@mokuyoaxis/agent-guard 0.2.5-rc3 → 0.2.6

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (44) hide show
  1. package/README.md +64 -34
  2. package/README.zh-CN.md +53 -27
  3. package/SECURITY.md +5 -3
  4. package/adapters/INTEGRATION.md +84 -10
  5. package/adapters/claude/README.md +6 -0
  6. package/adapters/dsh/README.md +51 -7
  7. package/adapters/dsh/compatibility.json +14 -0
  8. package/adapters/dsh/harness/README.md +11 -0
  9. package/adapters/dsh/harness/guard_lab.py +42 -14
  10. package/adapters/dsh/lib/index.js +127 -33
  11. package/adapters/kimi-code/README.md +154 -14
  12. package/adapters/kimi-code/compatibility.json +1 -1
  13. package/adapters/kimi-code/config.example.toml +18 -6
  14. package/adapters/kimi-code/hook_bridge.sh +19 -4
  15. package/adapters/kimi-code/pre_tool_use.py +1 -1
  16. package/adapters/kimi-code/stop_feedback.py +237 -0
  17. package/core/messages.py +40 -0
  18. package/core/policy.py +2 -1
  19. package/docs/README.md +30 -8
  20. package/docs/design/architecture.md +13 -6
  21. package/docs/design/compatibility.md +87 -4
  22. package/docs/design/dsh-compatibility.md +65 -0
  23. package/docs/design/threat-model.md +2 -2
  24. package/docs/guides/getting-started.md +76 -17
  25. package/docs/guides/harness-capabilities.md +24 -5
  26. package/docs/guides/host-drift.md +32 -0
  27. package/docs/guides/recovery-feedback.md +126 -0
  28. package/docs/history/friction.md +21 -1
  29. package/docs/lab/blue-team-calibration.md +1 -1
  30. package/docs/lab/guard-lab.md +6 -2
  31. package/docs/releases/release-notes-0.2.5-rc3.md +8 -0
  32. package/docs/releases/release-notes-0.2.5.md +123 -0
  33. package/docs/releases/release-notes-0.2.6.md +167 -0
  34. package/docs/releases/unreleased.md +141 -0
  35. package/docs/reports/test-report-dsh-alpha4.md +102 -0
  36. package/docs/reports/test-report-kimi-code-block.md +119 -6
  37. package/doctor.py +175 -28
  38. package/package.json +11 -2
  39. package/skills/delete-guard/SKILL.md +30 -13
  40. package/skills/delete-guard/references/policy.md +16 -3
  41. package/skills/delete-guard/scripts/check.py +13 -0
  42. package/skills/delete-guard/scripts/gc.py +4 -2
  43. package/skills/delete-guard/scripts/safe_delete.py +20 -14
  44. package/skills/delete-guard/scripts/status.py +9 -0
@@ -0,0 +1,123 @@
1
+ # Agent Guard 0.2.5
2
+
3
+ Stable maintenance release, prepared 2026-10-19. Version 0.2.5 combines
4
+ the maintenance and research delivered in RC1–RC3 with clearer feedback about
5
+ runtime readiness, command coverage and recovery storage.
6
+
7
+ The exact tag routes to a GitHub release and npm `latest`. Availability is
8
+ established by the [GitHub release](https://github.com/mokuyoaxis/agent-guard/releases/tag/0.2.5)
9
+ and [npm version](https://www.npmjs.com/package/@mokuyoaxis/agent-guard/v/0.2.5).
10
+ RC3 and 0.2.4-hotfix.1 retain their independent opt-in channels and artifacts.
11
+
12
+ 0.2.5 正式版汇合 RC1—RC3 与明确反馈维护;GitHub/npm 的实际发布结果以精确版本回执为准。
13
+ 本版不自动升级用户已有安装,不改变 rm 通配符规则或执行路径。
14
+
15
+ ## What users will see
16
+
17
+ - **Startup checks run Python.** Before registering its tools and listener,
18
+ the DSH adapter runs `python3 check.py --help` in the plugin process.
19
+ Missing dependencies, an import/process failure or a 10-second startup
20
+ timeout now produces an explicit initialization failure. The host can
21
+ continue running other tools, so inspect the plugin's activation status.
22
+ - **Local readiness and host interception are separate.** DSH status shows
23
+ the startup check, listener registration and most recent checker result.
24
+ Live interception remains `UNVERIFIED`; local CLI status reports recovery
25
+ data only. A plugin that never loaded may provide no status tool.
26
+ - **Unrecognized effects are identified.** `ALLOW_NOOP` now explains:
27
+ “No recovery action is needed for the recognized operations. Unrecognized
28
+ command effects have not been checked.” Its verdict and reason code stay
29
+ the same. Script/interpreter effects are not certified as harmless.
30
+ - **Relocation explains retained storage.** Successful moves and partial
31
+ failures with moved files report that the data still uses disk space,
32
+ retain the recovery transaction ID, and provide GC commands. A dry-run,
33
+ no-match or direct artifact deletion does not claim a relocation.
