Zum Hauptinhalt springen
Sichere ProgrammierungI'm an AI agent. I read the agent-economy job boards' own numbers.(05.10.2026 um 03:41 Uhr)
••••
Sichere ProgrammierungYour ops dashboard does not need a frontend framework(05.10.2026 um 03:47 Uhr)
•
Sichere ProgrammierungThree pieces, zero readers: what I got wrong about publishing(05.10.2026 um 03:47 Uhr)
•
Sichere ProgrammierungProofDesk: A contact review is only as current as its evidence(05.10.2026 um 03:49 Uhr)
•
AI & KI NachrichtenAI Agents - Tool Calling And Its Types(05.10.2026 um 03:49 Uhr)
•
Sichere ProgrammierungSTAGE LADDER - A Private, Offline Speaking Coach Built for a Friend(05.10.2026 um 03:51 Uhr)
••
Sichere ProgrammierungI'm an AI agent. I read the agent-economy job boards' own numbers.(05.10.2026 um 03:41 Uhr)
••••
Sichere ProgrammierungYour ops dashboard does not need a frontend framework(05.10.2026 um 03:47 Uhr)
•
Sichere ProgrammierungThree pieces, zero readers: what I got wrong about publishing(05.10.2026 um 03:47 Uhr)
•
Sichere ProgrammierungProofDesk: A contact review is only as current as its evidence(05.10.2026 um 03:49 Uhr)
•
AI & KI NachrichtenAI Agents - Tool Calling And Its Types(05.10.2026 um 03:49 Uhr)
•
Sichere ProgrammierungSTAGE LADDER - A Private, Offline Speaking Coach Built for a Friend(05.10.2026 um 03:51 Uhr)
••
Intelligence View
⚡ tsecurity.de Intelligence

GitHub Release: can1357/oh-my-pi v18.4.11 (02.10.2026)

Release v18.4.11 von can1357/oh-my-pi auf GitHub: @oh-my-pi/pi-agent-core Fixed Fixed lenient argument validation for tools such as yield: malformed tool-call…

Beitrag
0
Seite
0
↗ Quelle (GitHub · can1357/oh-my-pi)
Social ReaktionenReagiere als Erste:r — dein Feedback zählt!
can1357/oh-my-piv18.4.1102.10.2026@github-actions[bot]

@oh-my-pi/pi-agent-core


Fixed



  • Fixed lenient argument validation for tools such as yield: malformed tool-call JSON is now reported to the model instead of causing the tool to run with empty arguments.


@oh-my-pi/pi-ai


Fixed



  • Fixed Cursor cached prompt token accounting to prevent duplicate input-token and cost reporting on cached turns.

  • Fixed auth-broker credential handling so late token-refresh responses cannot restore logged-out credentials or overwrite a newer login.


@oh-my-pi/pi-catalog


Fixed



  • Fixed new Fireworks sessions failing on the first turn by updating the default model to kimi-k3, which is currently supported by Fireworks.


@oh-my-pi/pi-coding-agent


Added



  • Added goal management for RPC hosts and optional automatic goal continuation via goal.continuationModes: ["rpc"]. RPC clients can create, inspect, pause, resume, and remove goals, and view the current goal in get_state.

  • Added --goal <objective> for interactive launches to begin a new session in goal mode without requiring the /goal command.

  • Added periodic completion estimates for running subagents, with configurable polling through task.completionProbeMs and progress displayed in wait and task views.

  • Added the RPC fork command (RpcClient.fork(entryId?), Python fork(entry_id=None)): it moves an RPC session onto a new session file holding the history up to and including any message entry (and the tool results answering a cut tool-call batch), together with the session's artifacts, or a copy of the whole session when entryId is omitted (#14077 by @andrebrait).

  • Added reason ("branch", "fork" or "btw") to the session_before_branch and session_branch extension and hook events, so handlers can tell whether entryId is dropped (branch) or kept (#14077 by @andrebrait).


Fixed



  • Fixed skill-description and text-prediction data not respecting XDG directories; existing data is now migrated to $XDG_DATA_HOME/omp when applicable.

  • Fixed subagent MCP calls ignoring the parent transport timeout, including configured OMP_MCP_TIMEOUT_MS and unlimited (timeout: 0) settings.

  • Fixed fresh setups failing on the first turn when the automatically selected model did not support the configured thinking level.

  • Fixed the read tool hanging and the TUI becoming unresponsive when asked to read standard input, FIFOs, or other non-regular files; these paths are now rejected.

  • Fixed project configuration from ~/.omp being incorrectly applied to unrelated working directories under the user's home directory.

  • Fixed omp update failing on standalone-binary installs when npm advertised a version whose GitHub release was never published; the updater now installs the newest published release instead (#12913).


@oh-my-pi/pi-tui


Added



  • Added subagent completion percentages to the agent tree, task, and wait views.


Changed



  • Updated notebook evaluation cells in native hosts to use directional gutter indicators for inputs and outputs, with a progress indicator while a cell is running.


Fixed



  • Fixed multiline paste on Windows so pasted line breaks are inserted correctly instead of terminal escape sequences.


@oh-my-pi/pi-utils


Added



  • Added XDG-aware utility paths for skill descriptions and prediction state, with automatic adoption of legacy data when XDG locations are first resolved.


Fixed



  • Fixed machine-global daemon runtime paths so brokers such as text prediction use the shared XDG state location across profiles and custom agent directories.


@oh-my-pi/pi-wire


Added



  • Added support for agent completion estimates in the wire protocol.


What's Changed



  • fix(tui): decoded win32-input-mode records inside bracketed paste by @roboomp in #14066

  • feat(coding-agent): start goal mode at interactive launch by @shawnkoh in #13879

  • feat(coding-agent): goal command, goal state and opt-in continuation for RPC hosts by @shawnkoh in #13952

  • fix(coding-agent): fix skill-descriptions.db && predict 's pos for xdg spec by @Parsifa1 in #13648

  • fix(read): refuse FIFOs and devices instead of blocking on them by @DrFaustus-vic in #13585

  • fix(coding-agent): fit default thinking level to the auto-picked startup model by @will-bogusz in #13657

  • fix(ai): stop counting cached Cursor prompt tokens twice by @will-bogusz in #13723

  • fix(mcp): honor configured transport deadlines in subagent proxies by @NikkeTryHard in #13862

  • fix(ai): keep newer broker credentials over delayed refresh replies by @atyrode in #13770

  • docs: qualify the browser MCP filter section in mcp-config by @pavel-kalmykov in #13896

  • fix(discovery): never treat ~/.omp as a project config dir by @NaC-L in #14084

  • fix(catalog): default fireworks to kimi-k3 by @alphastorm in #14068

  • fix(agent): reported malformed tool json to lenient tools by @roboomp in #14096

  • fix(cli): resolve binary updates against published GitHub releases by @roboomp in #12914

  • feat(coding-agent/rpc): added fork command that cuts at any transcript entry by @andrebrait in #14077

  • fix(pi-edit): strip the Windows verbatim prefix when validating hashline recovery by @jchanghong023 in #13045


New Contributors



Full Changelog: v18.4.10...v18.4.11

🔍 CTI & Forensik

Cyber Threat Intelligence & Forensik

ATT&CK-Navigator · IoC-Radar · Exploit-Belege
CTI Threat Relationship Graph
Akteure · Techniken · Beziehungen
2 Knoten · 1 Relationen
CVE / Incident Threat Actor Software MITRE ATT&CK CWE Weakness IoC
Zum Aktualisieren ziehen
Nächster Beitrag