[{"id":3687593,"web_url":"http://patchwork.ozlabs.org/comment/3687593/","msgid":"","list_archive_url":null,"date":"2026-05-07T08:25:45","subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","submitter":{"id":2694,"url":"http://patchwork.ozlabs.org/api/people/2694/","name":"Daniel P. Berrangé","email":"berrange@redhat.com"},"content":"On Tue, May 05, 2026 at 06:01:03PM +0100, Alex Bennée wrote:\n> While triaging the issue tracker I wondered if this would be a\n> suitable job for an AI agent. Unfortunately the OSS program doesn't\n> give any credits to run agents in gitlab. However I do have access to\n> models from my editor and ECA so I built one and tested it on a few\n> issues.\n> \n> Obviously this can't apply as is because it probably encodes too much\n> of my local setup (using pass for API keys) and uses the ECA as my\n> preferred coding agent. I assume at some point there will be agreement\n> between all the agents where skill live.\n> \n> Signed-off-by: Alex Bennée \n\n..snip..\n\n> diff --git a/.agents/skills/qemu-issue-triage/assets/labels.txt b/.agents/skills/qemu-issue-triage/assets/labels.txt\n> new file mode 100644\n> index 00000000000..d329f34183d\n> --- /dev/null\n> +++ b/.agents/skills/qemu-issue-triage/assets/labels.txt\n\nSeeing our labels listed like this triggers my urge to \"tidy\" :-)\n\nDon't take anything below to be a complaint / blocker about this patch.\nThis patch is fine in so much as it faithfully represents the mess we\nhave created in gitlab.\n\n> @@ -0,0 +1,133 @@\n> +# SPDX-License-Identifier: GPL-2.0-or-later\n> +ACPI Power Management related (ACPI / SMBIOS / HEST / GHES)\n> +Audio Audio devices; both backend (host audio) and frontend (guest audio)\n\nMixing frontend and backend is a bad idea in general IMHO.\n\nI feel like we should also have an explicit label for each backend, for\nboth audio and every other backend type.\n\n> +Audit Tooling A group for bugs and issues found via automated tooling such as fuzzing, sanitizers or AI\n> +Audit Tooling::AI For bugs found with AI assisted tools such as Mythos and other similar things\n> +Audit Tooling::Fuzzer Issues found via fuzzing. For security issues, please consult https://www.qemu.org/contribute/security-process/\n> +Audit Tooling::Sanitizer For issues found using sanitizers such as asan, lsan and tsan\n\nLabels with \"::\" are mutually exculsive, which is possibly not\nwhat we want here ? Should the first thing be 'Audit Tooling::Other'\ninstead of unqualified ?\n\n> +Bite Sized Candidates for first contributions; see also https://wiki.qemu.org/Contribute/BiteSizedTasks\n> +Build System configure, make, Meson, ninja, gcc, clang, ccache, etc.\n> +CI Continuous Integration; gitlab, travis, patchew, etc.\n> +CLI Command Line Interface\n> +Chardev Character device backends and related issues\n\nWe should have per-backend labels\n\n> +Closed::Duplicate There is already another ticket that is about the same issue\n> +Closed::Fixed The issue was fixed. Yay!\n> +Closed::Invalid This issue was not really a problem\n> +Closed::NotOurBug This is a bug, but not a bug in QEMU. Please report it and/or include a link to the report.\n> +Closed::NotReproducible This issue was not reproducible\n> +Closed::UnbackedFeature Nobody was willing to work on this feature request\n> +Closed::WontFix The issue was acknowledged, but the fix would be too complex, too expensive, or would introduce other problems.\n> +Cryptography\n> +Documentation Sphinx documentation, man pages, the wiki, --help output, etc.\n> +GDB Issues relating to using GDB via the gdbstub\n> +GUI Graphical User Interface (gtk, SDL, curses, VNC, spice, ...)\n> +GUI::Cocoa Cocoa\n> +GUI::DBus DBus\n> +GUI::GTK\n> +GUI::SDL SDL\n> +GUI::SPICE SPICE\n\nspice is duplicated later\n\n> +GUI::VNC\n\nI'd probably suggest \"ui\" as the prefix to match the dir / subsystem\nname.\n\nAlso probably use \":\" instead of \"::\" as there could be cases where\na bug affects multiple UIs.\n\n> +Guest Agent Issues related to the qemu-guest-agent binary. https://wiki.qemu.org/Features/GuestAgent\n> +Hard\n> +Launchpad Issues migrated from Launchpad\n> +Migration\n\nSurprised we don't want more categories here\n\n> +Modules\n> +Networking\n> +Python Python library issues (./python/)\n> +QAPI/QMP QEMU API / QEMU Machine Protocol, HMP and CLI, etc.\n> +QOM QEMU Object Model\n> +Regression\n> +Security\n> +Semihosting Semihosting calls provide a simple ABI for early bring-up of embedded devices and provide a way to output to the console and do basic file i/o while being debugged\n> +Softfloat QEMU's FPU emulation code (TCG only)\n> +Stable::can't fix The bug was reported on a stable branch but the fix is too invasive for backporting\n> +Stable::obsolete The bug was reported on a stable branch that is not maintained anymore\n> +Stable::to backport The bug was reported on a stable branch and needs to be backported on the next release from the branch\n> +Storage Block subsystem, Storage devices, etc.\n> +TCG plugins Anything related to the TCG plugins feature\n\nPerhaps accel:tcg:plugins ?\n\n> +TestCase The report includes a testcase\n> +Tests qtests, iotests, acceptance tests, VM tests, docker tests, and more.\n> +USB\n> +VFIO\n\nThis annoying sorting of all uppercase, then all lowercase is\npresent in the gitlab UI too\n\nhttps://gitlab.com/qemu-project/qemu/-/labels\n\nWe should probalby be universally lowercase, so that sorting is\nsensible.\n\n> +accel: HAX Intel's Hardware Accelerated Execution Manager (HAXM)\n> +accel: HVF Apple Hypervisor Framework\n> +accel: KVM Linux Kernel-based Virtual Machine\n> +accel: TCG QEMU Tiny Code Generator\n> +accel: WHPX Microsoft Windows Hypervisor Platform (WHPX)\n> +accel: Xen Xen Hypervisor\n\nWe're inconsistent in whether we use a space after \":\". Here we do,\nbelow we don't.\n\n> +block:9p The 9p network file system\n> +block:NVMe\n\nThese two are not like the others under 'block:'. 'NVMe' is frontend device,\nand 9p is a filesystem. I'd assume 'block:' applies to block/*.c\n\n> +block:curl\n> +block:nbd\n> +block:nfs Issues related to the NFS backend\n> +block:qcow2\n> +block:ssh\n> +block:vmdk\n\nProbably want a \"block:core\" for stuff not specific to one of the listed\nbackends.\n\n> +bsd-user\n> +device: PCI\n> +device: TPM Trusted Platform Module (TPM) devices\n> +device:graphics Issues relating to display device emulation, or rendering in general. See also \"GUI\".\n> +device:input Keyboards, Mice, Touchscreens, HIDs, etc.\n> +device:iommu IOMMU and SMMU\n> +device:pflash Parallel NOR flashes emulation\n> +device:sdmmc SD or (e)MMC cards emulation\n> +device:virtio virtio-related issues. https://www.linux-kvm.org/page/Virtio\n> +device:watchdog\n\nHere we sometimes have a space after : and sometimes don't\n\n\n> +efi EFI firmware related issues\n> +flaky-ci For test cases that are flaky when run under our CI\n> +gitlab\n\nSo should we be using \"CI\" or \"gitlab\" for CI issues :)\n\nProbably we should have:\n\n ci:gitlab\n ci:flaky\n\n> +guest: AIX\n> +guest: BSD Guest OS is BSD (NetBSD/FreeBSD/OpenBSD/etc)\n> +guest: Linux Guest OS is Linux/Linux-based\n> +guest: Windows Microsoft Windows guest\n> +guest: macOS Apple macOS / Darwin as guest OS\n> +guest: os2\n> +host: aarch64 Bugs reproducible on AArch64 hosts\n> +host: arm Bugs reproducible on ARM hosts\n> +host: loongarch64 Bugs reproducible on LoongArch64 hosts.\n> +host: mips Bugs reproducible on MIPS hosts\n> +host: ppc Bugs reproducible on Power hosts\n> +host: riscv Bugs reproducible on RISC-V hosts\n> +host: s390 Bugs reproducible on s390 hosts\n> +host: sparc64 Bugs specific to Sparc64 hosts\n> +host: x86 Bugs reproducible on x86 hosts\n> +host:32bit These are mostly TCG related bugs where we sometimes struggle with emulating larger guests, especially atomic and address space issues.\n\nMore space inconsistency\n\n> +hostos: BSD FreeBSD, OpenBSD, NetBSD, and derivatives as host OSes\n> +hostos: Linux Linux-based host operating systems (Fedora, RHEL/CentOS, Debian, Ubuntu, openSuSE et al)\n> +hostos: Windows Microsoft Windows host OS\n> +hostos: macOS Apple macOS / Darwin as a host OS\n> +icount issues relating to icount, deterministic execution and record/replay functionality\n\nPerhaps accel:tcg:icount ?\n\n> +kind: Not user visible\n\nWhat's this for, and why : instead of :: ? \n\n> +kind::Bug Bug or defect in functionality.\n> +kind::Feature Request Feature request or new functionality.\n> +kind::Task Research, investigations, and miscellaneous issues.\n> +libvfio-user\n> +linux-user\n> +qemu-img\n\nShould we have a \"tools:qemu-img\", and \"tools:....\" for everything\nelse too ?\n\n> +spice\n\nRedundant with 'GUI::SPICE\"\n\n> +sysadmin\n\nAny idea what this is supposed to refer to ?