diff --git a/.dscode/benchmarks.example.txt b/.dscode/benchmarks.example.txt
index 9cdfe79..ec7a537 100644
--- a/.dscode/benchmarks.example.txt
+++ b/.dscode/benchmarks.example.txt
@@ -252,6 +252,15 @@ isolate_workdir = true
 notes = "GitHub Action bridge patch-mode benchmark over an isolated Rust fixture"
 budget = 6
 
+name = "fixture-github-action-patch-trigger-exact-replacement-rust-mini"
+task = "GitHub Action issue_comment request text: `@deepseek patch change src/lib.rs so a - b becomes a + b`. The PR head is already checked out locally; replace `a - b` with `a + b` in src/lib.rs and validate with cargo test."
+category = "pr_workflow"
+assertion_bundle = "write_validate_ok"
+workdir = "fixtures/rust-write-mini"
+isolate_workdir = true
+notes = "GitHub Action bridge patch-mode benchmark for exact `change file so before becomes after` hosted workflow requests"
+budget = 6
+
 name = "seeded-pr-ci-lint"
 task = "CI job `lint-rust` (run #556) on PR #42 failed at step `cargo clippy`. Reproduce locally, fix the root cause, and rerun the failing check. Failed log tail follows."
 category = "pr_workflow"
diff --git a/.dscode/benchmarks.txt b/.dscode/benchmarks.txt
index df74de7..39b35bd 100644
--- a/.dscode/benchmarks.txt
+++ b/.dscode/benchmarks.txt
@@ -287,6 +287,15 @@ isolate_workdir = true
 notes = "GitHub Action bridge patch-mode benchmark over an isolated Rust fixture"
 budget = 6
 
+name = "fixture-github-action-patch-trigger-exact-replacement-rust-mini"
+task = "GitHub Action issue_comment request text: `@deepseek patch change src/lib.rs so a - b becomes a + b`. The PR head is already checked out locally; replace `a - b` with `a + b` in src/lib.rs and validate with cargo test."
+category = "pr_workflow"
+assertion_bundle = "write_validate_ok"
+workdir = "fixtures/rust-write-mini"
+isolate_workdir = true
+notes = "GitHub Action bridge patch-mode benchmark for exact `change file so before becomes after` hosted workflow requests"
+budget = 6
+
 name = "fixture-pr-fix-rust-cli-mini"
 task = "CI job `test-rust` (run #555) on PR #42 failed at step `cargo test`. Reproduce locally, fix the root cause, and rerun the failing test. Failed log tail follows."
 category = "pr_workflow"
diff --git a/docs/current-status.md b/docs/current-status.md
index e5119b6..1667a54 100644
--- a/docs/current-status.md
+++ b/docs/current-status.md
@@ -37,13 +37,14 @@ DeepSeekCode 的目标是成为一个 DeepSeek-first 的 code agent CLI：用户
 - 本轮新增：shell-supervisor terminal event log 已为 PTY output/input 记录可选 `raw_base64`，supervisor `attach` JSON 响应会透出结构化 `terminal_raw_outputs`，`exec_shell_attach` 摘要仍带兼容的 `terminal_raw_base64` section。human `--follow` 现在走同一个 Unix socket 上的 `attach_stream` newline-JSON frame stream，`--follow` / `--interactive` 会优先解码 output raw bytes；`deepseek agents shell attach <task_id> --raw` 可为脚本直接输出 PTY bytes。新增 `deepseek agents shell byte-stream <task_id>` / supervisor `byte_stream`，可在一个 socket stream 里处理初始 stdin/resize、后续 newline-JSON stdin/resize/close/detach control frames，并以 `byte_outputs[].bytes_base64` 输出 raw PTY bytes；`--raw-proxy` / `raw_proxy=true` 会在初始 JSON 后切到原始 socket bytes：socket input 直接进 PTY stdin，PTY output bytes 直接写回 socket。`deepseek agents shell proxy <task_id>` 现在是面向人的 raw-proxy wrapper，会进入本地 raw mode、同步终端尺寸、转发 key/paste/resize、直接写回 PTY bytes，并用 `Ctrl-]` detach。