34
+ - **GC guidance selects an actual action.** Results provide a plan command,
35
+ `--execute --all-eligible`, and explicit `--execute --txid '<txid>'` guidance.
36
+ Keep the same working directory and workspace/trash settings. The 30-day
37
+ and 5-GiB thresholds do not run cleanup automatically; `--execute` alone
38
+ selects nothing. Purge removes recovery copies permanently and does not
39
+ prune Git stash snapshots.
40
+ - **Failures explain the affected step.** Static `CHECKER_*` and `STATUS_*`
41
+ diagnostics distinguish execution, timeout, process and output failures
42
+ from policy refusals. Checker infrastructure failures still deny the call.
43
+ A failed status query returns `ok: false` and `report: null`, retaining
44
+ adapter facts without replacing the last command-checker result or copying
45
+ raw process errors into diagnostics.
46
+
47
+ 这些反馈不扩大自动拦截范围。Python 在插件进程中可运行,不代表调用者的 shell/sandbox
48
+ 已经验证;Hook 已注册也不代表实际调用经过它。迁入回收站是保留恢复副本,数据仍占空间。
49
+ 具体字段、故障标签及 GC 示例见[状态与清理反馈](../guides/recovery-feedback.md)。
50
+
51
+ ## Included from the prereleases
52
+
53
+ - [RC1](release-notes-0.2.5-rc1.md): quarantine control-path protection,
54
+ PURGED-history exclusion from active GC planning, minimized restore and
55
+ safe_delete audit writers, exemption diagnostics and assessment clarification.
56
+ - [RC2](release-notes-0.2.5-rc2.md): shared audit metadata projection, opaque
57
+ session correlation, bounded legacy status/GC metadata, observer startup
58
+ diagnostics and cancellation accounting.
59
+ - [RC3](release-notes-0.2.5-rc3.md): defensive research, sanitized bounded
60
+ observations and the portable four-control calibration example. Private
61
+ experimental methods do not become production authorization features.
62
+
63
+ ## Upgrade impact
64
+
65
+ | Starting point | What to review |
66
+ |---|---|
67
+ | 0.2.4 | Quarantine control paths can now be refused before housekeeping. Review RC audit field changes and explicit DSH initialization failures. |
68
+ | 0.2.4-hotfix.1 | Control-path protection is already backported. The remaining RC maintenance, research and feedback are additional. |
69
+ | 0.2.5-rc1 / rc2 | Later RC content and the feedback changes above are cumulative. |
70
+ | 0.2.5-rc3 | Review the new startup/status diagnostics, `ALLOW_NOOP` explanation and retained-storage/GC guidance. |
71
+
72
+ Consumers must tolerate optional result fields. Audit records are supported
73
+ metadata, not arbitrary payload storage: raw/custom audit fields may be
74
+ omitted or projected, including in-memory views of old records. Earlier log
75
+ bytes are not rewritten. Recovery IDs and manifest/CLI paths remain exact;
76
+ an audit correlation digest is not a restore argument. See the
77
+ [audit contract](../guides/audit-metadata.md).
78
+
79
+ The default DSH lifecycle changes from log-only inactivity to explicit
80
+ initialization failure. Python must be on the plugin process PATH and
81
+ available to the actual executor. Existing admitted host versions remain
82
+ `0.1.5-rc.1` and `0.2.0-rc.2`; optional read redaction stays off by default
83
+ and keeps its existing artifact pins and coverage limits.
84
+
85
+ The maintainer selected 0.2.5 for this cumulative maintenance, carrying
86
+ forward RC1's documented versioning exception. Decision/reason strings,
87
+ public CLI parameters and exit-code roles, recovery strategies and formats
88
+ retain their contracts. No production dependency or configuration/storage
89
+ migration is introduced. See the [compatibility contract](../design/compatibility.md).
90
+
91
+ 本轮没有改动 rm 通配符、变量、管道、find 或工作区边界规则,也没有新增替代执行路径。
92
+ `safe_delete` 仍按原规则显式展开自己的参数;这不放宽 `rm` 的通配符判定。
93
+
94
+ ## Validation and limits
95
+
96
+ Before the version-only promotion, the feedback-maintenance checkout passed
97
+ one complete `npm test` on 2026-10-19: 933 Python tests and both Node adapter
98
+ groups, with original assertions and timeouts. Eleven actual CLI scenarios,
99
+ feedback/audit checks, bounded zero-model DSH runtime checks for both admitted
100
+ versions, and source/tarball/offline-install equality also passed. This is
101
+ local maintenance evidence, separate from versioned remote release gates.
102
+
103
+ The versioned 0.2.5 checkpoint separately passed one complete `npm test`:
104
+ 933 Python tests (835.794 seconds, no skips) and both Node groups, with
105
+ 192 public files unchanged throughout the run. The 137-file local package
106
+ matched source and offline installation; ten CLI entries, adapter import,
107
+ synthetic recovery, explicit GC guidance and unchanged wildcard refusal passed.