\n\n> +target: alpha DEC Alpha [alpha]\n> +target: arm Arm AArch32 or AArch64 [arm, aarch64]\n> +target: avr Atmel AVR [avr]\n> +target: hexagon Qualcomm Hexagon [hexagon]\n> +target: hppa Hewlett-Packard Precision Architecture; HP/HP, PA-RISC [hppa]\n> +target: i386 Intel/AMD x86 [i386, x86_64]\n> +target: loongarch loongarch64 target architecture\n> +target: m68k Motorola 68000 [m68k]\n> +target: microblaze Xilinx MicroBlaze [microblaze, microblazeel]\n> +target: mips MIPS [mips, mipsel, mips64, mips64el]\n> +target: nios2 Altera Nios II [nios2]\n> +target: openrisc OpenRISC [or1k]\n> +target: ppc IBM Power Architecture, PowerPC [ppc, ppc64, ppc64le]\n> +target: riscv RISC-V [riscv32, riscv64]\n> +target: rx Renesas RX [rx]\n> +target: s390x IBM Z, SystemZ, zSeries [s390x]\n> +target: sh4 Renesas SuperH [sh4, sh4eb]\n> +target: sparc Sun Microsystems SPARC [sparc, sparc64]\n> +target: tricore Infineon TriCore [tricore]\n> +target: xtensa Tensilica Xtensa [xtensa, xtensaeb]\n> +workflow::Confirmed Bugs that have been confirmed and reproduced.\n> +workflow::In Progress Someone is working on this issue.\n> +workflow::Needs Info Issue has insufficient information to verify.\n> +workflow::Patch available A patch is available\n> +workflow::Triaged Issue has been triaged and given a topic label.\n\n\nWith regards,\nDaniel","headers":{"Return-Path":"","X-Original-To":"incoming@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=pass (1024-bit key;\n unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256\n header.s=mimecast20190719 header.b=CjJL2zOm;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=nongnu.org\n (client-ip=209.51.188.17; helo=lists1p.gnu.org;\n envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org;\n receiver=patchwork.ozlabs.org)"],"Received":["from lists1p.gnu.org (lists1p.gnu.org [209.51.188.17])\n\t(using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits))\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4gB51b0Jmpz1yKd\n\tfor ; Thu, 07 May 2026 18:26:11 +1000 (AEST)","from localhost ([::1] helo=lists1p.gnu.org)\n\tby lists1p.gnu.org with esmtp (Exim 4.90_1)\n\t(envelope-from )\n\tid 1wKu3T-00086f-Rf; Thu, 07 May 2026 04:25:59 -0400","from eggs.gnu.org ([2001:470:142:3::10])\n by lists1p.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from )\n id 1wKu3S-00086O-2N\n for qemu-devel@nongnu.org; Thu, 07 May 2026 04:25:58 -0400","from us-smtp-delivery-124.mimecast.com ([170.10.133.124])\n by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from )\n id 1wKu3P-0002FG-L9\n for qemu-devel@nongnu.org; Thu, 07 May 2026 04:25:57 -0400","from mx-prod-mc-08.mail-002.prod.us-west-2.aws.redhat.com\n (ec2-35-165-154-97.us-west-2.compute.amazonaws.com [35.165.154.97]) by\n relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3,\n cipher=TLS_AES_256_GCM_SHA384) id us-mta-584-g7KOFEI9OkOTOVEmtWDehw-1; Thu,\n 07 May 2026 04:25:51 -0400","from mx-prod-int-05.mail-002.prod.us-west-2.aws.redhat.com\n (mx-prod-int-05.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.17])\n (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest\n SHA256)\n (No client certificate requested)\n by mx-prod-mc-08.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS\n id 5E37F1800343; Thu, 7 May 2026 08:25:50 +0000 (UTC)","from redhat.com (unknown [10.44.49.217])\n by mx-prod-int-05.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with\n ESMTPS\n id 15B351953947; Thu, 7 May 2026 08:25:48 +0000 (UTC)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com;\n s=mimecast20190719; t=1778142354;\n h=from:from:reply-to:reply-to:subject:subject:date:date:\n message-id:message-id:to:to:cc:cc:mime-version:mime-version:\n content-type:content-type:\n content-transfer-encoding:content-transfer-encoding:\n in-reply-to:in-reply-to:references:references;\n bh=5mMj7pbWg94xgyeLU5D1oCuH2dps3RMkdKTnfJCyvYg=;\n b=CjJL2zOm5ox2bVu5kank7jMAmro3XXo/2J/I/l5Kbe8kclNndMoP++DuDihQl5DIVUVsSV\n X52AaYRtepImbtTAZ7qWeNM9dYyH8RswibibPowcKIdDgmh/pL/tXpWHspSU99b5Pu+FPe\n dloFsNMtXUBiZBOBJ5fter33AmT6QGw=","X-MC-Unique":"g7KOFEI9OkOTOVEmtWDehw-1","X-Mimecast-MFC-AGG-ID":"g7KOFEI9OkOTOVEmtWDehw_1778142350","Date":"Thu, 7 May 2026 09:25:45 +0100","From":"Daniel =?utf-8?b?UC4gQmVycmFuZ8Op?= ","To":"Alex =?utf-8?q?Benn=C3=A9e?= ","Cc":"qemu-devel@nongnu.org","Subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","Message-ID":"","References":"<20260505170105.228162-1-alex.bennee@linaro.org>\n <20260505170105.228162-9-alex.bennee@linaro.org>","MIME-Version":"1.0","Content-Type":"text/plain; charset=utf-8","Content-Disposition":"inline","Content-Transfer-Encoding":"8bit","In-Reply-To":"<20260505170105.228162-9-alex.bennee@linaro.org>","User-Agent":"Mutt/2.3.1 (2026-03-20)","X-Scanned-By":"MIMEDefang 3.0 on 10.30.177.17","Received-SPF":"pass client-ip=170.10.133.124;\n envelope-from=berrange@redhat.com;\n helo=us-smtp-delivery-124.mimecast.com","X-Spam_score_int":"-24","X-Spam_score":"-2.5","X-Spam_bar":"--","X-Spam_report":"(-2.5 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.443,\n DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1,\n RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H5=0.001, RCVD_IN_MSPIKE_WL=0.001,\n SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no","X-Spam_action":"no action","X-BeenThere":"qemu-devel@nongnu.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"qemu development ","List-Unsubscribe":",\n ","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n ","Reply-To":"Daniel =?utf-8?b?UC4gQmVycmFuZ8Op?= ","Errors-To":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org","Sender":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org"}},{"id":3687649,"web_url":"http://patchwork.ozlabs.org/comment/3687649/","msgid":"","list_archive_url":null,"date":"2026-05-07T09:20:57","subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","submitter":{"id":85046,"url":"http://patchwork.ozlabs.org/api/people/85046/","name":"Philippe Mathieu-Daudé","email":"philmd@linaro.org"},"content":"On 7/5/26 10:25, Daniel P. Berrangé wrote:\n> On Tue, May 05, 2026 at 06:01:03PM +0100, Alex Bennée wrote:\n>> While triaging the issue tracker I wondered if this would be a\n>> suitable job for an AI agent. Unfortunately the OSS program doesn't\n>> give any credits to run agents in gitlab. However I do have access to\n>> models from my editor and ECA so I built one and tested it on a few\n>> issues.\n>>\n>> Obviously this can't apply as is because it probably encodes too much\n>> of my local setup (using pass for API keys) and uses the ECA as my\n>> preferred coding agent. I assume at some point there will be agreement\n>> between all the agents where skill live.\n>>\n>> Signed-off-by: Alex Bennée \n> \n> ..snip..\n> \n>> diff --git a/.agents/skills/qemu-issue-triage/assets/labels.txt b/.agents/skills/qemu-issue-triage/assets/labels.txt\n>> new file mode 100644\n>> index 00000000000..d329f34183d\n>> --- /dev/null\n>> +++ b/.agents/skills/qemu-issue-triage/assets/labels.txt\n> \n> Seeing our labels listed like this triggers my urge to \"tidy\" :-)\n\nShould we improve MAINTAINERS and store these tags there, then\ngenerate labels.txt?\n\n> \n> Don't take anything below to be a complaint / blocker about this patch.\n> This patch is fine in so much as it faithfully represents the mess we\n> have created in gitlab.\n> \n>> @@ -0,0 +1,133 @@\n>> +# SPDX-License-Identifier: GPL-2.0-or-later\n>> +ACPI Power Management related (ACPI / SMBIOS / HEST / GHES)\n>> +Audio Audio devices; both backend (host audio) and frontend (guest audio)\n> \n> Mixing frontend and backend is a bad idea in general IMHO.\n> \n> I feel like we should also have an explicit label for each backend, for\n> both audio and every other backend type.\n> \n>> +Audit Tooling A group for bugs and issues found via automated tooling such as fuzzing, sanitizers or AI\n>> +Audit Tooling::AI For bugs found with AI assisted tools such as Mythos and other similar things\n>> +Audit Tooling::Fuzzer Issues found via fuzzing. For security issues, please consult https://www.qemu.org/contribute/security-process/\n>> +Audit Tooling::Sanitizer For issues found using sanitizers such as asan, lsan and tsan\n> \n> Labels with \"::\" are mutually exculsive, which is possibly not\n> what we want here ? Should the first thing be 'Audit Tooling::Other'\n> instead of unqualified ?\n> \n>> +Bite Sized Candidates for first contributions; see also https://wiki.qemu.org/Contribute/BiteSizedTasks\n>> +Build System configure, make, Meson, ninja, gcc, clang, ccache, etc.\n>> +CI Continuous Integration; gitlab, travis, patchew, etc.\n>> +CLI Command Line Interface\n>> +Chardev Character device backends and related issues\n> \n> We should have per-backend labels\n> \n>> +Closed::Duplicate There is already another ticket that is about the same issue\n>> +Closed::Fixed The issue was fixed. Yay!\n>> +Closed::Invalid This issue was not really a problem\n>> +Closed::NotOurBug This is a bug, but not a bug in QEMU. Please report it and/or include a link to the report.\n>> +Closed::NotReproducible This issue was not reproducible\n>> +Closed::UnbackedFeature Nobody was willing to work on this feature request\n>> +Closed::WontFix The issue was acknowledged, but the fix would be too complex, too expensive, or would introduce other problems.\n>> +Cryptography\n>> +Documentation Sphinx documentation, man pages, the wiki, --help output, etc.