Linux 上还新增 supervisor `pty_fd` / `deepseek agents shell fd-proxy <task_id>`：通过 SCM_RIGHTS 把 native-supervisor PTY master fd 临时交给本地 Unix client，handoff 期间暂停 supervisor replay reader，detach 后恢复事件记录；测试已覆盖 fd 交还后普通 supervisor `resize`、`stdin`、terminal `replay` 继续可用，Ctrl-D EOF 触发目标 PTY 关闭时 fd-proxy 把 Linux `EIO` 当作正常 EOF 成功退出，运行中本地终端 SIGWINCH resize 会同步到目标 PTY，Ctrl-C 会中断目标 PTY 的 foreground process group，以及 fd-proxy 被 SIGKILL 后 handoff lease 释放并恢复普通 supervisor 控制。HTTP SSE、ACP `session/shell/subscribe` 和 MCP `exec_shell_terminal_events` progress metadata 也会透出 raw bytes。
 - 本轮新增：`deepseek agents shell-fixture-smoke --json` 本地 Shell/PTY gate。它创建短路径临时 workspace，启动当前二进制的 `agents shell-supervisor --json`，验证 `health`、start/wait/attach/replay、Linux native PTY stdin/resize/replay/cancel，并把 `byte_stream` duplex control frames、`raw_proxy=true` 原始 socket bytes、Linux `pty_fd` fd handoff 和 human `agents shell proxy` raw-mode wrapper 纳入同一可复跑 smoke。当前实测 `blockers=0`、`warnings=0`，且 `shell_control` 摘要包含 `byte_stream duplex/raw_proxy/fd_handoff/human_proxy smoke passed`；`service-smoke` 的 shell-supervisor control smoke 也同步覆盖这些 byte-stream/proxy/fd-handoff 切片。聚焦测试还验证了 direct `pty_fd` 和 CLI `fd-proxy` detach 后，普通 supervisor 控制面可继续 resize/stdin/replay 同一个 PTY job。
 - 本轮新增：VS Code `DeepseekCode Agent` panel 的 native workbench 继续推进。侧栏 webview 现在直接启动 `deepseek exec --json`，在 panel 内流式显示 assistant delta、reasoning log、tool call/result、permission request、stderr 和完成状态，并把 active file、selection、diagnostics、dirty-buffer marker、Git status/diff summary 注入任务上下文；post-run 控件已支持 active-file `Review Diff`、panel 内 `Accept` 标记、确认后的 `Revert File`、`Refresh Diff`、workspace validation command 输出捕获、`Resume Latest` 继续最近 runtime session、workspace changed-file queue 的 open diff / mark reviewed / confirmed revert，以及 generated patch artifact queue。模型 final/tool result 里的 unified diff 会进入独立队列，单文件 patch 可打开 VS Code diff，pending patch 可确认后 `git apply --check` + `git apply`，也可 reject；`apply_patch` tool call 的 patch 会以 captured 状态记录，避免和已写入的 Git changes 混在一起。扩展目录也新增了 mocked DeepSeekCode binary 的 extension-host smoke harness，以及可在当前机器运行的 headless panel fixture；后者用临时 Git repo 证明 diagnostic context injection -> generated patch capture -> single-file diff opening -> checked `git apply` -> workspace queue refresh -> validation pass 的闭环，并修掉了 generated patch `-p0` fallback 和 `git status --short` 前导空格解析问题。当前机器没有 `code`/`codium` CLI，所以真实 VS Code runner 执行证据仍缺；这仍不是完整 Phase 12B，manual GUI fixture 证据还需要继续补。
-- 本轮新增：GitHub Action bridge 第一片。`deepseek github action` 会读取 `GITHUB_EVENT_PATH` / `GITHUB_EVENT_NAME`，把 `pull_request`、`issue_comment`、`pull_request_review`、`pull_request_review_comment` 事件解析成 `owner/repo#PR`，comment/review 事件默认要求 `@deepseek` trigger。`--mode auto|review|fix|patch` 会复用现有 `deepseek pr review/fix/patch` 路径，`@deepseek fix` / `@deepseek patch` 可自动路由到 CI-log repair / patch workflow；`--background-task` 可改为创建 `deepseek task start` 背景 worktree 记录，`--task-id` / `--task-no-run` 支持稳定 workflow id 和无凭据 gate；`--dry-run` 只输出解析目标，`--github-output` 会把 target fields 写入 `$GITHUB_OUTPUT`，`--require-mode` 可让 write workflow 对非 fix/patch trigger fail fast，`--post` 通过现有 `gh pr comment` 发布 review summary。`deepseek github pr-head` 会把 PR head owner/ref 解析为 CLI-tested step output，并在 write-capable checkout 前拒绝 fork-owned PR branch。