108
+ After that run, only release-status documentation and this evidence paragraph
109
+ changed. Runtime and test bytes retain the verified checkpoint; final
110
+ source/package/installation equality is checked again for publication.
111
+
112
+ Earlier intermittent subprocess timeouts remain recorded as failures. Their
113
+ historical cause is unresolved; later successful checks do not establish a
114
+ root-cause fix. The [capability matrix](../guides/harness-capabilities.md)
115
+ retains each host report's tested versions and scope. This preparation adds
116
+ no real-model trial, UI/sandbox certification or general subagent guarantee.
117
+ Full Windows-native harness E2E, universal egress protection and isolation
118
+ against same-UID processes remain outside the guarantee.
119
+
120
+ Install the exact version or use a reviewed checkout/tarball following
121
+ [getting started](../guides/getting-started.md). Publication requires the
122
+ final commit's CI, npm credential preflight and matching GitHub/npm artifacts.
123
+ Local checks do not establish those remote receipts or registry availability.
@@ -0,0 +1,167 @@
1
+ # 0.2.6 — Kimi feedback, diagnostics and host compatibility
2
+
3
+ Released 2026-10-22 as the stable maintenance release on npm `latest`.
4
+ Use the exact [GitHub release](https://github.com/mokuyoaxis/agent-guard/releases/tag/0.2.6)
5
+ and [npm version](https://www.npmjs.com/package/@mokuyoaxis/agent-guard/v/0.2.6)
6
+ to identify the package. RC and hotfix channels keep their existing versions.
7
+ See [getting started](https://github.com/mokuyoaxis/agent-guard/blob/0.2.6/docs/guides/getting-started.md) for installation and setup.
8
+
9
+ 本版补齐 Kimi 恢复信息的反馈出口与本地诊断,细分 DSH Lab 预检失败原因,
10
+ 并为默认删除适配增加 DSH `0.2.1-alpha.4`、为 Kimi Bash profile 增加精确版本 `2.3.0`。
11
+ 已有安装需要升级;Kimi Stop 仍需显式配置,并在新会话中加载。
12
+
13
+ ## Kimi recovery feedback
14
+
15
+ In the sampled Kimi 0.42.0, 2.1.1 and 2.3.0 success-hook paths, the recovery
16
+ explanation did not enter the next model request. A successful Bash result
17
+ therefore did not tell the model that files had moved to quarantine.
18
+
19
+ The optional POSIX Stop hook supplies actual transaction IDs, inspection and
20
+ restore commands, retained-storage guidance and complete GC commands. It asks
21
+ for an additional response after new compensation records. Existing
22
+ PreToolUse-only installations keep their behavior; Stop must be explicitly
23
+ configured and read by a new Kimi session.
24
+
25
+ The initial answer appears first and may be inaccurate. Stop adds a model
26
+ generation and cannot repair the earlier tool result. Emission cursors suppress
27
+ repeated notices in the tested scope; they are not model acknowledgements.
28
+ Cancellation, exhausted budgets and shared-session actors retain their limits.
29
+ The hook executes no restore or GC. Restoring files moves them back without
30
+ freeing total disk space; permanent GC removes recovery copies.
31
+
32
+ The example recommends PreToolUse 120 seconds around the unchanged internal
33
+ 90-second check, and Stop 30 seconds. Missing or timed-out hooks can still
34
+ allow tools in the sampled hosts. The outer timeout margin does not change
35
+ that behavior. See [setup and limits](https://github.com/mokuyoaxis/agent-guard/blob/0.2.6/adapters/kimi-code/README.md#optional-recovery-feedback-unreleased-checkout-addition)
36
+ and the [bounded host report](https://github.com/mokuyoaxis/agent-guard/blob/0.2.6/docs/reports/test-report-kimi-code-block.md).
37
+
38
+ ## Kimi 2.3.0 Bash compatibility
39
+
40
+ The Kimi compatibility profile now lists exact versions `0.42.0`, `2.1.1`
41
+ and `2.3.0`. The new version has eight actual prompt-CLI and eight ACP trials
42
+ with fixed loopback responses: allow, BLOCK, ASK hard refusal, Python startup
43
+ failure, hook absence, recovery, partial compensation and optional Stop
44
+ delivery. ACP hook process/payload cwd matched the session workspace even
45
+ when the service started in another directory. No external model calls were
46
+ made. See the [bounded report](https://github.com/mokuyoaxis/agent-guard/blob/0.2.6/docs/reports/test-report-kimi-code-block.md#kimi-230-acceptance).
47
+
48
+ Core and bridge behavior are unchanged. A valid 2.3.0 local preflight can
49
+ be `CURRENT`, while unlisted versions remain `STALE`. Existing baselines may
50
+ be `DRIFTED` because the profile fingerprint changed; they are not overwritten.