\n>> +GDB Issues relating to using GDB via the gdbstub\n>> +GUI Graphical User Interface (gtk, SDL, curses, VNC, spice, ...)\n>> +GUI::Cocoa Cocoa\n>> +GUI::DBus DBus\n>> +GUI::GTK\n>> +GUI::SDL SDL\n>> +GUI::SPICE SPICE\n> \n> spice is duplicated later\n> \n>> +GUI::VNC\n> \n> I'd probably suggest \"ui\" as the prefix to match the dir / subsystem\n> name.\n> \n> Also probably use \":\" instead of \"::\" as there could be cases where\n> a bug affects multiple UIs.\n> \n>> +Guest Agent Issues related to the qemu-guest-agent binary. https://wiki.qemu.org/Features/GuestAgent\n>> +Hard\n>> +Launchpad Issues migrated from Launchpad\n>> +Migration\n> \n> Surprised we don't want more categories here\n> \n>> +Modules\n>> +Networking\n>> +Python Python library issues (./python/)\n>> +QAPI/QMP QEMU API / QEMU Machine Protocol, HMP and CLI, etc.\n>> +QOM QEMU Object Model\n>> +Regression\n>> +Security\n>> +Semihosting Semihosting calls provide a simple ABI for early bring-up of embedded devices and provide a way to output to the console and do basic file i/o while being debugged\n>> +Softfloat QEMU's FPU emulation code (TCG only)\n>> +Stable::can't fix The bug was reported on a stable branch but the fix is too invasive for backporting\n>> +Stable::obsolete The bug was reported on a stable branch that is not maintained anymore\n>> +Stable::to backport The bug was reported on a stable branch and needs to be backported on the next release from the branch\n>> +Storage Block subsystem, Storage devices, etc.\n\nWe should really expand this one.\n\n>> +TCG plugins Anything related to the TCG plugins feature\n> \n> Perhaps accel:tcg:plugins ?\n> \n>> +TestCase The report includes a testcase\n>> +Tests qtests, iotests, acceptance tests, VM tests, docker tests, and more.\n>> +USB\n>> +VFIO\n> \n> This annoying sorting of all uppercase, then all lowercase is\n> present in the gitlab UI too\n> \n> https://gitlab.com/qemu-project/qemu/-/labels\n> \n> We should probalby be universally lowercase, so that sorting is\n> sensible.\n> \n>> +accel: HAX Intel's Hardware Accelerated Execution Manager (HAXM)\n>> +accel: HVF Apple Hypervisor Framework\n>> +accel: KVM Linux Kernel-based Virtual Machine\n>> +accel: TCG QEMU Tiny Code Generator\n>> +accel: WHPX Microsoft Windows Hypervisor Platform (WHPX)\n>> +accel: Xen Xen Hypervisor\n> \n> We're inconsistent in whether we use a space after \":\". Here we do,\n> below we don't.\n> \n>> +block:9p The 9p network file system\n>> +block:NVMe\n> \n> These two are not like the others under 'block:'. 'NVMe' is frontend device,\n> and 9p is a filesystem. I'd assume 'block:' applies to block/*.c\n> \n>> +block:curl\n>> +block:nbd\n>> +block:nfs Issues related to the NFS backend\n>> +block:qcow2\n>> +block:ssh\n>> +block:vmdk\n> \n> Probably want a \"block:core\" for stuff not specific to one of the listed\n> backends.\n> \n>> +bsd-user\n>> +device: PCI\n>> +device: TPM Trusted Platform Module (TPM) devices\n>> +device:graphics Issues relating to display device emulation, or rendering in general. See also \"GUI\".\n>> +device:input Keyboards, Mice, Touchscreens, HIDs, etc.\n>> +device:iommu IOMMU and SMMU\n>> +device:pflash Parallel NOR flashes emulation\n>> +device:sdmmc SD or (e)MMC cards emulation\n>> +device:virtio virtio-related issues. https://www.linux-kvm.org/page/Virtio\n>> +device:watchdog\n> \n> Here we sometimes have a space after : and sometimes don't\n> \n> \n>> +efi EFI firmware related issues\n\nfirmware:efi, ...\n\n>> +flaky-ci For test cases that are flaky when run under our CI\n>> +gitlab\n> \n> So should we be using \"CI\" or \"gitlab\" for CI issues :)\n> \n> Probably we should have:\n> \n> ci:gitlab\n> ci:flaky\n> \n>> +guest: AIX\n>> +guest: BSD Guest OS is BSD (NetBSD/FreeBSD/OpenBSD/etc)\n>> +guest: Linux Guest OS is Linux/Linux-based\n>> +guest: Windows Microsoft Windows guest\n>> +guest: macOS Apple macOS / Darwin as guest OS\n>> +guest: os2\n\ns/guest/guestos/? (vs hostos)\n\n>> +host: aarch64 Bugs reproducible on AArch64 hosts\n>> +host: arm Bugs reproducible on ARM hosts\n>> +host: loongarch64 Bugs reproducible on LoongArch64 hosts.\n>> +host: mips Bugs reproducible on MIPS hosts\n>> +host: ppc Bugs reproducible on Power hosts\n>> +host: riscv Bugs reproducible on RISC-V hosts\n>> +host: s390 Bugs reproducible on s390 hosts\n>> +host: sparc64 Bugs specific to Sparc64 hosts\n>> +host: x86 Bugs reproducible on x86 hosts\n>> +host:32bit These are mostly TCG related bugs where we sometimes struggle with emulating larger guests, especially atomic and address space issues.\n> \n> More space inconsistency\n> \n>> +hostos: BSD FreeBSD, OpenBSD, NetBSD, and derivatives as host OSes\n>> +hostos: Linux Linux-based host operating systems (Fedora, RHEL/CentOS, Debian, Ubuntu, openSuSE et al)\n>> +hostos: Windows Microsoft Windows host OS\n>> +hostos: macOS Apple macOS / Darwin as a host OS\n>> +icount issues relating to icount, deterministic execution and record/replay functionality\n> \n> Perhaps accel:tcg:icount ?\n> \n>> +kind: Not user visible\n> \n> What's this for, and why : instead of :: ?\n> \n>> +kind::Bug Bug or defect in functionality.\n>> +kind::Feature Request Feature request or new functionality.\n>> +kind::Task Research, investigations, and miscellaneous issues.\n>> +libvfio-user\n>> +linux-user\n>> +qemu-img\n> \n> Should we have a \"tools:qemu-img\", and \"tools:....\" for everything\n> else too ?\n> \n>> +spice\n> \n> Redundant with 'GUI::SPICE\"\n> \n>> +sysadmin\n> \n> Any idea what this is supposed to refer to ?\n\nDescribed as:\n\n Issues related to QEMU project infrastructure. You\n should probably also check on the projects IRC channel\n if the issue is urgent - https://www.qemu.org/support/\n\n> \n>> +target: alpha DEC Alpha [alpha]\n>> +target: arm Arm AArch32 or AArch64 [arm, aarch64]\n>> +target: avr Atmel AVR [avr]\n>> +target: hexagon Qualcomm Hexagon [hexagon]\n>> +target: hppa Hewlett-Packard Precision Architecture; HP/HP, PA-RISC [hppa]\n>> +target: i386 Intel/AMD x86 [i386, x86_64]\n>> +target: loongarch loongarch64 target architecture\n>> +target: m68k Motorola 68000 [m68k]\n>> +target: microblaze Xilinx MicroBlaze [microblaze, microblazeel]\n>> +target: mips MIPS [mips, mipsel, mips64, mips64el]\n>> +target: nios2 Altera Nios II [nios2]\n>> +target: openrisc OpenRISC [or1k]\n>> +target: ppc IBM Power Architecture, PowerPC [ppc, ppc64, ppc64le]\n>> +target: riscv RISC-V [riscv32, riscv64]\n>> +target: rx Renesas RX [rx]\n>> +target: s390x IBM Z, SystemZ, zSeries [s390x]\n>> +target: sh4 Renesas SuperH [sh4, sh4eb]\n>> +target: sparc Sun Microsystems SPARC [sparc, sparc64]\n>> +target: tricore Infineon TriCore [tricore]\n>> +target: xtensa Tensilica Xtensa [xtensa, xtensaeb]\n>> +workflow::Confirmed Bugs that have been confirmed and reproduced.\n>> +workflow::In Progress Someone is working on this issue.\n>> +workflow::Needs Info Issue has insufficient information to verify.\n>> +workflow::Patch available A patch is available\n>> +workflow::Triaged Issue has been triaged and given a topic label.\n> \n> \n> With regards,\n> Daniel","headers":{"Return-Path":"","X-Original-To":"incoming@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=pass (2048-bit key;\n unprotected) header.d=linaro.org header.i=@linaro.org header.a=rsa-sha256\n header.s=google header.b=hhi/OtgL;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=nongnu.org\n (client-ip=209.51.188.17; helo=lists1p.gnu.org;\n envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org;\n receiver=patchwork.ozlabs.org)"],"Received":["from lists1p.gnu.org (lists1p.gnu.org [209.51.188.17])\n\t(using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits))\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4gB6FS37HSz1y04\n\tfor ; Thu, 07 May 2026 19:21:32 +1000 (AEST)","from localhost ([::1] helo=lists1p.gnu.org)\n\tby lists1p.gnu.org with esmtp (Exim 4.90_1)\n\t(envelope-from )\n\tid 1wKuuo-0002f0-DD; Thu, 07 May 2026 05:21:06 -0400","from eggs.gnu.org ([2001:470:142:3::10])\n by lists1p.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from ) id 1wKuum-0002eO-Cm\n for qemu-devel@nongnu.org; Thu, 07 May 2026 05:21:04 -0400","from mail-wm1-x335.google.com ([2a00:1450:4864:20::335])\n by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128)\n (Exim 4.90_1) (envelope-from ) id 1wKuuj-0007SM-UX\n for qemu-devel@nongnu.org; Thu, 07 May 2026 05:21:04 -0400","by mail-wm1-x335.google.com with SMTP id\n 5b1f17b1804b1-488b8bc6bc9so3617575e9.3\n for ; Thu, 07 May 2026 02:21:00 -0700 (PDT)","from [192.168.69.200] (88-187-86-199.subs.proxad.net.