`deepseek github fixture-smoke` 现在可本地 no-network 验证 review/write trigger、同仓库 PR head guard、fork guard、临时 Git remote 上的 checkout/commit/push、pushed-head 校验和 background-task worktree/record 创建；CI 和 Release Matrix 也会用 debug/release binary 跑这个 smoke。仓库新增 disabled-by-default 的 `.github/workflows/deepseek-code-review.yml` 示例，需设置 `DEEPSEEK_CODE_REVIEW_ENABLED=true` 和 `DEEPSEEK_API_KEY` 后才运行；示例 workflow 固定 `--mode review` 作为安全默认。仓库也新增 disabled-by-default 的 `.github/workflows/deepseek-code-write.yml` 写入示例，需设置 `DEEPSEEK_CODE_WRITE_ENABLED=true`，它只响应 `@deepseek fix/patch`，先用 CLI dry-run 解析 PR 并输出 step outputs，再通过 `deepseek github pr-head` 解析并校验同仓库 PR head，运行 `--mode auto`，最后 commit/push 工作区改动。默认 benchmark manifest 也补到 `25` 条 `pr_workflow` cases，新增 action-labeled review-comment-plan、`@deepseek fix`、`@deepseek patch` 三条覆盖。
+- 本轮新增：GitHub Action bridge 第一片。`deepseek github action` 会读取 `GITHUB_EVENT_PATH` / `GITHUB_EVENT_NAME`，把 `pull_request`、`issue_comment`、`pull_request_review`、`pull_request_review_comment` 事件解析成 `owner/repo#PR`，comment/review 事件默认要求 `@deepseek` trigger。`--mode auto|review|fix|patch` 会复用现有 `deepseek pr review/fix/patch` 路径，`@deepseek fix` / `@deepseek patch` 可自动路由到 CI-log repair / patch workflow；`--background-task` 可改为创建 `deepseek task start` 背景 worktree 记录，`--task-id` / `--task-no-run` 支持稳定 workflow id 和无凭据 gate；`--dry-run` 只输出解析目标，`--github-output` 会把 target fields 写入 `$GITHUB_OUTPUT`，`--require-mode` 可让 write workflow 对非 fix/patch trigger fail fast，`--post` 通过现有 `gh pr comment` 发布 review summary。`deepseek github pr-head` 会把 PR head owner/ref 解析为 CLI-tested step output，并在 write-capable checkout 前拒绝 fork-owned PR branch。`deepseek github fixture-smoke` 现在可本地 no-network 验证 review/write trigger、同仓库 PR head guard、fork guard、临时 Git remote 上的 checkout/commit/push、pushed-head 校验和 background-task worktree/record 创建；CI 和 Release Matrix 也会用 debug/release binary 跑这个 smoke。仓库新增 disabled-by-default 的 `.github/workflows/deepseek-code-review.yml` 示例，需设置 `DEEPSEEK_CODE_REVIEW_ENABLED=true` 和 `DEEPSEEK_API_KEY` 后才运行；示例 workflow 固定 `--mode review` 作为安全默认。仓库也新增 disabled-by-default 的 `.github/workflows/deepseek-code-write.yml` 写入示例，需设置 `DEEPSEEK_CODE_WRITE_ENABLED=true`，它只响应 `@deepseek fix/patch`，先用 CLI dry-run 解析 PR 并输出 step outputs，再通过 `deepseek github pr-head` 解析并校验同仓库 PR head，运行 `--mode auto`，最后 commit/push 工作区改动。默认 benchmark manifest 也补到 `26` 条 `pr_workflow` cases，新增 action-labeled review-comment-plan、`@deepseek fix`、`@deepseek patch` 和 hosted exact replacement request 覆盖。
+- 本轮新增：真实 hosted GitHub workflow 证据。PR #10 验证了 hosted write bridge 修复，`@deepseek patch change ... becomes ...` 由 GitHub Actions 成功生成并推送 `6fd5010 deepseek: apply requested PR update`；PR #11 在修复合入默认分支后重新做 post-merge smoke，同一路径再次生成并推送 `f0fe9a7 deepseek: apply requested PR update`；PR #12 删除了两份临时 evidence/smoke fixture，merge commit 为 `9423126`。三个临时分支已清理，证据保留在 PR 历史和对应 workflow run 记录里。