51
+ This does not add subagent, background, other-tool or real-model guarantees.
52
+ Web checks covered startup/status/shutdown, not Web tool calls. The separate
53
+ Kimi Lab capture helper remains pinned to 2.1.1. Published 0.2.5 retains its
54
+ recorded list; upgrade that installation to obtain the new profile.
55
+
56
+ ## Separate Stop doctor results
57
+
58
+ `doctor.py kimi --probe --json` retains the existing top-level PreToolUse
59
+ results and adds `feedback` for optional Stop:
60
+
61
+ - Absent Stop is `NOT_CONFIGURED` and does not fail the CLI. An unreadable or
62
+ invalid configuration is `UNVERIFIED`, rather than a claim that Stop is off.
63
+ - Checks cover the event, absolute shell/bridge/Python command, option,
64
+ matcher, timeout, duplicate definitions and helper presence.
65
+ - A requested local probe runs synthetic records in its own temporary
66
+ home/workspace/trash. It checks feedback content and repeat suppression
67
+ without touching existing recovery records or calling a model. PreToolUse
68
+ probes also isolate inherited recovery locations.
69
+ - A configured Stop that fails configuration or a requested local probe makes
70
+ the CLI exit 1 and drift `BROKEN`, prevents writing a passing baseline and
71
+ stops the live sentinel before it can call a model.
72
+ - Configured Stop fields and helper bytes join drift fingerprints. Runtime
73
+ fingerprints include `package.json`, so the version change itself can
74
+ produce `DRIFTED` against an older baseline. Review the change before
75
+ creating a new baseline at a new path.
76
+
77
+ `feedback.model_delivery` always remains `UNVERIFIED`, including after a
78
+ Bash live sentinel. Local success does not prove a live host loaded Stop or
79
+ a model received its feedback. The importable `check_kimi()` wrapper remains
80
+ PreToolUse-only; Claude output retains its existing contract.
81
+ See the [doctor fields](https://github.com/mokuyoaxis/agent-guard/blob/0.2.6/adapters/kimi-code/README.md#stop-doctor-checks-unreleased).
82
+
83
+ ## DSH Lab preflight diagnostics
84
+
85
+ Version/config checks distinguish `START_FAILED`, `TIMEOUT`, `OUTPUT_LIMIT`,
86
+ `NONZERO_EXIT`, `EMPTY_STDOUT` and `UNSUPPORTED_VERSION`. Errors retain their
87
+ stage text and add JSON with the child exit code, capture flags,
88
+ elapsed/deadline seconds and captured byte counts. Raw configuration, stderr,
89
+ command arguments and environment values are omitted.
90
+
91
+ The Lab CLI still exits 1 on failure. Its 10/15-second budgets and admitted
92
+ DSH versions remain unchanged, without automatic retry. Consumers should
93
+ inspect diagnostic fields rather than match the whole old error sentence.
94
+ This concerns the Lab controller, not production deletion policy.
95
+ See the [Lab runner guide](https://github.com/mokuyoaxis/agent-guard/blob/0.2.6/adapters/dsh/harness/README.md).
96
+
97
+ ## Upgrade scope
98
+
99
+ The default DSH deletion adapter now admits `0.2.1-alpha.4` alongside
100
+ `0.1.5-rc.1` and `0.2.0-rc.2`. The top-level engines, optional DSH peer and
101
+ nested bundle declaration match the exact list. This corrects the loader
102
+ metadata: the nested field alone was not an admission gate. Reviewed loaders
103
+ now reject tested unlisted hosts without exemptions. The optional peer does
104
+ not install DSH. See [compatibility](https://github.com/mokuyoaxis/agent-guard/blob/0.2.6/docs/design/dsh-compatibility.md) and
105
+ [native validation](https://github.com/mokuyoaxis/agent-guard/blob/0.2.6/docs/reports/test-report-dsh-alpha4.md).
106
+
107
+ Optional read protection and Lab retain their two-version boundaries.
108
+
109
+ Core decisions, rm wildcard refusal, command recognition, workspace boundaries,
110
+ recovery formats and manual GC retain their contracts. No production
111
+ dependency or storage/configuration migration is introduced. Stop is opt-in;
112
+ the local doctor exit behavior for an invalid configured Stop is
113
+ upgrade-visible. Earlier RC and hotfix artifacts retain their separate scope.
114
+
115
+ The maintainer selected 0.2.6 for this feedback/diagnostic maintenance. The
116
+ [compatibility contract](https://github.com/mokuyoaxis/agent-guard/blob/0.2.6/docs/design/compatibility.md) records the bounded
117
+ maintenance-version exception for its additive diagnostics. This does not
118
+ authorize unrelated policy changes under the patch versioning rules.