\n [88.187.86.199]) by smtp.gmail.com with ESMTPSA id\n ffacd0b85a97d-4504f4857ffsm18339511f8f.0.2026.05.07.02.20.58\n (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128);\n Thu, 07 May 2026 02:20:58 -0700 (PDT)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=linaro.org; s=google; t=1778145659; x=1778750459; darn=nongnu.org;\n h=content-transfer-encoding:in-reply-to:from:references:cc:to\n :content-language:subject:user-agent:mime-version:date:message-id\n :from:to:cc:subject:date:message-id:reply-to;\n bh=jX12XVC+Vho/n7PvBrFP/IjM7M1aVSvvTTtKaSzihnk=;\n b=hhi/OtgLtTdg9nBJBrY4l06OD0yFRQ4iGESTGu3AOI8yCxdv3HvDe9bqgDcEigd0NP\n dBVXM5VLlDze996SMELsnTw0iELXDrYogKfPsK9LZnQsVqnrfeG7VYPeJs5dbCNLMu7h\n QWZk5g8uqHcp5Bc/vI8XD7I/5pfNNg+sqDqH/LySgn4nVIpCz7eF++8fpD2cfpPZ36Nb\n L1wqWB8r+IIQIbbPP25RfzlpN2ZrwgmEDJzJ03n9Ne9a7tbDGWuRuIAAUo/NP+GWaTCv\n yrZZWeWZKBSlkHpuR/4da4KFh2G4XKsoXjdEMZKUAamZ9otJReT0Olls06aVX5no5E8r\n CMJQ==","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1778145659; x=1778750459;\n h=content-transfer-encoding:in-reply-to:from:references:cc:to\n :content-language:subject:user-agent:mime-version:date:message-id\n :x-gm-gg:x-gm-message-state:from:to:cc:subject:date:message-id\n :reply-to;\n bh=jX12XVC+Vho/n7PvBrFP/IjM7M1aVSvvTTtKaSzihnk=;\n b=C0MlcemQxMYpmrKrFy2IpmPoC7cDqWtSK4rbi8VXuNrW5CLts5jR4ZrPC+S+54NBxI\n kKH4fS+BkUDlCmvDaqt4Ynamot6tXXul9zPWD//oLplPd+eUIyxPG+i1xV64H5qaYDW7\n WoX/zxbUoakmlj44HIqR0q2O+JJe4mwqi0jvSZ5GnSDou5ttItKX7iAZwTJBh/TNcV3F\n g/yV6MDk0VAtrYk+aPYWhjhWG7Sgdq77OkYgZmPF4pY24E/9n2Th+7lz27gmnAnPJtQL\n /08DRUoChYuN8HqN514Qg0hWRWqSO39IhuJxBMnVcPsbIKBsQzqPsZFbYSSoZh2qG7Zv\n 6PVg==","X-Gm-Message-State":"AOJu0YyqESO+IyM5mS7MM67Y1Pabg5Ds43XV/U4JzWzhjHpOA0U8jn1l\n +LzAk1vz+un1c3MbJyVYy19MEG1eATvW5jeucVFxhZxZtePuMxpXJKvIJT4Fv4XSBPU=","X-Gm-Gg":"AeBDietRUojyuSHus/E/VFAlOW9h9VioopJwHyZl7NvIQMPF014LDdIqL2vaNv4Dyd4\n efx+YsofPTTKRG3SD6rl0Nfk7H6iSu1AUa9E3kdNP49WnvjILENZSf8RVB7qI+6UBKd37cUhUFa\n 5NODUm//u7MyQ1K1L2VC75TQo3+5U/whezLykpZTS/OQtlXVFX0U8ra0VMK0vZNWfRCU6CHBCsi\n q2c1Q9epVPBU1LHbFUpmoRamxXt6Hy797y65iITPKS981iK9zIVlGzOl15QSrr/+OV0FTyl6IsG\n 8iukJC7G0OAgbRRaYv24LfZOXF1/GKbnqlf03Pw1wVqv/q6109qCjvGkuGYvqWxXiyE9C3dCFOb\n nTreg07WN8A8Mhp2Wz1iZQxHVMh/PHGW8QfEhqnWtDImxkNmCavpOym+vVq9moHwe8cI0lrHWW0\n JIYaN/UW5LpQcFoQc517eiFk6VjXkaGTnsG/w2/gKycEedu16JBitEK6REfPfCC+YoWWKVBRN9i\n hz/hYTPh+7bYzw=","X-Received":"by 2002:a05:600c:3208:b0:48a:75b9:b0bc with SMTP id\n 5b1f17b1804b1-48e51f46c07mr62308975e9.29.1778145658957;\n Thu, 07 May 2026 02:20:58 -0700 (PDT)","Message-ID":"","Date":"Thu, 7 May 2026 11:20:57 +0200","MIME-Version":"1.0","User-Agent":"Mozilla Thunderbird","Subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","Content-Language":"en-US","To":"=?utf-8?q?Daniel_P=2E_Berrang=C3=A9?= , =?utf-8?q?A?=\n\t=?utf-8?q?lex_Benn=C3=A9e?= ","Cc":"qemu-devel@nongnu.org","References":"<20260505170105.228162-1-alex.bennee@linaro.org>\n <20260505170105.228162-9-alex.bennee@linaro.org>\n ","From":"=?utf-8?q?Philippe_Mathieu-Daud=C3=A9?= ","In-Reply-To":"","Content-Type":"text/plain; charset=UTF-8; format=flowed","Content-Transfer-Encoding":"8bit","Received-SPF":"pass client-ip=2a00:1450:4864:20::335;\n envelope-from=philmd@linaro.org; helo=mail-wm1-x335.google.com","X-Spam_score_int":"-20","X-Spam_score":"-2.1","X-Spam_bar":"--","X-Spam_report":"(-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1,\n DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1,\n RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001,\n SPF_PASS=-0.001 autolearn=ham autolearn_force=no","X-Spam_action":"no action","X-BeenThere":"qemu-devel@nongnu.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"qemu development ","List-Unsubscribe":",\n ","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n ","Errors-To":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org","Sender":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org"}},{"id":3687674,"web_url":"http://patchwork.ozlabs.org/comment/3687674/","msgid":"","list_archive_url":null,"date":"2026-05-07T09:32:19","subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","submitter":{"id":2694,"url":"http://patchwork.ozlabs.org/api/people/2694/","name":"Daniel P. Berrangé","email":"berrange@redhat.com"},"content":"On Thu, May 07, 2026 at 11:20:57AM +0200, Philippe Mathieu-Daudé wrote:\n> On 7/5/26 10:25, Daniel P. Berrangé wrote:\n> > On Tue, May 05, 2026 at 06:01:03PM +0100, Alex Bennée wrote:\n> > > While triaging the issue tracker I wondered if this would be a\n> > > suitable job for an AI agent. Unfortunately the OSS program doesn't\n> > > give any credits to run agents in gitlab. However I do have access to\n> > > models from my editor and ECA so I built one and tested it on a few\n> > > issues.\n> > > \n> > > Obviously this can't apply as is because it probably encodes too much\n> > > of my local setup (using pass for API keys) and uses the ECA as my\n> > > preferred coding agent. I assume at some point there will be agreement\n> > > between all the agents where skill live.\n> > > \n> > > Signed-off-by: Alex Bennée \n> > \n> > ..snip..\n> > \n> > > diff --git a/.agents/skills/qemu-issue-triage/assets/labels.txt b/.agents/skills/qemu-issue-triage/assets/labels.txt\n> > > new file mode 100644\n> > > index 00000000000..d329f34183d\n> > > --- /dev/null\n> > > +++ b/.agents/skills/qemu-issue-triage/assets/labels.txt\n> > \n> > Seeing our labels listed like this triggers my urge to \"tidy\" :-)\n> \n> Should we improve MAINTAINERS and store these tags there, then\n> generate labels.txt?\n\nTricky question. IMHO the MAINTAINERS file is not neccessarily\nthe right granularity for issue labels. \n\n\n> > > +Storage Block subsystem, Storage devices, etc.\n> \n> We should really expand this one.\n\nThis has always confused me when we have many \"block:\" labels too.\n\nMixing backends and frontends is also an anti-pattern for label\ntagging.\n\nI'd think 'block:' for all backend stuff, and 'device:storage'\nfor all frontend stuff\n\n\n> > > +block:9p The 9p network file system\n> > > +block:NVMe\n> > \n> > These two are not like the others under 'block:'. 'NVMe' is frontend device,\n> > and 9p is a filesystem. I'd assume 'block:' applies to block/*.c\n> > \n> > > +block:curl\n> > > +block:nbd\n> > > +block:nfs Issues related to the NFS backend\n> > > +block:qcow2\n> > > +block:ssh\n> > > +block:vmdk\n> > \n> > Probably want a \"block:core\" for stuff not specific to one of the listed\n> > backends.\n\n> > > +efi EFI firmware related issues\n> \n> firmware:efi, ...\n\nYes, we have many more firmwares in git\n\n\n> > > +guest: AIX\n> > > +guest: BSD Guest OS is BSD (NetBSD/FreeBSD/OpenBSD/etc)\n> > > +guest: Linux Guest OS is Linux/Linux-based\n> > > +guest: Windows Microsoft Windows guest\n> > > +guest: macOS Apple macOS / Darwin as guest OS\n> > > +guest: os2\n> \n> s/guest/guestos/? (vs hostos)\n\nYes,\n\n> \n> > > +host: aarch64 Bugs reproducible on AArch64 hosts\n> > > +host: arm Bugs reproducible on ARM hosts\n> > > +host: loongarch64 Bugs reproducible on LoongArch64 hosts.\n> > > +host: mips Bugs reproducible on MIPS hosts\n> > > +host: ppc Bugs reproducible on Power hosts\n> > > +host: riscv Bugs reproducible on RISC-V hosts\n> > > +host: s390 Bugs reproducible on s390 hosts\n> > > +host: sparc64 Bugs specific to Sparc64 hosts\n> > > +host: x86 Bugs reproducible on x86 hosts\n\nAnd 'hostarch' for these perhaps\n\n\n> > > +host:32bit These are mostly TCG related bugs where we sometimes struggle with emulating larger guests, especially atomic and address space issues.\n\n\n> > \n> > More space inconsistency\n> > \n> > > +hostos: BSD FreeBSD, OpenBSD, NetBSD, and derivatives as host OSes\n> > > +hostos: Linux Linux-based host operating systems (Fedora, RHEL/CentOS, Debian, Ubuntu, openSuSE et al)\n> > > +hostos: Windows Microsoft Windows host OS\n> > > +hostos: macOS Apple macOS / Darwin as a host OS\n> > > +icount issues relating to icount, deterministic execution and record/replay functionality\n\nWith regards,\nDaniel","headers":{"Return-Path":"","X-Original-To":"incoming@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=pass (1024-bit key;\n unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256\n header.s=mimecast20190719 header.b=Cj7gqHVl;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=nongnu.org\n (client-ip=209.51.188.17; helo=lists1p.gnu.org;\n envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org;\n receiver=patchwork.ozlabs.org)"],"Received":["from lists1p.gnu.org (lists1p.gnu.org [209.51.188.17])\n\t(using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits))\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4gB6Vx4XXcz1yCg\n\tfor ; Thu, 07 May 2026 19:33:12 +1000 (AEST)","from localhost ([::1] helo=lists1p.gnu.org)\n\tby lists1p.gnu.org with esmtp (Exim 4.90_1)\n\t(envelope-from )\n\tid 1wKv5v-0005gy-DT; Thu, 07 May 2026 05:32:35 -0400","from eggs.gnu.org ([2001:470:142:3::10])\n by lists1p.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from )\n id 1wKv5t-0005eC-9J\n for qemu-devel@nongnu.org; Thu, 07 May 2026 05:32:33 -0400","from us-smtp-delivery-124.mimecast.com ([170.10.133.124])\n by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from )\n id 1wKv5r-0001jV-Dj\n for qemu-devel@nongnu.org; Thu, 07 May 2026 05:32:33 -0400","from mx-prod-mc-06.mail-002.prod.us-west-2.aws.redhat.com\n (ec2-35-165-154-97.us-west-2.compute.amazonaws.com [35.165.154.97]) by\n relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3,\n cipher=TLS_AES_256_GCM_SHA384) id us-mta-12-dVnQxGtIOH-Rp6y9xrPJmQ-1; Thu,\n 07 May 2026 05:32:25 -0400","from mx-prod-int-05.mail-002.prod.us-west-2.aws.redhat.com\n (mx-prod-int-05.