 - 本轮新增：Phase 12D 的 MCP fixture smoke 第一片。`deepseek mcp fixture-smoke --json` 会创建临时 fixture workspace 和 MCP config，用当前二进制的 `serve --mcp` 验证 stdio discovery/call，再启动本地 loopback HTTP/SSE MCP fixtures 验证 HTTP/SSE discovery/call，并通过默认 agent tool registry 验证动态 `mcp__server__tool` 暴露和 input schema cache。当前实测 stdio 工具发现 `57` 个、HTTP/SSE 各 `1` 个，三类 call 均通过，动态 schema cache 覆盖 `stdio-self/read_file`、`http-fixture/echo`、`sse-fixture/echo`。fixture 现在还会配置一个故意失败的 `broken-stdio` server，并证明它不会隐藏或破坏健康 server 的动态工具发现；同时验证 generic `mcp_call` 和动态 `mcp__stdio-self__read_file` 的 permission request、allowlisted allow、allowlist deny 三条 policy 路径。最新 JSON 字段 `bad_server_isolated`、`mcp_call_permission_ok`、`dynamic_permission_ok`、`mcp_call_allow_ok`、`mcp_call_allowlist_deny_ok`、`dynamic_allow_ok`、`dynamic_allowlist_deny_ok` 均为 `true`。本轮还把 prompts/resources/templates 纳入同一个 fixture smoke：stdio/HTTP/SSE 的 prompt discovery/get、resource discovery/read、resource template discovery 均通过，最新 JSON 中 `stdio_prompt_ok`、`http_prompt_ok`、`sse_prompt_ok`、`stdio_resource_ok`、`http_resource_ok`、`sse_resource_ok` 均为 `true`，template counts 为 `3/1/1`。这补上了 completion gate 中 MCP stdio/HTTP/SSE tool discovery/call/schema 注入、prompt/resource/template、bad-server isolation、MCP tool approval/allowlist 的本地证据。
 - 本轮新增：Phase 12D hooks fixture smoke。新增 `deepseek hooks fixture-smoke --json`，它创建临时 hook root 和 workspace，安装结构化 `{"decision":"allow","add_context":"..."}` recorder scripts，然后通过真实 `AgentLoop::run_with_client` 触发 `list_files` 工具调用。当前实测 JSON 为 `deepseek.hooks_fixture_smoke.v1`，`session_start_ok`、`user_prompt_submit_ok`、`pre_tool_ok`、`post_tool_ok`、`session_stop_ok`、`hook_contexts_ok`、`tool_ran_ok` 全为 `true`，事件顺序为 `session_start -> user_prompt_submit -> pre_tool_use -> post_tool_use -> session_stop`。这给 Phase 12D hooks prompt/session/tool lifecycle 和 structured allow/add_context 提供了单命令本地 gate。
 - 本轮新增：Phase 12D skills/custom command validation。新增 `deepseek skills list [--json]` 与 `deepseek skills validate [--strict] [--json]`，按运行时同一优先级扫描 bundled skills 和 `workspace.user_skills_dir`，报告同名覆盖、loader 错误、空核心元数据、空 `allowed_tools` 和未知工具名。当前 `cargo run --quiet -- skills validate --strict --json --dir skills` 实测 bundled `skills/` 共 `16` 个 skill，`valid_files=16`、`error_count=0`、`warning_count=0`、`ok=true`。`docs/skills-and-profiles.md` 也补了 PR review、release-check、security-lite 三类 skill 示例。这给 Phase 12D skill metadata validation 和 command/skill discovery 提供了单命令本地 gate。
 - 本轮新增：Phase 12D subagent fixture smoke。`dispatch_subagent` / `dispatch_subagents` 现在支持 `write_scope` / `write_set` 元数据，child prompt 会带 assigned write scope，parallel summary 会输出 `meta.parallel_blocked_children`、`meta.parallel_readback_required`、`meta.parallel_next_action`、`meta.parallel_child_N_files`、`meta.parallel_child_N_write_scope` 和 `meta.parallel_write_scope_conflicts`。父 planner 现在会同时消费 `dispatch_subagent` 与 `dispatch_subagents` 汇总，看到 child files 后先 `read_file` 回读再继续。新增 `deepseek agents subagent-fixture-smoke --json` 本地 gate，当前实测 `parser_ok`、`disjoint_write_scope_ok`、`readback_required_ok`、`blocker_summary_ok`、`conflict_summary_ok`、`artifact_ok` 全为 `true`，`child_count=2`。默认 benchmark manifest 已有 `20` 条 `subagent` category cases；benchmark runner 现在支持 `--category <name>` 与可重复 `--case <name>`，filtered run 只生成 report，不推进 history，也不强制全量 trend/live gate。当前 targeted subagent benchmark 实测 `20/20`，报告在 `/tmp/deepseek-subagent-benchmark.md`，trend/live 均标记为 filtered selection skip。本轮补上了并发 subagent 汇总的 readback 单测、fixture gate 和 targeted benchmark evidence。