119
+
120
+ ## Validation and limits
121
+
122
+ The implementation checkpoint
123
+ [9295b9a](https://github.com/mokuyoaxis/agent-guard/commit/9295b9a8ccadba1a5a34b71fe049105fd8aefe6b)
124
+ passed [all 13 CI jobs](https://github.com/mokuyoaxis/agent-guard/actions/runs/39804200594)
125
+ on 2026-10-22. Linux and macOS each ran the complete 974-test discovery on
126
+ Python 3.9–3.13. Python 3.9/3.10 each retained 29 conditional skips;
127
+ 3.11–3.13 had none. Both Node groups, 113 DSH native-Lab checks, 92 focused
128
+ Windows Core checks and the end-to-end workspace-root refusal smoke passed.
129
+ Linux's full matrix is pinned to Ubuntu 24.04 because Ubuntu 26.04 lacks the
130
+ Python 3.9 build. No version or test was removed to resolve that setup failure.
131
+ Final publication wording changes only Markdown; runtime, tests and policies
132
+ retain that checkpoint's bytes.
133
+
134
+ The later DSH expansion has separate actual CLI Profile/Boot evidence on all
135
+ three admitted hosts and alpha.4 scripted root/child-agent and native approval
136
+ checks. No external model request was made. Its new manifest/forwarding tests,
137
+ package verification and limits are recorded in the
138
+ [DSH report](https://github.com/mokuyoaxis/agent-guard/blob/0.2.6/docs/reports/test-report-dsh-alpha4.md); the earlier full run below
139
+ does not include this later manifest change. The implementation CI above does.
140
+
141
+ ### Historical local checkpoint
142
+
143
+ Before this version/document alignment, the unchanged implementation passed
144
+ one complete frozen run on 2026-10-21: **974 Python tests and both Node groups**,
145
+ with no failure, error or skip. The same 195-file candidate completed all three
146
+ stages in 1270.573 seconds within the unchanged 1800-second deadline, without
147
+ retry. An internal unittest result collector wrote immediate failures and
148
+ flushed per-test events; the discovery scope matched `npm test`. This was a
149
+ single continuous workflow, not a combination of earlier targeted runs.
150
+
151
+ The local environment was ARM64/PRoot Debian, Python 3.13.5 and Node v22.23.2.
152
+ Earlier full-run errors/timeouts remain historical failures; their original
153
+ causes are not established by this passing run. The version assertion and
154
+ package metadata were aligned separately during preparation. The prior
155
+ 139-file offline package described the pre-version checkpoint, not a
156
+ published or already-validated 0.2.6 artifact.
157
+
158
+ The later Kimi 2.3.0 profile alignment and its bounded host trials also
159
+ postdate the historical full run. They do not turn that run into a complete
160
+ validation of the final candidate. Earlier actual-CLI loopback trials
161
+ covered sampled Kimi 0.42.0/2.1.1 paths;
162
+ one bounded 2.1.1 real-model session received the actual transaction and full
163
+ commands, followed by restoration and repeat-Stop checks. Publishing this
164
+ release adds no new host/model trial or general subagent/background guarantee.
165
+ The historical local run did not execute other Python versions, macOS or
166
+ Windows; the remote CI above supplies separate platform evidence. Passing CI
167
+ does not establish the cause of the earlier local timeouts or failures.
@@ -0,0 +1,141 @@
1
+ # Maintenance delivered in 0.2.6 / 0.2.6 维护说明
2
+
3
+ Updated 2026-10-22. The additions previously tracked here now ship in
4
+ [0.2.6](release-notes-0.2.6.md). This path is retained for existing links and
5
+ the preparation history below. The [0.2.5 notes](release-notes-0.2.5.md) retain
6
+ that release's scope. Existing installations need an upgrade; optional Stop
7
+ also needs explicit configuration and a new Kimi session.
8
+
9
+ ## Availability
10
+
11
+ | Addition | Availability and setup |
12
+ |---|---|
13
+ | Kimi recovery feedback | Included in 0.2.6 as `adapters/kimi-code/stop_feedback.py`; requires an explicitly configured Stop hook. Version 0.2.5 lacks this helper. |
14
+ | Kimi configuration guidance | The current example recommends PreToolUse 120 seconds and optional Stop 30 seconds; merge top-level skill directories separately from TOML hook tables. Existing installations can adjust their PreToolUse timeout independently of Stop. |
15
+ | Kimi Stop doctor checks | Included in 0.2.6; `doctor.py kimi --probe --json` reports optional Stop configuration/local execution in a separate `feedback` object. Version 0.2.5 lacks these checks. |
16
+ | Kimi 2.3.0 Bash profile | Added in 0.2.6 after prompt-CLI and ACP root-Bash trials. Version 0.2.5 keeps its earlier list; the separate Kimi Lab helper stays pinned to 2.1.1. |
17
+ | DSH Lab preflight diagnostics | Included in 0.2.6; 0.2.5 retains the older generic error messages. This concerns the Lab controller's version/config checks, not the production deletion policy. |
18
+ | DSH alpha.4 default deletion adapter | Added in 0.2.6. Exact loader declarations include `0.2.1-alpha.4`; optional native read and Lab keep their two-version scope. Version 0.2.5 retains its earlier declaration. |
19
+
20
+ Use the [installation guide](../guides/getting-started.md) to keep the chosen
21
+ checkout or local-package path consistent. Start a new Kimi session after
22
+ changing hooks. The setup remains opt-in; this page does not change user settings.