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.17])\n (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest\n SHA256)\n (No client certificate requested)\n by mx-prod-mc-06.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS\n id 43EA418005B5; Thu, 7 May 2026 09:32:24 +0000 (UTC)","from redhat.com (unknown [10.44.49.217])\n by mx-prod-int-05.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with\n ESMTPS\n id E25D61953947; Thu, 7 May 2026 09:32:22 +0000 (UTC)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com;\n s=mimecast20190719; t=1778146350;\n h=from:from:reply-to:reply-to:subject:subject:date:date:\n message-id:message-id:to:to:cc:cc:mime-version:mime-version:\n content-type:content-type:\n content-transfer-encoding:content-transfer-encoding:\n in-reply-to:in-reply-to:references:references;\n bh=MIplG652C+44eNB8SHxgDXOIgZNYyLfTOoS35oSYyU0=;\n b=Cj7gqHVlC3U1CT4JTmpLDYSUPFfX2/e7vscNbpvG3/YpfwLF9vAinWFC9CCOr9Mui0Wb4Z\n k52EB2Rfz6Ll2h21WCayWMn98/pridV/DpvCXq1j64aW9e3eBsxuweYDoZ1Q2RekXzNIyS\n VPolXhP1314pUxfNd9e22k5sO66WFi8=","X-MC-Unique":"dVnQxGtIOH-Rp6y9xrPJmQ-1","X-Mimecast-MFC-AGG-ID":"dVnQxGtIOH-Rp6y9xrPJmQ_1778146344","Date":"Thu, 7 May 2026 10:32:19 +0100","From":"Daniel =?utf-8?b?UC4gQmVycmFuZ8Op?= ","To":"Philippe =?utf-8?q?Mathieu-Daud=C3=A9?= ","Cc":"Alex =?utf-8?q?Benn=C3=A9e?= ,\n qemu-devel@nongnu.org","Subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","Message-ID":"","References":"<20260505170105.228162-1-alex.bennee@linaro.org>\n <20260505170105.228162-9-alex.bennee@linaro.org>\n \n ","MIME-Version":"1.0","Content-Type":"text/plain; charset=utf-8","Content-Disposition":"inline","Content-Transfer-Encoding":"8bit","In-Reply-To":"","User-Agent":"Mutt/2.3.1 (2026-03-20)","X-Scanned-By":"MIMEDefang 3.0 on 10.30.177.17","Received-SPF":"pass client-ip=170.10.133.124;\n envelope-from=berrange@redhat.com;\n helo=us-smtp-delivery-124.mimecast.com","X-Spam_score_int":"-24","X-Spam_score":"-2.5","X-Spam_bar":"--","X-Spam_report":"(-2.5 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.443,\n DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1,\n RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H5=0.001, RCVD_IN_MSPIKE_WL=0.001,\n SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no","X-Spam_action":"no action","X-BeenThere":"qemu-devel@nongnu.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"qemu development ","List-Unsubscribe":",\n ","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n ","Reply-To":"Daniel =?utf-8?b?UC4gQmVycmFuZ8Op?= ","Errors-To":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org","Sender":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org"}},{"id":3687770,"web_url":"http://patchwork.ozlabs.org/comment/3687770/","msgid":"<87zf2bl7r8.fsf@draig.linaro.org>","list_archive_url":null,"date":"2026-05-07T12:32:59","subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","submitter":{"id":39532,"url":"http://patchwork.ozlabs.org/api/people/39532/","name":"Alex Bennée","email":"alex.bennee@linaro.org"},"content":"Daniel P. Berrangé writes:\n\n> On Tue, May 05, 2026 at 06:01:03PM +0100, Alex Bennée wrote:\n>> While triaging the issue tracker I wondered if this would be a\n>> suitable job for an AI agent. Unfortunately the OSS program doesn't\n>> give any credits to run agents in gitlab. However I do have access to\n>> models from my editor and ECA so I built one and tested it on a few\n>> issues.\n>> \n>> Obviously this can't apply as is because it probably encodes too much\n>> of my local setup (using pass for API keys) and uses the ECA as my\n>> preferred coding agent. I assume at some point there will be agreement\n>> between all the agents where skill live.\n>> \n>> Signed-off-by: Alex Bennée \n>\n> ..snip..\n>\n>> diff --git a/.agents/skills/qemu-issue-triage/assets/labels.txt\n>> b/.agents/skills/qemu-issue-triage/assets/labels.txt\n>> new file mode 100644\n>> index 00000000000..d329f34183d\n>> --- /dev/null\n>> +++ b/.agents/skills/qemu-issue-triage/assets/labels.txt\n>\n> Seeing our labels listed like this triggers my urge to \"tidy\" :-)\n>\n> Don't take anything below to be a complaint / blocker about this patch.\n> This patch is fine in so much as it faithfully represents the mess we\n> have created in gitlab.\n>\n>> @@ -0,0 +1,133 @@\n>> +# SPDX-License-Identifier: GPL-2.0-or-later\n>> +ACPI Power Management related (ACPI / SMBIOS / HEST / GHES)\n>> +Audio Audio devices; both backend (host audio) and frontend (guest\n>> audio)\n>\n> Mixing frontend and backend is a bad idea in general IMHO.\n>\n> I feel like we should also have an explicit label for each backend, for\n> both audio and every other backend type.\n\nBackend: chardev\nBackend: audio\n?\n\nI suspect the block backends are special enough they should stay part of\nblock: - what other backends do we have?\n\n>\n>> +Audit Tooling A group for bugs and issues found via automated\n>> tooling such as fuzzing, sanitizers or AI\n>> +Audit Tooling::AI For bugs found with AI assisted tools such as\n>> Mythos and other similar things\n>> +Audit Tooling::Fuzzer Issues found via fuzzing. For security\n>> issues, please consult\n>> https://www.qemu.org/contribute/security-process/\n>> +Audit Tooling::Sanitizer For issues found using sanitizers such as\n>> asan, lsan and tsan\n>\n> Labels with \"::\" are mutually exculsive, which is possibly not\n> what we want here ? Should the first thing be 'Audit Tooling::Other'\n> instead of unqualified ?\n\nI've added that, as well as Audit Tooling::Static Analysis for Coverity.\n\n>\n>> +Bite Sized Candidates for first contributions; see also\n>> https://wiki.qemu.org/Contribute/BiteSizedTasks\n>> +Build System configure, make, Meson, ninja, gcc, clang, ccache, etc.\n>> +CI Continuous Integration; gitlab, travis, patchew, etc.\n>> +CLI Command Line Interface\n>> +Chardev Character device backends and related issues\n>\n> We should have per-backend labels\n>\n>> +Closed::Duplicate There is already another ticket that is about the\n>> same issue\n>> +Closed::Fixed The issue was fixed. Yay!\n>> +Closed::Invalid This issue was not really a problem\n>> +Closed::NotOurBug This is a bug, but not a bug in QEMU. Please\n>> report it and/or include a link to the report.\n>> +Closed::NotReproducible This issue was not reproducible\n>> +Closed::UnbackedFeature Nobody was willing to work on this feature request\n>> +Closed::WontFix The issue was acknowledged, but the fix would be\n>> too complex, too expensive, or would introduce other problems.\n>> +Cryptography\n>> +Documentation Sphinx documentation, man pages, the wiki, --help\n>> output, etc.\n>> +GDB Issues relating to using GDB via the gdbstub\n>> +GUI Graphical User Interface (gtk, SDL, curses, VNC, spice, ...)\n>> +GUI::Cocoa Cocoa\n>> +GUI::DBus DBus\n>> +GUI::GTK\n>> +GUI::SDL SDL\n>> +GUI::SPICE SPICE\n>\n> spice is duplicated later\n\nPrompt: \"find all the issues with the \"spice\" label and label them with the GUI::SPICE label instead\"\n\nthe result was:\n\n general: relabling spice issues (5 steps, 13.5K / 1M) ✅ 1m 26s\n\n I have successfully relabeled all GitLab issues in the `qemu-project/qemu` repository by replacing the \"spice\" label with the \"GUI::SPICE\" label.\n\n ### Summary of Actions:\n - **Total Issues Updated**: 21 (including both open and closed issues).\n - **Relabeling**: Removed the `spice` label and applied the `GUI::SPICE` label to each identified issue.\n - **Verification**: Confirmed that `glab issue list --label spice` now returns no results, while `glab issue list --label \"GUI::SPICE\"` includes all updated issues.\n\n ### Updated Issues:\n The following 21 issues were updated: \n `3148`, `3070`, `2860`, `2667`, `2639`, `2561`, `2411`, `2335`, `2282`, `2071`, `1926`, `1829`, `1778`, `1777`, `1553`, `1549`, `1431`, `1426`, `1285`, `681`, `232`.\n\nabout 0.08p in inference costs.\n\n>\n>> +GUI::VNC\n>\n> I'd probably suggest \"ui\" as the prefix to match the dir / subsystem\n> name.\n>\n> Also probably use \":\" instead of \"::\" as there could be cases where\n> a bug affects multiple UIs.\n>\n>> +Guest Agent Issues related to the qemu-guest-agent binary.\n>> https://wiki.qemu.org/Features/GuestAgent\n>> +Hard\n\nI think there is 1 bug that is Hard.\n\n>> +Launchpad Issues migrated from Launchpad\n>> +Migration\n>\n> Surprised we don't want more categories here\n>\n>> +Modules\n>> +Networking\n>> +Python Python library issues (./python/)\n>> +QAPI/QMP QEMU API / QEMU Machine Protocol, HMP and CLI, etc.\n>> +QOM QEMU Object Model\n>> +Regression\n>> +Security\n>> +Semihosting Semihosting calls provide a simple ABI for early\n>> bring-up of embedded devices and provide a way to output to the\n>> console and do basic file i/o while being debugged\n>> +Softfloat QEMU's FPU emulation code (TCG only)\n>> +Stable::can't fix The bug was reported on a stable branch but the\n>> fix is too invasive for backporting\n>> +Stable::obsolete The bug was reported on a stable branch that is\n>> not maintained anymore\n>> +Stable::to backport The bug was reported on a stable branch and\n>> needs to be backported on the next release from the branch\n>> +Storage Block subsystem, Storage devices, etc.