 - 本轮新增：MCP 模型规划 benchmark 第一片。benchmark runner 现在支持 per-case 自举 `stdio-self` MCP fixture，可在 isolated workdir 写入 `.dscode/mcp.json`、按 case 开关动态 MCP 工具暴露，并设置 case-local `mcp_call_allowlist`。默认 manifest 新增 `fixture-mcp-dynamic-readme`、`fixture-mcp-generic-call-readme`、`fixture-mcp-allowlist-deny-recovery` 三条 MCP cases，分别覆盖动态 `mcp__stdio-self__read_file`、generic `mcp_call`、allowlist deny 后通过 `mcp_list_tools` 恢复。本轮 targeted MCP manifest 从 `/tmp` 运行实测 `3/3`，报告在 `/tmp/deepseek-mcp-benchmark.md`；完整默认 manifest 已扩到 `82` cases，并已刷新通过 `82/82`，最新完整报告在 `.dscode/benchmarks/latest.md`。
-- 本轮新增：benchmark PR planner hardening。离线 planner 现在会保留 `github_pr_context` / `review` / `pr_review_comment_plan` 这类结构化观察，不会因为同属 `Other` kind 被后续工具压缩成 superseded stub；PR comment 失败恢复在成功重建 plan 后不再重复重建第二次；skill auto-select 也会避免把远程 PR review/comment 任务降级到隐藏 `github_pr_context` / `review` / `pr_review_comment_plan` 的 debug skill。`run_shell` 现在会把 `pytest` / `python -m pytest` 缺失以及 profile 生成的 `uv run pytest` 安全标准化到 `uv --with pytest` fallback，并会自动发现 `~/.local/toolchains/go/*/bin` / `~/sdk/go*/bin` 这类用户级 Go toolchain。当前完整离线 benchmark 实测 `82/82`，`25` 条 `pr_workflow` 中 planner/action/comment-plan 项全绿，新增 `mcp` category `3/3`；当前 82-case trend gate 处于 comparable warmup，`found 2`，live gate 基于本机 dogfood ledger 从 `runs=5` 到 `runs=20` 通过。
+- 本轮新增：benchmark PR planner hardening。离线 planner 现在会保留 `github_pr_context` / `review` / `pr_review_comment_plan` 这类结构化观察，不会因为同属 `Other` kind 被后续工具压缩成 superseded stub；PR comment 失败恢复在成功重建 plan 后不再重复重建第二次；skill auto-select 也会避免把远程 PR review/comment 任务降级到隐藏 `github_pr_context` / `review` / `pr_review_comment_plan` 的 debug skill。`run_shell` 现在会把 `pytest` / `python -m pytest` 缺失以及 profile 生成的 `uv run pytest` 安全标准化到 `uv --with pytest` fallback，并会自动发现 `~/.local/toolchains/go/*/bin` / `~/sdk/go*/bin` 这类用户级 Go toolchain。当前完整离线 benchmark 历史实测 `82/82`；本轮新增 hosted exact patch request targeted benchmark 通过，`26` 条 `pr_workflow` 中 planner/action/comment-plan/exact-request 项均有覆盖，新增 `mcp` category `3/3`；当前 trend gate 处于 comparable warmup，`found 2`，live gate 基于本机 dogfood ledger 从 `runs=5` 到 `runs=20` 通过。
 - 本轮新增：offline dogfood replay 覆盖补强。`cargo run --quiet -- dogfood replay-benchmark --category pr_workflow --limit 12 --benchmark-gate` 新增了 12 条 `pr_workflow` replay，覆盖 GitHub Action `@deepseek fix` / `@deepseek patch`、JS/Rust/Python/Go PR CI repair、PR retry validate、second-round feedback 和 Go patch validate，全部成功；该批次把 ledger 推到 `17` runs 后暴露 live coverage gate 还缺 `recovery` slice。随后 `cargo run --quiet -- dogfood replay-benchmark --category recovery --limit 3 --benchmark-gate` 新增 3 条 recovery replay，`recovery` 为 `3/3`，最终 `.dscode/dogfood/latest.md` 为 `20` runs、`19/20` success、`1` historical failed、`0` stuck、`0` manual；post-replay default benchmark 为 `82/82`，live gate `pass against previous dogfood snapshot (runs 5 -> 20)`。这些仍是 `offline` transport，不能替代后续真实 model-backed dogfood。
 - 本轮新增：`deepseek dogfood live-plan` 的推荐命令改为 `deepseek dogfood live-run ...`，文本和 JSON 都同时输出 dry-run 与 `--execute` 命令，避免 release operator 为 model-backed 证据误走 offline-friendly `replay-benchmark` 路径。`deepseek dogfood live-plan` 和 `deepseek dogfood live-run --json` 现在还输出 `post_run_report_command` / `evidence_gate`，直接给出 `dogfood report --require-live-runs ... --require-live-category ...` 的后置验收命令，让真实 online 执行后的 model-backed 证据可以 fail closed。`deepseek dogfood live-run --json` 保持机器可读 dry-run plan，包含 selected cases、online readiness、execute blocker 和 follow-up `--execute` command；它故意不和 `--execute` 混用，避免在线执行日志污染 JSON。