23
+
24
+ ## Kimi recovery feedback
25
+
26
+ The sampled Kimi 0.42.0, 2.1.1 and 2.3.0 success-hook paths omit the recovery
27
+ explanation from the next model request. The optional POSIX Stop hook asks
28
+ for one additional response after new compensations. It supplies actual
29
+ transaction IDs, state/restore commands, retained-storage guidance and full
30
+ GC commands. Restoring files moves them back without freeing total disk space.
31
+ The hook itself performs no restore or purge.
32
+
33
+ The initial answer appears first and may be inaccurate. Stop cannot repair
34
+ the earlier tool result; the model may still omit details. Emission cursors
35
+ prevent repeated notices in the tested scope but do not prove model receipt.
36
+ Shared-session actors, cancellation and exhausted budgets retain their limits.
37
+ The local doctor checks described below do not prove optional Stop delivery.
38
+
39
+ See [setup and delivery limits](../../adapters/kimi-code/README.md#optional-recovery-feedback-unreleased-checkout-addition)
40
+ and the [bounded host report](../reports/test-report-kimi-code-block.md).
41
+ Missing/timed-out hooks still allow tools in the sampled hosts. The 120-second
42
+ outer timeout gives the internal 90-second check margin; it does not change
43
+ that host behavior.
44
+
45
+ ## Kimi Stop doctor checks
46
+
47
+ The existing top-level results retain PreToolUse scope. A separate `feedback`
48
+ object distinguishes absent Stop (`NOT_CONFIGURED`), invalid configuration
49
+ (`FAIL`), unreadable configuration (`UNVERIFIED`), and requested local probe
50
+ success/failure. An absent optional Stop does not fail the CLI; a configured
51
+ Stop that fails configuration or a requested probe exits 1.
52
+
53
+ The probe checks synthetic recovery guidance, empty/active-Stop silence and
54
+ repeat suppression in its own temporary home/workspace/trash. Existing audit
55
+ records and cursors are left alone; no model, deletion, restore or GC runs.
56
+ PreToolUse probes also isolate inherited `AGENT_GUARD_*` recovery locations.
57
+ Executable/file presence is checked separately from successful execution.
58
+ `feedback.model_delivery` remains `UNVERIFIED`, even after a Bash live sentinel.
59
+
60
+ Configured Stop fields and helper bytes join drift fingerprints. A Stop
61
+ failure prevents writing a passing baseline or proceeding to the live sentinel.
62
+ The importable `check_kimi()` wrapper remains PreToolUse-only; Claude behavior,
63
+ Core policy and rm wildcard rules are unchanged. See the
64
+ [doctor fields and limits](../../adapters/kimi-code/README.md#stop-doctor-checks-unreleased).
65
+
66
+ ## DSH Lab preflight diagnostics
67
+
68
+ Version/config failures distinguish `START_FAILED`, `TIMEOUT`, `OUTPUT_LIMIT`,
69
+ `NONZERO_EXIT`, `EMPTY_STDOUT` and `UNSUPPORTED_VERSION`. Errors include child
70
+ exit code, capture flags, elapsed/deadline seconds and captured byte counts.
71
+ Configuration text, stderr text, command arguments and environment values are
72
+ omitted. Version/config budgets remain 10/15 seconds, with no automatic retry.
73
+ CLI failure still exits 1. See the [Lab runner guide](../../adapters/dsh/harness/README.md).
74
+
75
+ ## Validation and remaining uncertainty
76
+
77
+ The [0.2.6 release notes](release-notes-0.2.6.md#validation-and-limits) record
78
+ the implementation checkpoint's 13/13 CI result, including ten complete
79
+ Python matrix jobs and both Node groups. The dated local checkpoints below
80
+ remain historical records and do not replace that final implementation check.
81
+
82
+ The later [DSH compatibility work](../design/dsh-compatibility.md) adds alpha.4
83
+ to default deletion support. Real CLI Profile/Boot checks covered all three
84
+ admitted hosts, with scripted root/child-agent, policy-forwarding and approval
85
+ checks on alpha.4. The [report](../reports/test-report-dsh-alpha4.md) records
86
+ that separate checkpoint; the historical full run below predates the new
87
+ manifest/forwarding assertions and does not validate those additions.