\n>> +TCG plugins Anything related to the TCG plugins feature\n>\n> Perhaps accel:tcg:plugins ?\n>\n\nPlugins currently implies accel:tcg but I'm not sure it is directly\naccelerator related. Some of the run-loop hooks are TCG agnostic.\n\n>> +TestCase The report includes a testcase\n>> +Tests qtests, iotests, acceptance tests, VM tests, docker tests,\n>> and more.\n>> +USB\n>> +VFIO\n>\n> This annoying sorting of all uppercase, then all lowercase is\n> present in the gitlab UI too\n>\n> https://gitlab.com/qemu-project/qemu/-/labels\n>\n> We should probalby be universally lowercase, so that sorting is\n> sensible.\n>\n>> +accel: HAX Intel's Hardware Accelerated Execution Manager (HAXM)\n>> +accel: HVF Apple Hypervisor Framework\n>> +accel: KVM Linux Kernel-based Virtual Machine\n>> +accel: TCG QEMU Tiny Code Generator\n>> +accel: WHPX Microsoft Windows Hypervisor Platform (WHPX)\n>> +accel: Xen Xen Hypervisor\n>\n> We're inconsistent in whether we use a space after \":\". Here we do,\n> below we don't.\n>\n>> +block:9p The 9p network file system\n>> +block:NVMe\n>\n> These two are not like the others under 'block:'. 'NVMe' is frontend device,\n> and 9p is a filesystem. I'd assume 'block:' applies to block/*.c\n>\n>> +block:curl\n>> +block:nbd\n>> +block:nfs Issues related to the NFS backend\n>> +block:qcow2\n>> +block:ssh\n>> +block:vmdk\n>\n> Probably want a \"block:core\" for stuff not specific to one of the listed\n> backends.\n\nI'll let the block guys fix this up.\n\n>\n>> +bsd-user\n>> +device: PCI\n>> +device: TPM Trusted Platform Module (TPM) devices\n>> +device:graphics Issues relating to display device emulation, or\n>> rendering in general. See also \"GUI\".\n>> +device:input Keyboards, Mice, Touchscreens, HIDs, etc.\n>> +device:iommu IOMMU and SMMU\n>> +device:pflash Parallel NOR flashes emulation\n>> +device:sdmmc SD or (e)MMC cards emulation\n>> +device:virtio virtio-related issues.\n>> https://www.linux-kvm.org/page/Virtio\n>> +device:watchdog\n>\n> Here we sometimes have a space after : and sometimes don't\n>\n>\n>> +efi EFI firmware related issues\n>> +flaky-ci For test cases that are flaky when run under our CI\n>> +gitlab\n>\n> So should we be using \"CI\" or \"gitlab\" for CI issues :)\n>\n> Probably we should have:\n>\n> ci:gitlab\n> ci:flaky\n>\n>> +guest: AIX\n>> +guest: BSD Guest OS is BSD (NetBSD/FreeBSD/OpenBSD/etc)\n>> +guest: Linux Guest OS is Linux/Linux-based\n>> +guest: Windows Microsoft Windows guest\n>> +guest: macOS Apple macOS / Darwin as guest OS\n>> +guest: os2\n>> +host: aarch64 Bugs reproducible on AArch64 hosts\n>> +host: arm Bugs reproducible on ARM hosts\n>> +host: loongarch64 Bugs reproducible on LoongArch64 hosts.\n>> +host: mips Bugs reproducible on MIPS hosts\n>> +host: ppc Bugs reproducible on Power hosts\n>> +host: riscv Bugs reproducible on RISC-V hosts\n>> +host: s390 Bugs reproducible on s390 hosts\n>> +host: sparc64 Bugs specific to Sparc64 hosts\n>> +host: x86 Bugs reproducible on x86 hosts\n>> +host:32bit These are mostly TCG related bugs where we sometimes\n>> struggle with emulating larger guests, especially atomic and address\n>> space issues.\n>\n> More space inconsistency\n>\n>> +hostos: BSD FreeBSD, OpenBSD, NetBSD, and derivatives as host OSes\n>> +hostos: Linux Linux-based host operating systems (Fedora,\n>> RHEL/CentOS, Debian, Ubuntu, openSuSE et al)\n>> +hostos: Windows Microsoft Windows host OS\n>> +hostos: macOS Apple macOS / Darwin as a host OS\n>> +icount issues relating to icount, deterministic execution and\n>> record/replay functionality\n>\n> Perhaps accel:tcg:icount ?\n>\n>> +kind: Not user visible\n>\n> What's this for, and why : instead of :: ?\n\nNo idea - is this the mechanism we use to hide live security issues?\n\n>\n>> +kind::Bug Bug or defect in functionality.\n>> +kind::Feature Request Feature request or new functionality.\n>> +kind::Task Research, investigations, and miscellaneous issues.\n>> +libvfio-user\n>> +linux-user\n>> +qemu-img\n>\n> Should we have a \"tools:qemu-img\", and \"tools:....\" for everything\n> else too ?\n>\n>> +spice\n>\n> Redundant with 'GUI::SPICE\"\n>\n>> +sysadmin\n>\n> Any idea what this is supposed to refer to ?\n\nthere is one issue where CI runs fail on some runners and not others. I\nadded some flavour text.\n\n>\n>> +target: alpha DEC Alpha [alpha]\n>> +target: arm Arm AArch32 or AArch64 [arm, aarch64]\n>> +target: avr Atmel AVR [avr]\n>> +target: hexagon Qualcomm Hexagon [hexagon]\n>> +target: hppa Hewlett-Packard Precision Architecture; HP/HP, PA-RISC\n>> [hppa]\n>> +target: i386 Intel/AMD x86 [i386, x86_64]\n>> +target: loongarch loongarch64 target architecture\n>> +target: m68k Motorola 68000 [m68k]\n>> +target: microblaze Xilinx MicroBlaze [microblaze, microblazeel]\n>> +target: mips MIPS [mips, mipsel, mips64, mips64el]\n>> +target: nios2 Altera Nios II [nios2]\n>> +target: openrisc OpenRISC [or1k]\n>> +target: ppc IBM Power Architecture, PowerPC [ppc, ppc64, ppc64le]\n>> +target: riscv RISC-V [riscv32, riscv64]\n>> +target: rx Renesas RX [rx]\n>> +target: s390x IBM Z, SystemZ, zSeries [s390x]\n>> +target: sh4 Renesas SuperH [sh4, sh4eb]\n>> +target: sparc Sun Microsystems SPARC [sparc, sparc64]\n>> +target: tricore Infineon TriCore [tricore]\n>> +target: xtensa Tensilica Xtensa [xtensa, xtensaeb]\n>> +workflow::Confirmed Bugs that have been confirmed and reproduced.\n>> +workflow::In Progress Someone is working on this issue.\n>> +workflow::Needs Info Issue has insufficient information to verify.\n>> +workflow::Patch available A patch is available\n>> +workflow::Triaged Issue has been triaged and given a topic label.\n>\n>\n> With regards,\n> Daniel","headers":{"Return-Path":"","X-Original-To":"incoming@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=pass (2048-bit key;\n unprotected) header.d=linaro.org header.i=@linaro.org header.a=rsa-sha256\n header.s=google header.b=pwPHyoLR;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=nongnu.org\n (client-ip=209.51.188.17; helo=lists1p.gnu.org;\n envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org;\n receiver=patchwork.ozlabs.org)"],"Received":["from lists1p.gnu.org (lists1p.gnu.org [209.51.188.17])\n\t(using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits))\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4gBBWS3kMsz1y04\n\tfor ; Thu, 07 May 2026 22:33:54 +1000 (AEST)","from localhost ([::1] helo=lists1p.gnu.org)\n\tby lists1p.gnu.org with esmtp (Exim 4.90_1)\n\t(envelope-from )\n\tid 1wKxue-0006Mh-HQ; Thu, 07 May 2026 08:33:08 -0400","from eggs.gnu.org ([2001:470:142:3::10])\n by lists1p.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from )\n id 1wKxuc-0006MF-C8\n for qemu-devel@nongnu.org; Thu, 07 May 2026 08:33:06 -0400","from mail-wm1-x32d.google.com ([2a00:1450:4864:20::32d])\n by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128)\n (Exim 4.90_1) (envelope-from )\n id 1wKxuZ-0001jL-Qs\n for qemu-devel@nongnu.org; Thu, 07 May 2026 08:33:06 -0400","by mail-wm1-x32d.google.com with SMTP id\n 5b1f17b1804b1-488b0e1b870so11678975e9.2\n for ; Thu, 07 May 2026 05:33:03 -0700 (PDT)","from draig.lan ([185.124.0.195]) by smtp.gmail.com with ESMTPSA id\n 5b1f17b1804b1-48e530d8691sm86634235e9.2.2026.05.07.05.33.00\n (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256);\n Thu, 07 May 2026 05:33:00 -0700 (PDT)","from draig (localhost [IPv6:::1])\n by draig.lan (Postfix) with ESMTP id 85B625F870;\n Thu, 07 May 2026 13:32:59 +0100 (BST)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=linaro.org; s=google; t=1778157181; x=1778761981; darn=nongnu.org;\n h=content-transfer-encoding:mime-version:message-id:date:user-agent\n :references:in-reply-to:subject:cc:to:from:from:to:cc:subject:date\n :message-id:reply-to;\n bh=AtI/Qwg/QafoL2lal9Xw/KFCmVwmBYPmxmbKF0CMwdU=;\n b=pwPHyoLRlbBMlKDqeQSZDMJLzw6FmRON3FI/23q8l+2o2SVqMFI20CdxTR7begnf+f\n j6mBwrq9/rajutm//7icU6v7IuV50VQseIinYVpv4JRkzb31yAx+60C5VxISf54eKGEj\n uauaL21jVJcLu7pDTDgDU4X0NaEkCiwDhBvx8de18k4Ww9dDLVDlWHfaKaMnkGHvhuIF\n okvwvBIhpakDIcHVSmkNlRJNhy/eM6mfQ9jXDWdf9eESSqjZ2oZ0qgD8w93HFLPFMCes\n JWezQqZJjxH9yHJ4bdEAlbcWiIwdzlDhqDM2al2txRiegSiR4Z4jkIhwCPTR+N4NLJt7\n SkWQ==","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1778157181; x=1778761981;\n h=content-transfer-encoding:mime-version:message-id:date:user-agent\n :references:in-reply-to:subject:cc:to:from:x-gm-gg\n :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to;\n bh=AtI/Qwg/QafoL2lal9Xw/KFCmVwmBYPmxmbKF0CMwdU=;\n b=fUm67sDgZwRMTiDyTrp9qru+vJ/xKrCRcT/oQXBVRWkkqRv9wgKsZSDM2QvSeF/8Vy\n hq7CcPCt0OSgW1W3OI3clw2ynzYYj/dNjo3avrFZ4mnYLOPciHURhmNvIbJBiN/K+qF8\n 2dbY2zjgduinfcva6Y4Annaa8evC21Iw59Ae+do0q8HqADUR5g/2xrXEqMYibDYdwGXJ\n 12b0kfdjV9VJTAa94Ab68PIV7Kf6qULYXhzO4O5LDQ1bLblnXANQnX+od382IyWlxXJV\n dSiWeh6x2EaxFkt0cSD40xjfZmdE5Wi+tRpXzkXSsDIV0kqQ1x/cZHxUcnEzQKLrN3ne\n u0xg==","X-Gm-Message-State":"AOJu0Yw2uhvRj5uWkMt6BkuPgLp1T4FT2UXU1xRe7xJImubTzX1ZEiP9\n BQRgJ02exsgZbSm9nj4wnvYBGUsjg9uN4YMCVZ+zYUaY84hHHC4s9m2IiXDGRKArQgJDs93LWF1\n hKlQsu3o=","X-Gm-Gg":"AeBDiet56xaf7yLYYSvCG6sYjid7sZvzSKl+DD4hdwn9o/r+DPryDVy1stygVabJ+pV\n AtPo1LFqwnbKGe0ZzUoNx1LkE3FzJIkQUjWea1esU1D58j/h9DalIldJrERbP+d/fzA0ptpJLVu\n WRq4W6KUdni/oXsVetU8ieLGAqjOWqaspdxhBkDvPxKPB4nIHYyhuoGbX5iTFfWGrcZEfPVYLkI\n xTy0y4BvDnDlmfsrsTBs0YUf+YGay5md4DfEfE8QfjaJ/q8m6DV+Q0a0sc+XtEKxnFweZ1gkxBQ\n ejeq3mzOhV+WZWhwCQHFOuur5Emc3VDVcDjFuVjwS/k1aTU6P75Q/ZnAXmxZ5IuoF14OKiLRDeL\n 4TIX/1Ud87+GI21QT8iG95HIpQrlxcYCMHxzxdY4V+MeV0yK65CucBn2eg6SjLuazgO2rHjHO8Q\n KF/5x4oBr3wFalNM5Zq7nWIRUjWPwV9EpO6A==","X-Received":"by 2002:a05:600c:4e0c:b0:48d:46a:6e5b with SMTP id\n 5b1f17b1804b1-48e51e19110mr140221295e9.7.1778157181249;\n Thu, 07 May 2026 05:33:01 -0700 (PDT)","From":"=?utf-8?q?Alex_Benn=C3=A9e?