`dogfood live-run` 还支持 `--api-key-file`/`--key-file` 指向仓库外 key 文件，只把 key 注入当前进程的 `model.api_key_env` 并在返回时恢复，JSON 只记录 `credential_source` 和文件路径，不输出 key 值。`dogfood live-run --execute --evidence-out <path>` 现在会在批次结束或首个失败后写出 `deepseek.dogfood.live_run_evidence.v1` JSON，记录 before/after ledger live counts、每个 case 追加的 model-backed ledger 行、benchmark gate 结果、同一条 post-run report gate，以及当前 ledger 文件的 `fnv1a64` fingerprint，仍不写入 API key 值。`deepseek dogfood live-evidence --file <path>` 现在可验证该 evidence 文件，默认要求 completed、online、至少 1 条 appended model-backed row；`--require-benchmark-gate` 可把 benchmark gate 也纳入 release fail-closed 检查，`--require-report-gate` 会读取 evidence 的 structured `evidence_gate` 和 ledger path，用 `dogfood report` 同一套 live requirement 逻辑验证 full live gate，重新计算 ledger fingerprint 并逐条核对 evidence 中 appended case 的 timestamp/outcome/model_transport/category 能在 ledger 中找到匹配记录，而不是执行 JSON 里的 shell command；`--json` 输出 `deepseek.dogfood.live_evidence_verification.v1`，`--out <path>` 可把 verification JSON 落盘作为 release evidence artifact。`dogfood external-fixture` 真实执行现在也默认要求 `model_transport=online`，离线只能 dry-run 或显式 `--allow-offline` 做 rehearsal，避免把 offline disposable repo 样本误计为 release evidence；`--evidence-out` 会写出 `deepseek.dogfood.external_fixture_evidence.v1`，包含 appended external fixture row、release-evidence readiness 和 ledger fingerprint，便于上传发布证据。
 - 本轮新增：在线 DeepSeek dogfood 从 smoke 推进到完整 release gate。使用当前进程注入的 DeepSeek key 执行 `dogfood live-run --execute --evidence-out ...`，最终 `deepseek dogfood report --limit 100 --require-live-runs 100 --require-live-success-rate 90 --require-live-category write_validate:25:90 --require-live-category recovery:25:90 --require-live-category pr_workflow:25:90` 通过；外部 fixture 跑完后 `live-plan` 显示 `105` 条 online run、`99` 条 success，分类为 `write_validate 29/30`、`recovery 23/25`、`pr_workflow 47/50`。执行过程中又修掉两类真实模型卡点：Python pytest retry readback 现在能识别 `def test_` / `assert ` 测试文件，并从错误的 `a * b` 回退到 `a + b`；空搜索恢复任务在看到 no matches 后完成 repository layout inspection 会 clean finish，不再重复列目录。release evidence verification 落在 `.dscode/dogfood/live-evidence-final-total-pr-4-release-verification.json`，`report_gate_passed=true`。
@@ -90,9 +91,9 @@ deepseek agents shell-fixture-smoke --json
 4. 产品打磨
    - TUI 已能用，但还需要更多真实工作流下的性能、长输出、失败恢复、窗口 resize、旧终端兼容性验证。
    - VS Code 已有 native panel、resume、active-file review、workspace changed-file queue、generated patch queue/apply/reject、extension-host smoke harness、headless diagnostic patch fixture 和 validation 第一片，但完整 IDE agent workbench 仍缺真实 VS Code CLI runner 证据和 manual GUI fixture 证据。
-   - GitHub automation 已有 event bridge、review/fix/patch mode routing、review workflow 示例、写入型 PR-head checkout workflow 示例、本地 workflow fixture smoke、`25` 条 `pr_workflow` benchmark cases，以及 `14/14` offline `pr_workflow` dogfood replay；当前本机已有 `50` 条 online model-backed `pr_workflow` 样本、`47` 条 success，分类 release gate 已通过；还缺真实远端 fixture repo 上的 hosted workflow run 证据。
+   - GitHub automation 已有 event bridge、review/fix/patch mode routing、review workflow 示例、写入型 PR-head checkout workflow 示例、本地 workflow fixture smoke、真实 hosted write workflow 证据、`26` 条 `pr_workflow` benchmark cases，以及 `14/14` offline `pr_workflow` dogfood replay；当前本机已有 `50` 条 online model-backed `pr_workflow` 样本、`47` 条 success，分类 release gate 已通过。后续重点是把这类远端证据沉淀成更稳定的周期性 smoke，而不是继续保留临时 fixture 文件。