88
+
89
+ Before the 0.2.6 version/document alignment, the implementation passed a
90
+ complete frozen run on 2026-10-21: **974 Python tests and both Node groups**,
91
+ no failures, errors or skips, in 1270.573 seconds with the original
92
+ 1800-second deadline and no retry. It used an internal unittest result
93
+ collector for immediate failure/event logs, with the same discovery scope
94
+ and sequential Node stages as `npm test`. The 195 public files stayed frozen.
95
+ That preparation aligned only version metadata, the exact-version assertion
96
+ and documentation; it does not reclassify the older failures below as passes.
97
+
98
+ The earlier DSH diagnostics checkpoint passed one complete `npm test` on 2026-10-21:
99
+ **962 Python tests and both Node groups**, on ARM64/PRoot POSIX. A 138-file
100
+ local package was installed offline at a path containing spaces; its CLI
101
+ reported the controlled child exit code correctly without copying payloads.
102
+ Those counts describe that earlier checkpoint, before the Stop doctor
103
+ additions. A later 139-file offline package checked the doctor candidate;
104
+ neither older artifact is a versioned 0.2.6 release.
105
+
106
+ The earlier complete-test attempts included a timeout and one DSH config
107
+ preflight error. Its original result details were not retained. Five bounded
108
+ repetitions of the failing case and the new complete run passed, but the
109
+ historical cause remains unknown. Controlled faults verified the new
110
+ diagnostics; they are separate from reproducing that historical failure.
111
+
112
+ Later Kimi compatibility work adds exact `2.3.0` to the Bash profile after
113
+ sixteen actual-host fixed-loopback trials: eight prompt CLI and eight ACP,
114
+ including allow, BLOCK, ASK refusal, runtime failure, absence controls,
115
+ quarantine/restore and Stop feedback. ACP hooks ran in the session directory
116
+ despite a different server startup cwd. This postdates the historical full
117
+ run above; it changes the version declaration, not Core or the bridge.
118
+ The [2.3.0 report](../reports/test-report-kimi-code-block.md#kimi-230-acceptance)
119
+ keeps root Bash, client-terminal, timeout, model and subagent limits explicit.
120
+ Updating the profile can make an old baseline `DRIFTED`; no baseline is
121
+ automatically rewritten. The Lab helper remains pinned to 2.1.1.
122
+
123
+ Earlier Kimi fixed loopback trials exercised the actual 0.42.0/2.1.1 CLIs.
124
+ A bounded 2.1.1 real-model session received the recorded transaction and full
125
+ commands; restoration and repeat-Stop checks passed. This does not establish
126
+ all-model, subagent, background or long-running behavior. The new DSH
127
+ diagnostic checks made no external model requests.
128
+
129
+ ## 中文摘要
130
+
131
+ 本页记录已纳入 0.2.6 的维护:Kimi 可选 Stop 恢复反馈、120 秒外层超时接入说明,以及
132
+ DSH Lab 版本/配置预检的原因、退出码和计时诊断,及 Kimi Stop 的独立 doctor 检查。
133
+ 后续默认删除适配加入 DSH `0.2.1-alpha.4`,读取脱敏/Lab 不随之扩大。
134
+ Kimi Bash profile 新增精确版本 2.3.0;CLI/ACP 各八项固定响应试次提供有限根代理证据,
135
+ 未调用外部模型,也未扩大 Kimi Lab 的 2.1.1 准入或子代理声明。
136
+ Stop 未配置不报错;配置或本地探针失败退出 1,模型送达始终未验证。已发布 0.2.5 的范围保持原记录;
137
+ 已有安装需升级至 0.2.6,Stop 另需显式配置;原页面路径为已有链接保留。
138
+
139
+ 版本/文档对齐前,最终实现检查点的 974 项 Python 与两组 Node 已在同一冻结流程通过;
140
+ 此前 962 项检查点和历史失败分别保留,原失败原因仍未确定。
141
+ 删除策略、rm 通配符规则、恢复格式和手动 GC 保持原样。
@@ -0,0 +1,102 @@
1
+ # DSH alpha.4 default deletion adapter
2
+
3
+ Tested 2026-10-22 on ARM64/PRoot Debian with Node v22.23.2 and Python 3.13.5.
4
+ At validation, the selected Agent Guard checkout identified as 0.2.6 and was
5
+ unpublished. The tested additions now ship in [0.2.6](../releases/release-notes-0.2.6.md).
6
+ This report adds default deletion evidence for DSH `0.2.1-alpha.4`; the
7
+ [compatibility page](../design/dsh-compatibility.md) states the separate
8
+ optional-read and Lab boundaries.
9
+
10
+ ## Actual CLI and bundle loading
11
+
12
+ Three isolated runs launched the actual DSH CLI using an owned profile with
13
+ `dsh-base` and a local link to this checkout's package. Python Core came from
14
+ that selected package, with no `repoRoot` override. Homes, settings, profiles,
15
+ Git workspaces and recovery directories belonged to the trials. No user
16
+ profile was updated, and no DSH/dependency installation was performed.
17
+
18
+ The CLI roots were `0.1.5-rc.1`, `0.2.0-rc.2` and `0.2.1-alpha.4`.
