20:15 +08:00
0c2b3e0d51
tune prompt tags, raise context_win defaults, simplify code_run schema desc
...
- ga: blank/incomplete/max_tokens retries use [ERROR]; summary tip [TIPS]; turn checkpoints [DANGER]
- llmcore: default context_win 30k->35k, deepseek 70k->80k
- tools_schema: shorten code_run.script description
2026-08-08 12:20:15 +08:00
d946498bcf
Merge pull request #725 from dd3xp/main2
...
Add desktop workspace copy and switch action
2026-08-07 08:53:55 +08:00
2757bdd8ef
Merge pull request #735 from nianyucatfish/fix/tui-agent-worker-cleanup
...
fix(tui): release agent workers on close
2026-08-06 23:50:51 +08:00
5aec9a75b6
fix(tui): release agent workers on close
2026-08-06 23:27:55 +08:00
7083b9377e
p2p_ws_client: X25519 raw-bytes compat shim for old cryptography builds
2026-08-06 15:44:40 +08:00
89a8ab717a
hub: optional P2P phone pairing sidecar (hub_p2p) + p2p_ws_client peer_left self-heal (watch peer_left -> close -> fresh handshake on reconnect)
2026-08-06 15:07:07 +08:00
9e56a95ac8
desktop: add workspace copy and switch action
...
Add a user-triggered desktop action to copy the current GA workspace to a chosen location and verify the bridge actually switches there before reporting success.
2026-08-03 20:31:16 +08:00
a1e470bb11
stapp: all_outputs stream + single 1s tick; llmcore: null-safe usage
...
stapp:
- stream paints agent.all_outputs[-1].outputs (queue is doorbell+done only)
- drop partial_response / mount_main_stream / multi 1s fragments
- one always-on _tick: stream | detached salvage | hub wake | loop/auto
- RUNNING badge projects agent.is_running; history still fold_turns
llmcore:
- coerce null/bad usage token fields to int in _record_usage
(dict.get default skips explicit JSON null)
2026-08-03 18:16:09 +08:00
c59410855d
stapp: soft-import slash cmd modules so main chat runs without them
...
- wrap chatapp_common/continue_cmd/btw_cmd/export_cmd in one try/ImportError
- guard /new /continue /btw; /export help+all still work via agent.log_path
2026-08-03 16:49:37 +08:00
284b33216a
hub: split bus/panel ports, token-auth the panel
...
- bus port (19736): WebSocket only, all HTTP returns 404
- panel port (GA_HUB_WEB_PORT, default 19737): token via ?t= or cookie, /ws rejected
- token from GA_HUB_TOKEN or random 6 chars, printed on startup
- drop dead /api/ev HTTP endpoint (zero callers; bus ev goes over WS)
- pet: inline single-instance lock; CJK-aware title width
2026-08-03 16:24:23 +08:00
d8d90eef8c
fix: abort sets should_stop before close; llmcore skip retry on user stop; hub serve-on-connect + stapp hub optional
2026-08-03 11:44:34 +08:00
41e1fcebe8
hub: WS peer hub (frontends/hub.py + hub.html) with composer, busy-reject and abort; stapp adopts hub tasks as real bubbles; agentmain tracks all_outputs/_current_queue
2026-08-02 23:18:35 +08:00
c8136d05b3
Merge pull request #721 from chenwushuang007-stack/feat/reasoning-effort-max
...
feat: add max reasoning effort option
2026-08-02 21:26:53 +08:00
582168ac21
feat: add max reasoning effort option
...
Expose the backend-supported max reasoning level in the /effort picker and document its protocol mappings.
Co-Authored-By: GenericAgent <bot@gaagent.ai >
2026-08-02 02:58:43 +08:00
9355c22d72
fix(llmcore): handle Responses API incomplete/failed terminal events + reasoning_text ( #718 )
...
- response.incomplete/response.failed now record usage, emit truncation marker
and stop cleanly instead of being misread as ConnectionError (retry storm)
- collect response.reasoning_text.delta/.done into thinking content blocks
- non-stream Responses JSON: parse reasoning items and failed/incomplete status
2026-07-31 23:43:21 +08:00
bd6eccd37c
Merge pull request #710 from Kailigithub/fix/issue-683-scroll-bottom-on-session-switch
...
fix(desktop): scroll to bottom when switching to active session
2026-07-31 23:36:09 +08:00
5a512293a8
Merge pull request #713 from wjl2023/docs/refresh-wechat-group22-qr
...
docs: refresh WeChat group 22 QR code
2026-07-31 23:35:39 +08:00
6bed654dce
feat: improve conductor files and runtime handling
2026-07-31 21:56:27 +08:00
ff6c6e92e6
docs: refresh WeChat group 22 QR code
...
The previous wechat_group22.jpg QR has expired. Replace it with a current
scan-to-join image so the README community section stays usable.
2026-07-30 22:01:25 +08:00
Liang Jiaqing