    - MCP 已有 stdio/HTTP/SSE 本地 fixture smoke、动态工具暴露、schema cache、prompt/resource/template 单命令 smoke、bad-server isolation、generic/dynamic MCP approval/allowlist policy 证据，也已有三条模型规划型 MCP benchmark 和完整默认 benchmark `82/82` 证据；当前没有已知 MCP-specific Phase 12D smoke 缺口。
-   - Hooks 已有 prompt submit、session start/stop、pre/post tool use 和 structured allow/add_context 的 `deepseek hooks fixture-smoke --json` 本地 gate；skills/custom command 已有 `deepseek skills validate --strict --json` 元数据 gate 和 discovery 文档；subagent 已有 `deepseek agents subagent-fixture-smoke --json` gate、20 条 subagent benchmark cases、targeted subagent benchmark `20/20`、完整默认 benchmark `82/82`、并发 child readback 和 write-scope conflict metadata。Phase 12D 本地 extension gates 已基本齐备，offline dogfood coverage gate 和 online dogfood release gate 都已通过；下一步应继续外部兼容性、hosted workflow 和真实 demo 证据。
+   - Hooks 已有 prompt submit、session start/stop、pre/post tool use 和 structured allow/add_context 的 `deepseek hooks fixture-smoke --json` 本地 gate；skills/custom command 已有 `deepseek skills validate --strict --json` 元数据 gate 和 discovery 文档；subagent 已有 `deepseek agents subagent-fixture-smoke --json` gate、20 条 subagent benchmark cases、targeted subagent benchmark `20/20`、完整默认 benchmark `82/82`、并发 child readback 和 write-scope conflict metadata。Phase 12D 本地 extension gates 已基本齐备，offline dogfood coverage gate 和 online dogfood release gate 都已通过；下一步应继续外部兼容性和真实 demo 证据。
    - 文档需要继续压缩成新用户能快速理解的安装、配置、试用、故障排查路径。
    - 和上游 DeepSeek-TUI 的新变化需要持续周期性 refresh。
 
@@ -133,4 +134,4 @@ DeepSeekCode 现在已经是一个可以实际使用的 code agent CLI，尤其
 
 最准确的公开表述是：
 
-> DeepSeekCode is usable today for dogfooding and repository work, with a full-screen TUI, durable runtime, permissioned tools, release binaries, cross-platform entrypoint smoke, a 100-run online dogfood release gate, initial external disposable-repo write-fixture evidence, and a committed real model-backed README demo SVG. The remaining work is hosted IDE/GitHub evidence, Windows/service proof, optional richer demo media, and public package-channel publishing.
+> DeepSeekCode is usable today for dogfooding and repository work, with a full-screen TUI, durable runtime, permissioned tools, release binaries, cross-platform entrypoint smoke, a 100-run online dogfood release gate, initial external disposable-repo write-fixture evidence, real hosted GitHub workflow evidence, and a committed real model-backed README demo SVG. The remaining work is hosted IDE evidence, Windows/service proof, optional richer demo media, and public package-channel publishing.
diff --git a/docs/superpowers/specs/2026-05-22-github-action-bridge.md b/docs/superpowers/specs/2026-05-22-github-action-bridge.md
index bf5b471..d5680af 100644
--- a/docs/superpowers/specs/2026-05-22-github-action-bridge.md
+++ b/docs/superpowers/specs/2026-05-22-github-action-bridge.md
@@ -92,8 +92,10 @@ convert GitHub event payloads into a PR review run.
   - action-labeled review comment planning case
   - action-labeled `@deepseek fix` JavaScript write/validate fixture
   - action-labeled `@deepseek patch` Rust write/validate fixture
-  - default `.dscode/benchmarks.txt` now has `25` `pr_workflow` cases, matching
-    the Phase 12C benchmark-count target.