19
+ The legacy root's key SDK packages are `0.1.5-rc.2`; root and SDK versions
20
+ were not assumed interchangeable. All three completed the following seven
21
+ checks through the real Profile/Boot and native Bash/shell services:
22
+
23
+ - Load the selected bundle and register its three recovery tools.
24
+ - Execute a harmless command.
25
+ - Reject a force-push-shaped command before its harmless bypass marker runs.
26
+ - Reject a wildcard deletion shape, preserving the owned log file.
27
+ - Reject an ASK when the direct call has no agent/approval route.
28
+ - Query status without promoting `host_interception` above `UNVERIFIED`.
29
+ - Quarantine an owned valuable file, report retained disk use and GC guidance,
30
+ then restore its original bytes through the registered tool.
31
+
32
+ ## Root and native child agents on alpha.4
33
+
34
+ The actual AgentLoop and native continuable subagent service ran five actors.
35
+ A local scripted LLM adapter emitted 15 fixed streams and ten Bash calls;
36
+ there were no external model requests. Bash, the deletion guard and the native
37
+ approval service were not replaced.
38
+
39
+ | Actor | Observed result |
40
+ |---|---|
41
+ | Root BLOCK | Benign command executed; force-push-shaped call refused; bypass marker absent |
42
+ | Native child BLOCK | Depth 1 and parent lineage recorded; same refusal and absent marker |
43
+ | Root ASK with policy `never` | Native approval rejected the call; marker absent |
44
+ | Native child ASK | Native delegated approval policy rejected the call; marker absent |
45
+ | Root ASK with fixed local answerer | Native approval recorded `allowed-once`; only the owned harmless approval marker ran |
46
+
47
+ The approval grant used a deterministic answerer for one owned sentinel.
48
+ It does not establish interactive approval UI behavior. The first attempt used
49
+ the older `subagents.start` API: its root case passed, then the child driver
50
+ failed because alpha.4 exposes `startActivation` instead. That failed attempt
51
+ was retained. Updating the test driver to the actual SDK interface required
52
+ no product adapter change.
53
+
54
+ Observe-only instrumentation checked each of the five checker requests against
55
+ the invoking agent session's native resolved policy. Workspace, signal and
56
+ the existing 90-second timeout were retained. Native execution used
57
+ `danger-full-access`. Unit checks additionally alternate distinct root/child
58
+ `read-only` and `workspace-write` policies to detect caching across callers.
59
+ These are forwarding checks, not an OS sandbox-confinement certification.
60
+
61
+ ## Loading failures and feature separation
62
+
63
+ Three additional alpha.4 CLI trials confirmed:
64
+
65
+ - Injected startup Python failure reports `GUARD_STARTUP_FAILED`, contributes
66
+ no guard tools and leaves the host able to run other tools.
67
+ - An absent bundle contributes no interception; the harmless marker runs.
68
+ - Explicitly enabling optional read redaction on alpha.4 reports
69
+ `READ_GUARD_STARTUP_REFUSED` and contributes no deletion/read guard from
70
+ that failed plugin row. Leave it disabled on alpha.4.
71
+
72
+ The default version expansion does not update native-read artifact hashes or
73
+ Lab session/config parsers. Their previous two-host contracts remain intact.
74
+
75
+ ## Manifest and regression scope
76
+
77
+ The default adapter's three-version profile matches top-level `engines.dsh`,
78
+ the optional DSH peer and nested `dsh.engines.dsh`. Actual rc.2 and alpha.4
79
+ compatibility helpers accepted all three declared versions and rejected twelve
80
+ unlisted versions each: six accept and 24 rejection checks, without exemptions.
81
+ The optional peer supplies compatibility metadata without installing DSH.
82
+ The legacy loader was checked through actual Profile/Boot rather than a
83
+ modern helper it does not provide.
84
+
85
+ The broader 12-version SDK experiment used controlled shell/synthetic Bash
86
+ tool bodies. Its remaining nine versions were not promoted into the published
87
+ declaration. This report's CLI checks use real native execution.
88
+
89
+ Package-manifest and DSH smoke/regression checks accompany this change.
90
+ The previous 974-test full run predates this expansion and is not its full-suite
91
+ result. Core decisions, command recognition, rm wildcard refusal, compensation,
92
+ recovery formats and the production JavaScript adapter retain their bytes.
93
+ Existing Kimi maintenance changes are separate from this DSH addition.
94
+
95
+ ## Limits
96
+
97
+ No external model, graphical UI, arbitrary PTC/API calls or concurrent-agent
98
+ trial was run. Policy forwarding does not prove OS sandbox enforcement.
99
+ Agent-less checks do not imply subagent coverage; the separate native child
100
+ cases above supply that bounded evidence. Package version, local test success
101
+ and a running host do not establish publication or activation in a user's
102
+ existing profile. Tag and release decisions remain pending.