= ","To":"Daniel P. =?utf-8?b?QmVycmFuZ8Op?= ","Cc":"qemu-devel@nongnu.org","Subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","In-Reply-To":" (\"Daniel P. =?utf-8?b?QmVycmFu?=\n\t=?utf-8?b?Z8OpIidz?= message of \"Thu, 7 May 2026 09:25:45 +0100\")","References":"<20260505170105.228162-1-alex.bennee@linaro.org>\n <20260505170105.228162-9-alex.bennee@linaro.org>\n ","User-Agent":"mu4e 1.14.1; emacs 30.1","Date":"Thu, 07 May 2026 13:32:59 +0100","Message-ID":"<87zf2bl7r8.fsf@draig.linaro.org>","MIME-Version":"1.0","Content-Type":"text/plain; charset=utf-8","Content-Transfer-Encoding":"quoted-printable","Received-SPF":"pass client-ip=2a00:1450:4864:20::32d;\n envelope-from=alex.bennee@linaro.org; helo=mail-wm1-x32d.google.com","X-Spam_score_int":"-20","X-Spam_score":"-2.1","X-Spam_bar":"--","X-Spam_report":"(-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1,\n DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1,\n RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001,\n SPF_PASS=-0.001 autolearn=ham autolearn_force=no","X-Spam_action":"no action","X-BeenThere":"qemu-devel@nongnu.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"qemu development ","List-Unsubscribe":",\n ","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n ","Errors-To":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org","Sender":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org"}},{"id":3687784,"web_url":"http://patchwork.ozlabs.org/comment/3687784/","msgid":"","list_archive_url":null,"date":"2026-05-07T12:59:54","subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","submitter":{"id":5111,"url":"http://patchwork.ozlabs.org/api/people/5111/","name":"Peter Maydell","email":"peter.maydell@linaro.org"},"content":"On Thu, 7 May 2026 at 13:33, Alex Bennée wrote:\n>\n> Daniel P. Berrangé writes:\n>\n> > On Tue, May 05, 2026 at 06:01:03PM +0100, Alex Bennée wrote:\n> >> +kind: Not user visible\n> >\n> > What's this for, and why : instead of :: ?\n>\n> No idea - is this the mechanism we use to hide live security issues?\n\nNo, that's separate (and generally we don't use it at all,\nso the only reason for a gitlab issue being \"confidential\"\nis that the submitter didn't read our policy on how to\nsubmit potential security issues, or misunderstood what\ngitlab's \"mark issue as confidential\" UI was for).\n\nThis label has no current issues, but I think the intent was\nto mark \"this is technically a bug, but in practice it doesn't\naffect any users because it's masked by other things or because\nno calling code uses the buggy bit of this function, or whatever\".\n\nSince it's unused, we could just delete the label.\n\nthanks\n-- PMM","headers":{"Return-Path":"","X-Original-To":"incoming@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=pass (2048-bit key;\n unprotected) header.d=linaro.org header.i=@linaro.org header.a=rsa-sha256\n header.s=google header.b=m8I4ydRG;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=nongnu.org\n (client-ip=209.51.188.17; helo=lists1p.gnu.org;\n envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org;\n receiver=patchwork.ozlabs.org)"],"Received":["from lists1p.gnu.org (lists1p.gnu.org [209.51.188.17])\n\t(using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits))\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4gBC6X0q3yz1y04\n\tfor ; Thu, 07 May 2026 23:00:50 +1000 (AEST)","from localhost ([::1] helo=lists1p.gnu.org)\n\tby lists1p.gnu.org with esmtp (Exim 4.90_1)\n\t(envelope-from )\n\tid 1wKyKs-0003IC-3H; Thu, 07 May 2026 09:00:15 -0400","from eggs.gnu.org ([2001:470:142:3::10])\n by lists1p.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from )\n id 1wKyKn-0003HX-OJ\n for qemu-devel@nongnu.org; Thu, 07 May 2026 09:00:09 -0400","from mail-yx1-xb134.google.com ([2607:f8b0:4864:20::b134])\n by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_128_GCM_SHA256:128)\n (Exim 4.90_1) (envelope-from )\n id 1wKyKl-0001P0-Ms\n for qemu-devel@nongnu.org; Thu, 07 May 2026 09:00:09 -0400","by mail-yx1-xb134.google.com with SMTP id\n 956f58d0204a3-65d071aac6eso676902d50.0\n for ; Thu, 07 May 2026 06:00:06 -0700 (PDT)"],"ARC-Seal":"i=1; a=rsa-sha256; t=1778158806; cv=none;\n d=google.com; s=arc-20240605;\n b=EfozV2+uQdi94mAYMakhcU8Yk5LuFbcIMZad1Hyf5Np3Yg/U4G0Sj/R/gwN6tn+Q4V\n TUZro3GFxpxpmLZDrWSzxfM2ALutvrH22g45ihQpZ6bj+lM9YHwutxtgMqtwwtsYbj3e\n 3w4OkMiXTDnRCg9zB/kYM98Gocxabdhyfm/LlfGeXgNI1gApsMG72t2RfNBdilMm2W0B\n LKI5VMzYqPfA+Rj4IZfhrb2FUlHw3xXsb9cUeX6+mF5OeQmydmybIkyYjLpzkNwMCQ0J\n vwiuWX6Y5DWDiZ/7JLi7boHunByLsjWGhCtuqCIEfBWvxe3wnFIvYx8vFvQvjZmp4ze6\n S9ew==","ARC-Message-Signature":"i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com;\n s=arc-20240605;\n h=content-transfer-encoding:cc:to:subject:message-id:date:from\n :in-reply-to:references:mime-version:dkim-signature;\n bh=tdYXwji1sz9BqZ3nJqTK/y4jhXnBdMm7sbEKyfx3W/U=;\n fh=ZUR3al20C4uS0IK46eApU2WIKvkUU47arxKUvA0VfwI=;\n b=gDlGt5rHh6gGXGJazC9zqrbahypGV+e+SO7wfeyvEOXVJ7nhoYWWXDYhHEYBZ28wbJ\n /UIwcGEhQ3eE2UGpZZTa0BLI4I0ccFqluLmzBe3Jw6VqM5ZxKqjp+4TH45+qphS/I/0e\n 7VJtkKdeeS0iBODx3TcjGk7Lk1tc/zvhV2UQwwEPVrnhAcT0+XWx9YXxBAplSdh7zmo8\n hzr0TBeONq5Tw5TQJiHSB4O5Rq2MncU8WQMyuVz5AAY3nuppUPC+fk0el5BCO43/xKQ6\n bU7S9PqwCXzaovNr1oVUduHZuhsqVcdNeHXadTEHUhor3RCtTHMEkKuWBYd0GD4BHffF\n QjZA==; darn=nongnu.org","ARC-Authentication-Results":"i=1; mx.google.com; arc=none","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=linaro.org; s=google; t=1778158806; x=1778763606; darn=nongnu.org;\n h=content-transfer-encoding:cc:to:subject:message-id:date:from\n :in-reply-to:references:mime-version:from:to:cc:subject:date\n :message-id:reply-to;\n bh=tdYXwji1sz9BqZ3nJqTK/y4jhXnBdMm7sbEKyfx3W/U=;\n b=m8I4ydRGXocxM9lS3tPcueNtobE4rVIDpTrbKieFiRWDg87bS/nHoVqPPrvk2mWzha\n jYZp+V10bLeg+Gj8fhH0xCq7OG1IPmmE5ntDxTpwgtcaFVqAvGQJhZV2GrVVru8lAs5l\n 0NwAiaB7M9MRNBZLdy5qH+BJJm9tL+zjBwZFXBwgFTb8O07ZddR06GfHWnRJnJIzn3F9\n nki0oDwN9OtPc5nAVRGhFLOe9brWhrQi95n+jSyNeSwaYsdk+0XeiF+InD6bMGPJ02H3\n Unh3soGJPGvsDrBxf53ZWaJ+Wyf3CO8x9Sie/aM+KUQy0oMgVt2r7W7kdmuGytTcT3p9\n mOOQ==","X-Google-DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20251104; t=1778158806; x=1778763606;\n h=content-transfer-encoding:cc:to:subject:message-id:date:from\n :in-reply-to:references:mime-version:x-gm-gg:x-gm-message-state:from\n :to:cc:subject:date:message-id:reply-to;\n bh=tdYXwji1sz9BqZ3nJqTK/y4jhXnBdMm7sbEKyfx3W/U=;\n b=j0Cok96fbh1BU5V9VjmhnfUbHExaF5PRESMHchMS4rGO7OZ5179p45hA94UtNXk8bA\n cxizdqxUyEDRU9DxQoepIUztRXcEocJV6FzkagUHSOLO89q4vu5f4sxV1hmZaVFDjicV\n j8raZpTeVeYuhJTlTya1cDlhf/vRZMcu5nPyf2xE+sb8TXbguJ+8h0Nvgu6SLQZU1ICF\n TbP+mNTGtR/z0Nr98Orl2SeLMTvaTcmjhq4cEIdPF+O4S9oUthOJkTq7bnst0HVnPpc/\n o/5mN+BRJHnT6IfAt/smWc7zblocdoMwavmOuZuMVfRkREaeg9ObzNn05l3dBEaJlt1N\n 1nDQ==","X-Forwarded-Encrypted":"i=1;\n AFNElJ8Wz/P8extYNwTBlCabXGFEsa05p84u9O9Ec2Zr+3xo1kI6Ftq1BHaPXmmXiSNwgBpiF3hmn6vZz61K@nongnu.org","X-Gm-Message-State":"AOJu0YwBKTEy2rngMvbxH7PK0job6HK5yT7NcyeXPotCVlnmgGId+o+7\n GLf7uBs3r+Onck/hJHYBKDA1VUvd6PKsW7lWtLxG27QA6noEKjMNgSkQo1y6Uskn7r1AgIp2+Xw\n DrqHYB2ySxQYDwSg+Hh3xeudPdz7JqwTqHpyL861GeA==","X-Gm-Gg":"Acq92OEMpuXJSUnFrCPY4TqTXPp8eTU6mvxDHTmPm97R4h3qXDuxsarKUHlVkpBzWBz\n jJhafuVSRHvpZzjZIV7sZMUDUH4l+63bLL1XYBj0mxSjUM0+fLKU3S3auTXsQS6MQABQ/FkCcGV\n kopcJSciH1MVLdur6NgGino95mzlHqbQiA+LlTc0TcsoEMiwzEPsNMNdnDbYL4e01kuNmGAg/zW\n ecACitKxPZDO8eVtsSXsHJG4GS690133QoAXxWaF51IZQv7hAkGULJh0eL9Xfk5t3xdeILHcqeT\n lKCvjJnavFVvZEyNhS9XIDbYioPXijFa+QMUhh7SvLzekl49Dhhl9ihTGZJtO8SsMkfdNcs/9j6\n Kbg==","X-Received":"by 2002:a05:690e:1449:b0:650:3b84:c250 with SMTP id\n 956f58d0204a3-65c79ad52b6mr7713559d50.2.1778158805428; Thu, 07 May 2026\n 06:00:05 -0700 (PDT)","MIME-Version":"1.0","References":"<20260505170105.228162-1-alex.bennee@linaro.org>\n <20260505170105.228162-9-alex.bennee@linaro.org>\n \n <87zf2bl7r8.fsf@draig.linaro.org>","In-Reply-To":"<87zf2bl7r8.fsf@draig.linaro.org>","From":"Peter Maydell ","Date":"Thu, 7 May 2026 13:59:54 +0100","X-Gm-Features":"AVHnY4JnQEqMVLnZrIZCeNQs_QBFsgflMTRTaawEsSe1MtgF2GDnY9G3qQhd8sU","Message-ID":"\n ","Subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","To":"=?utf-8?q?Alex_Benn=C3=A9e?= ","Cc":"=?utf-8?q?Daniel_P=2E_Berrang=C3=A9?