+  - action-labeled exact replacement request fixture for
+    `@deepseek patch change ... becomes ...`
+  - default `.dscode/benchmarks.txt` now has `26` `pr_workflow` cases,
+    exceeding the Phase 12C benchmark-count target.
 
 ## Verification
 
@@ -115,6 +117,9 @@ convert GitHub event payloads into a PR review run.
   - Python `pytest`/`uv run pytest` fixtures are covered by `run_shell` fallback
   - Go write-validate fixtures are covered by user-level Go toolchain discovery
   - live gate passes after offline dogfood coverage reached `runs=20`
+- `cargo run --quiet -- benchmark --case fixture-github-action-patch-trigger-exact-replacement-rust-mini --out /tmp/deepseek-hosted-exact-patch-benchmark.md`
+  - targeted result: `1/1`
+  - filtered run did not update benchmark history
 - `cargo run --quiet -- github action --event <tmp-event> --event-name issue_comment --dry-run --trigger @deepseek`
 - `cargo run --quiet -- github pr-head owner/repo#11 --repo-owner owner --github-output --json-file <tmp-pr-json>`
 - `cargo run --quiet -- github fixture-smoke --json`
@@ -139,16 +144,21 @@ convert GitHub event payloads into a PR review run.
 - dry-run samples for `@deepseek fix`, `@deepseek patch`, and explicit
   `--mode review`
 - YAML parse checks for both workflow examples
+- Hosted workflow evidence:
+  - PR #10 proved the hosted write bridge and produced
+    `6fd5010 deepseek: apply requested PR update` from GitHub Actions.
+  - PR #11 repeated the same write flow after the fixes were merged to the
+    default branch and produced `f0fe9a7 deepseek: apply requested PR update`.
+  - PR #12 removed the temporary evidence fixtures after the proof was
+    preserved in PR history.
 
 ## Remaining
 
-- Execute the workflow in a fixture repository and capture evidence that it
-  reads PR diff and posts a review comment.
-- Execute the write workflow in a fixture repository and capture evidence that
-  it checks out PR head, writes a fix/patch, and pushes back to the PR branch.
+- Promote or schedule a stable periodic hosted workflow smoke if this should
+  stay continuously monitored instead of relying on PR #10/#11 evidence.
 - Promote the refreshed benchmark report/history once the surrounding worktree
-  is ready.
+  is ready and a full unfiltered run is desired.
 - Collect online/model-backed `pr_workflow` dogfood evidence for the new
   action-labeled cases. The current `14/14` `pr_workflow` replay evidence uses
   offline transport and is useful for deterministic coverage, not a substitute
-  for hosted workflow/model-backed proof.
+  for model-backed proof.
diff --git a/src/cli/commands/benchmark.rs b/src/cli/commands/benchmark.rs
index 55e88c7..8d59ccb 100644
--- a/src/cli/commands/benchmark.rs
+++ b/src/cli/commands/benchmark.rs
@@ -2866,8 +2866,8 @@ seed_observations = "search_text:failed:no matches || recovery_hint:ok:after=sea
             .filter(|case| case.category == "pr_workflow")
             .count();
         assert!(
-            pr_workflow_cases >= 25,
-            "default manifest should keep Phase 12C pr_workflow coverage at or above 25 cases"
+            pr_workflow_cases >= 26,
+            "default manifest should keep Phase 12C pr_workflow coverage at or above 26 cases"
         );
 
         let review_case = cases
@@ -2910,6 +2910,22 @@ seed_observations = "search_text:failed:no matches || recovery_hint:ok:after=sea
             patch_case.expect_last_tool_output_contains.as_deref(),
             Some("meta.result=ok")
         );
+
+        let exact_patch_case = cases
+            .iter()
+            .find(|case| {
+                case.name == "fixture-github-action-patch-trigger-exact-replacement-rust-mini"
+            })
+            .expect("default manifest should include exact action patch replacement fixture");
+        assert_eq!(exact_patch_case.category, "pr_workflow");
+        assert!(exact_patch_case.isolate_workdir);
+        assert!(exact_patch_case.task.contains("@deepseek patch change"));
+        assert!(exact_patch_case.task.contains(" becomes "));
+        assert_eq!(exact_patch_case.expect_tool.as_deref(), Some("apply_patch"));
+        assert_eq!(
+            exact_patch_case.expect_last_tool_output_contains.as_deref(),
+            Some("meta.result=ok")
+        );
     }
 
     #[test]