Commit Graph

39 Commits

Author SHA1 Message Date
Jingzhe Xu 081fe2d172 feat: 完善两阶段 Agent 自进化 Pipeline、Skills 与 Benchmark (#129) 2026-07-30 15:59:58 +08:00
Yaowei Zheng 1d23a7acaf feat(web,server,core): attach files to a message from the composer (#121)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-29 23:44:10 +08:00
Yaowei Zheng 4681135423 chore: make non-i18n code English-only (#117)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-29 18:03:41 +08:00
Yaowei Zheng 5b22ad06da fix(core): retry on failed as well as timeout; only auth stops the run (#104)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-29 16:57:05 +08:00
Yaowei Zheng e0a47254af feat(server,web): page the cost center's error table, abbreviate the source, drop command-tool noise (#103)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-29 16:16:15 +08:00
Yaowei Zheng 6b3574f5c9 fix(core,tooling): keep the harness's own ports out of the Agent's environment and off the dev server (#100)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: J.Li <jl2388@cam.ac.uk>
2026-07-29 16:15:23 +08:00
Yaowei Zheng 2b708d37fe release: 0.1.4 (#99)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 01:57:59 +08:00
Yaowei Zheng 71669b2086 fix(server): assert the version endpoint against core's constants, not a literal null (#97)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 01:43:38 +08:00
Yaowei Zheng 00e699f4af release: 0.1.3 (#93)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 01:34:41 +08:00
Yaowei Zheng 5a90dd46cd fix(deps): resolve the open Dependabot alerts (#94)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 00:54:44 +08:00
rank-Yu 46463bee26 feat(core,cli,server,web): add goal mode — loop Tasks on one Session until an objective completes (#66)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-27 23:43:24 +08:00
Yaowei Zheng e1141ca010 feat(core,server,web,cli): show version in the web UI with update check and admin self-update (#74)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-27 23:34:06 +08:00
Yaowei Zheng 033d526f9f fix(server): harden test cleanup and deadlines for Windows runners (#88)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-27 23:16:20 +08:00
Yaowei Zheng f192db338e feat(server,web): import and export Trace files in the trace viewer (#73)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-27 22:54:57 +08:00
Yaowei Zheng a955046b73 fix(server): give the mid-stream fake session the skipReconnectWait member (#86)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-27 22:37:55 +08:00
Yaowei Zheng 094ebd6118 fix(server,web): live in-progress output survives refresh and reconnect (#77)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-27 22:31:57 +08:00
Yaowei Zheng 3d3495528c fix(core,web): retry transport and quota LLM errors, disable dead sessions on auth failure (#82)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-27 22:29:16 +08:00
Yaowei Zheng c369e089a7 feat(core,tooling): Windows support — shell selection, install.ps1, win-x64 release package, Windows CI (#79)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-27 22:17:35 +08:00
Yaowei Zheng f6ebf5d618 release: 0.1.2 (#69)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-26 23:18:16 +08:00
Yaowei Zheng 790f45191e fix(tooling): separate the dev data root from the installed one (#67)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-26 23:07:27 +08:00
Yaowei Zheng 7584171482 feat(core,server,web,cli): mid-run steering messages and square-bracket markers (#63)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-26 23:01:18 +08:00
Yaowei Zheng abd5b13d52 feat(core,web,cli): add file tools and per-tool call descriptions (#62)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-26 21:37:51 +08:00
Yaowei Zheng 1e23452f48 Handoff-style /model switch command and per-turn thinking level (#64)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-26 16:31:51 +08:00
Yaowei Zheng 816a823b75 fix(core): present the project dir to the model as the App Data Dir in the default system prompt (#61)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-26 15:08:09 +08:00
Yaowei Zheng 6b8b631e37 fix(web): use the separate-origin preview for in-app HTML rendering (#59)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-26 14:52:25 +08:00
Yaowei Zheng 3f868ac385 refactor(web): unify form controls, one notification rule, dedupe i18n copy (#54)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-24 18:43:18 +08:00
Yaowei Zheng b18ae8f5f1 feat(server,web): serve Workspace HTML previews from a separate origin (#46)
Serve "open in new tab" HTML previews from a separate origin (the loopback counterpart, or PENGUIN_PREVIEW_ORIGIN) with a signed, host-bound token, so localStorage/cookies/third-party embeds work while Agent-generated pages stay off the app origin. The app is canonicalized onto localhost and the preview host (127.0.0.1) serves only /preview/* — its /api answers 401 and app routes 302 to the canonical host — so the preview origin can neither set nor honor a session cookie.
2026-07-23 23:11:04 +08:00
Yaowei Zheng f3217dca4b release: 0.1.1 with Gemini 3.6 support and two blog posts (#44)
Co-authored-by: Alice <alice@prismshadow.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-23 06:13:49 +08:00
Yaowei Zheng c380113e26 feat: session source in session_meta and an Automated sidebar folder (#40)
Co-authored-by: Alice <alice@prismshadow.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-23 00:58:43 +08:00
Yaowei Zheng cabbab1c16 feat: per-model max output tokens and a conversation-time thinking level backed by agent settings (#28)
Co-authored-by: Alice <alice@prismshadow.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 22:22:41 +08:00
Zhang Jason 85f8b9bf1a fix(server): validate positiveIntParam and optionalDateParam inputs (#10) 2026-07-22 22:11:00 +08:00
Yaowei Zheng c9cd1f9dc5 feat(core): reserved-port and API-key guardrails in the default system prompt (#24)
Co-authored-by: Alice <alice@prismshadow.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 22:04:30 +08:00
Yaowei Zheng 636b25b63f feat(skills): vLLM and Ollama deployment plus LlamaFactory fine-tuning skills (#19)
Co-authored-by: Alice <alice@prismshadow.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 22:04:19 +08:00
Yaowei Zheng ea0549b8bb fix(llm): omit empty tools and keep tool_choice off the wire (#21)
Co-authored-by: Alice <alice@prismshadow.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 18:53:39 +08:00
Yaowei Zheng 0e134e9c6c Share language and theme across the sites; prepare the 0.1.0 release (#13)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-21 18:00:11 +08:00
Yaowei Zheng d4faee3a1e Changelog, dev startup, README, AgentHub 0.4.0, model catalog, and landing site (#7)
Branch-length batch covering tooling, the model layer, the Web App and the public
surfaces. Highlights:

- Changelog: a per-release `changelog/<version>/` tree, grouped by the surface each
  change touches, with a root CHANGELOG.md holding one line per release.
- Dev startup: `scripts/dev-prebuild.mjs` serializes the skills+core prebuild behind a
  lock and keeps `pnpm install` current; `pnpm dev` runs server+web together.
- AgentHub 0.3.3 -> 0.4.0: OmniMessage complete payloads carry one opaque `fidelity`
  object in place of item-level `signature`/`phase`, threaded verbatim through Trace,
  replay and resume; malformed classification adapted to the new error types.
- Model layer: a model is always referenced by an explicit `(provider, model_id)` pair.
  The provider is never inferred, guessed or defaulted -- both the catalog inference and
  the unique-match config resolution are gone, and CLI, SDK, server routes and
  run_subagent all require the complete pair. Catalog gains the Qwen Token Plan, Qwen
  Pay-As-You-Go and Fireworks AI gateways, plus an expanded OpenRouter group.
- Web App: catalog preset sync and per-group speed test on the Models page, positional
  slash commands, a markdown renderer, skill-library update reminders, and a vertically
  centred draft page whose upward menus size themselves to the room available.
- Public surfaces: restructured READMEs, the penguin.ooo landing site and blog, refreshed
  benchmark results for both suites, and the demo videos playing on the landing page.

Includes the fixes from a full review of the branch: 23 confirmed findings, among them a
provider-inference bug that could send one vendor's API key to another vendor's endpoint,
and an Escape handler that destroyed the composer's contents unrecoverably.

Verified on the branch head: pnpm test (1127 passing, 7 packages), pnpm typecheck and
pnpm format:check clean, Playwright e2e 14/14.
2026-07-21 17:43:31 +08:00
Yaowei Zheng 0eaaa54e25 Make English the repository working language (#5)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-20 17:45:02 +08:00
Yaowei Zheng 4fa2eef446 Serve the site from the penguin.ooo apex domain
Set the Pages workflow BASE_PATH to / (assets 404ed on the custom domain under the /<repo>/ subpath) and point all hardcoded site links at https://penguin.ooo.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018ihk8iQuo3kv2aPjAYEPuR
2026-07-19 15:05:47 +08:00
Yaowei Zheng 45bfae6e94 Initialize repository with harness code and assets
Initial import of all source code, config, and README assets: the
packages workspace (cli, core, server, web, docs, landing, skills),
build scripts, tooling config, and CI workflows.

Includes the data-layout revision made on this branch: the local data
root defaults to ~/.penguin/data (PENGUIN_HOME still overrides; the
installer keeps its binaries in ~/.penguin), and every Agent lives
under <project>/agents/<agent>/ — path helpers, the three
agent-enumeration scans, the system prompt, built-in Skills, tests
and docs all follow the new layout.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018ihk8iQuo3kv2aPjAYEPuR
2026-07-19 14:06:53 +08:00