= ,\n qemu-devel@nongnu.org","Content-Type":"text/plain; charset=\"UTF-8\"","Content-Transfer-Encoding":"quoted-printable","Received-SPF":"pass client-ip=2607:f8b0:4864:20::b134;\n envelope-from=peter.maydell@linaro.org; helo=mail-yx1-xb134.google.com","X-Spam_score_int":"-20","X-Spam_score":"-2.1","X-Spam_bar":"--","X-Spam_report":"(-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1,\n DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1,\n RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001,\n SPF_PASS=-0.001 autolearn=ham autolearn_force=no","X-Spam_action":"no action","X-BeenThere":"qemu-devel@nongnu.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"qemu development ","List-Unsubscribe":",\n ","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n ","Errors-To":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org","Sender":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org"}},{"id":3687827,"web_url":"http://patchwork.ozlabs.org/comment/3687827/","msgid":"","list_archive_url":null,"date":"2026-05-07T13:46:30","subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","submitter":{"id":2694,"url":"http://patchwork.ozlabs.org/api/people/2694/","name":"Daniel P. Berrangé","email":"berrange@redhat.com"},"content":"On Thu, May 07, 2026 at 01:32:59PM +0100, Alex Bennée wrote:\n> Daniel P. Berrangé writes:\n> \n> > On Tue, May 05, 2026 at 06:01:03PM +0100, Alex Bennée wrote:\n> >> While triaging the issue tracker I wondered if this would be a\n> >> suitable job for an AI agent. Unfortunately the OSS program doesn't\n> >> give any credits to run agents in gitlab. However I do have access to\n> >> models from my editor and ECA so I built one and tested it on a few\n> >> issues.\n> >> \n> >> Obviously this can't apply as is because it probably encodes too much\n> >> of my local setup (using pass for API keys) and uses the ECA as my\n> >> preferred coding agent. I assume at some point there will be agreement\n> >> between all the agents where skill live.\n> >> \n> >> Signed-off-by: Alex Bennée \n> >\n> > ..snip..\n> >\n> >> diff --git a/.agents/skills/qemu-issue-triage/assets/labels.txt\n> >> b/.agents/skills/qemu-issue-triage/assets/labels.txt\n> >> new file mode 100644\n> >> index 00000000000..d329f34183d\n> >> --- /dev/null\n> >> +++ b/.agents/skills/qemu-issue-triage/assets/labels.txt\n> >\n> > Seeing our labels listed like this triggers my urge to \"tidy\" :-)\n> >\n> > Don't take anything below to be a complaint / blocker about this patch.\n> > This patch is fine in so much as it faithfully represents the mess we\n> > have created in gitlab.\n> >\n> >> @@ -0,0 +1,133 @@\n> >> +# SPDX-License-Identifier: GPL-2.0-or-later\n> >> +ACPI Power Management related (ACPI / SMBIOS / HEST / GHES)\n> >> +Audio Audio devices; both backend (host audio) and frontend (guest\n> >> audio)\n> >\n> > Mixing frontend and backend is a bad idea in general IMHO.\n> >\n> > I feel like we should also have an explicit label for each backend, for\n> > both audio and every other backend type.\n> \n> Backend: chardev\n> Backend: audio\n> ?\n\nNo sorry, I meant chardev:socket, chardev:stdio, chardev:mux, etc and\naudio:dsound, audio:alsa, audio:pa, etc\n\n\n> >> +GUI Graphical User Interface (gtk, SDL, curses, VNC, spice, ...)\n> >> +GUI::Cocoa Cocoa\n> >> +GUI::DBus DBus\n> >> +GUI::GTK\n> >> +GUI::SDL SDL\n> >> +GUI::SPICE SPICE\n> >\n> > spice is duplicated later\n> \n> Prompt: \"find all the issues with the \"spice\" label and label them with the GUI::SPICE label instead\"\n> \n> the result was:\n> \n> general: relabling spice issues (5 steps, 13.5K / 1M) ✅ 1m 26s\n> \n> I have successfully relabeled all GitLab issues in the `qemu-project/qemu` repository by replacing the \"spice\" label with the \"GUI::SPICE\" label.\n> \n> ### Summary of Actions:\n> - **Total Issues Updated**: 21 (including both open and closed issues).\n> - **Relabeling**: Removed the `spice` label and applied the `GUI::SPICE` label to each identified issue.\n> - **Verification**: Confirmed that `glab issue list --label spice` now returns no results, while `glab issue list --label \"GUI::SPICE\"` includes all updated issues.\n> \n> ### Updated Issues:\n> The following 21 issues were updated: \n> `3148`, `3070`, `2860`, `2667`, `2639`, `2561`, `2411`, `2335`, `2282`, `2071`, `1926`, `1829`, `1778`, `1777`, `1553`, `1549`, `1431`, `1426`, `1285`, `681`, `232`.\n> \n> about 0.08p in inference costs.\n> \n\n> > What's this for, and why : instead of :: ?\n> \n> No idea - is this the mechanism we use to hide live security issues?\n\nsecurity issues should not be in the issue tracker at all\n\nWith regards,\nDaniel","headers":{"Return-Path":"","X-Original-To":"incoming@patchwork.ozlabs.org","Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=pass (1024-bit key;\n unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256\n header.s=mimecast20190719 header.b=aAdEbhFa;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=nongnu.org\n (client-ip=209.51.188.17; helo=lists1p.gnu.org;\n envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org;\n receiver=patchwork.ozlabs.org)"],"Received":["from lists1p.gnu.org (lists1p.gnu.org [209.51.188.17])\n\t(using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits))\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4gBD8N5SQqz1y04\n\tfor ; Thu, 07 May 2026 23:47:31 +1000 (AEST)","from localhost ([::1] helo=lists1p.gnu.org)\n\tby lists1p.gnu.org with esmtp (Exim 4.90_1)\n\t(envelope-from )\n\tid 1wKz40-0007m1-5M; Thu, 07 May 2026 09:46:52 -0400","from eggs.gnu.org ([2001:470:142:3::10])\n by lists1p.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from )\n id 1wKz3v-0007lo-Vu\n for qemu-devel@nongnu.org; Thu, 07 May 2026 09:46:51 -0400","from us-smtp-delivery-124.mimecast.com ([170.10.133.124])\n by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256)\n (Exim 4.90_1) (envelope-from )\n id 1wKz3s-0004Nc-EU\n for qemu-devel@nongnu.org; Thu, 07 May 2026 09:46:46 -0400","from mx-prod-mc-05.mail-002.prod.us-west-2.aws.redhat.com\n (ec2-54-186-198-63.us-west-2.compute.amazonaws.com [54.186.198.63]) by\n relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3,\n cipher=TLS_AES_256_GCM_SHA384) id us-mta-676-cSIPaSaYNxysqQiKCGDPpg-1; Thu,\n 07 May 2026 09:46:36 -0400","from mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com\n (mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.4])\n (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest\n SHA256)\n (No client certificate requested)\n by mx-prod-mc-05.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS\n id 253D8195608F; Thu, 7 May 2026 13:46:35 +0000 (UTC)","from redhat.com (unknown [10.44.49.217])\n by mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with\n ESMTPS\n id D497F3002D2D; Thu, 7 May 2026 13:46:33 +0000 (UTC)"],"DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com;\n s=mimecast20190719; t=1778161602;\n h=from:from:reply-to:reply-to:subject:subject:date:date:\n message-id:message-id:to:to:cc:cc:mime-version:mime-version:\n content-type:content-type:\n content-transfer-encoding:content-transfer-encoding:\n in-reply-to:in-reply-to:references:references;\n bh=3e8whisJbGatF2J9EbfyEEDqgIE2ddle93Z9OmMAF3U=;\n b=aAdEbhFaY4sz3E9/scpy9cbvl3q6qRxzJcqCJ/B0EckvqeGxIgvdDx3YHyQOqhrW+C7cbQ\n tALRAeY9jt8ySQluWn7urI0btTTWS0HE2io4T4hR6eMY4ptdkLL0m/zkWXPxW4eyyr1IhR\n WcfuCAmmQpGCPw1t4dgcRyA0/nyhOQQ=","X-MC-Unique":"cSIPaSaYNxysqQiKCGDPpg-1","X-Mimecast-MFC-AGG-ID":"cSIPaSaYNxysqQiKCGDPpg_1778161595","Date":"Thu, 7 May 2026 14:46:30 +0100","From":"Daniel =?utf-8?b?UC4gQmVycmFuZ8Op?= ","To":"Alex =?utf-8?q?Benn=C3=A9e?= ","Cc":"qemu-devel@nongnu.org","Subject":"Re: [RFC PATCH 08/10] .agents/skills: add qemu-issue-triage agent\n skill","Message-ID":"","References":"<20260505170105.228162-1-alex.bennee@linaro.org>\n <20260505170105.228162-9-alex.bennee@linaro.org>\n <87zf2bl7r8.fsf@draig.linaro.org>","MIME-Version":"1.0","Content-Type":"text/plain; charset=utf-8","Content-Disposition":"inline","Content-Transfer-Encoding":"8bit","In-Reply-To":"<87zf2bl7r8.fsf@draig.linaro.org>","User-Agent":"Mutt/2.3.1 (2026-03-20)","X-Scanned-By":"MIMEDefang 3.4.1 on 10.30.177.4","Received-SPF":"pass client-ip=170.10.133.124;\n envelope-from=berrange@redhat.com;\n helo=us-smtp-delivery-124.mimecast.com","X-Spam_score_int":"8","X-Spam_score":"0.8","X-Spam_bar":"/","X-Spam_report":"(0.8 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.438,\n DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1,\n RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H5=0.001, RCVD_IN_MSPIKE_WL=0.001,\n RCVD_IN_SBL_CSS=3.335, SPF_HELO_PASS=-0.001,\n SPF_PASS=-0.001 autolearn=no autolearn_force=no","X-Spam_action":"no action","X-BeenThere":"qemu-devel@nongnu.org","X-Mailman-Version":"2.1.29","Precedence":"list","List-Id":"qemu development ","List-Unsubscribe":",\n ","List-Archive":"","List-Post":"","List-Help":"","List-Subscribe":",\n ","Reply-To":"Daniel =?utf-8?b?UC4gQmVycmFuZ8Op?= ","Errors-To":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org","Sender":"qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org"}}]