@mokuyoaxis/agent-guard 0.2.5 → 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.
- package/README.md +39 -19
- package/README.zh-CN.md +33 -18
- package/adapters/INTEGRATION.md +84 -10
- package/adapters/claude/README.md +6 -0
- package/adapters/dsh/README.md +19 -8
- package/adapters/dsh/compatibility.json +14 -0
- package/adapters/dsh/harness/README.md +11 -0
- package/adapters/dsh/harness/guard_lab.py +42 -14
- package/adapters/kimi-code/README.md +154 -14
- package/adapters/kimi-code/compatibility.json +1 -1
- package/adapters/kimi-code/config.example.toml +18 -6
- package/adapters/kimi-code/hook_bridge.sh +19 -4
- package/adapters/kimi-code/pre_tool_use.py +1 -1
- package/adapters/kimi-code/stop_feedback.py +237 -0
- package/docs/README.md +19 -6
- package/docs/design/architecture.md +7 -2
- package/docs/design/compatibility.md +53 -3
- package/docs/design/dsh-compatibility.md +65 -0
- package/docs/guides/getting-started.md +55 -7
- package/docs/guides/harness-capabilities.md +22 -4
- package/docs/guides/host-drift.md +32 -0
- package/docs/guides/recovery-feedback.md +29 -1
- package/docs/releases/release-notes-0.2.6.md +167 -0
- package/docs/releases/unreleased.md +141 -0
- package/docs/reports/test-report-dsh-alpha4.md +102 -0
- package/docs/reports/test-report-kimi-code-block.md +119 -6
- package/doctor.py +175 -28
- package/package.json +11 -2
|
@@ -305,15 +305,20 @@ order of value:
|
|
|
305
305
|
|
|
306
306
|
## Delivery status and design directions
|
|
307
307
|
|
|
308
|
-
The stable release line is 0.2.
|
|
308
|
+
The stable release line is 0.2.6. Previous stable 0.2.5, opt-in
|
|
309
309
|
0.2.4-hotfix.1 and prerelease 0.2.5-rc3 retain their separate artifacts.
|
|
310
310
|
Version 0.2.5 retains RC recovery, shared audit,
|
|
311
311
|
observer maintenance and [defensive research](../research/README.md), plus
|
|
312
312
|
clearer local startup/status and retained-storage feedback. Private research
|
|
313
313
|
methods do not add a general authorization service or production enforcement
|
|
314
314
|
point. Deletion rules and execution routes retain their RC behavior.
|
|
315
|
-
See [
|
|
315
|
+
See [release notes](../releases/release-notes-0.2.6.md) and
|
|
316
316
|
[compatibility](compatibility.md) for behaviour and validation boundaries.
|
|
317
|
+
Release [0.2.6](../releases/release-notes-0.2.6.md) adds
|
|
318
|
+
optional Kimi Stop feedback, its doctor checks and Lab preflight diagnostics.
|
|
319
|
+
It also adds reviewed DSH alpha.4 default deletion and Kimi 2.3.0 Bash compatibility.
|
|
320
|
+
Core policy is unchanged; scope and delivery limits are tracked in the
|
|
321
|
+
[maintenance details](../releases/unreleased.md).
|
|
317
322
|
|
|
318
323
|
The milestones below describe historical delivery and future design scope,
|
|
319
324
|
not a committed schedule or a guarantee that new compensation types need no
|
|
@@ -4,9 +4,10 @@ agent-guard's promise is recoverability. A promise is only as good as its
|
|
|
4
4
|
stability over time - this page states exactly what may change and what
|
|
5
5
|
may not, per release class.
|
|
6
6
|
|
|
7
|
-
The stable release line is [0.2.
|
|
8
|
-
the cumulative RC maintenance
|
|
9
|
-
[0.2.5-rc3](../releases/release-notes-0.2.5-rc3.md),
|
|
7
|
+
The stable release line is [0.2.6](../releases/release-notes-0.2.6.md), carrying
|
|
8
|
+
the cumulative RC maintenance and the feedback/diagnostic additions below.
|
|
9
|
+
The opt-in prerelease remains [0.2.5-rc3](../releases/release-notes-0.2.5-rc3.md),
|
|
10
|
+
0.2.5 is the previous stable, and
|
|
10
11
|
[0.2.4-hotfix.1](https://github.com/mokuyoaxis/agent-guard/releases/tag/0.2.4-hotfix.1)
|
|
11
12
|
is an opt-in quarantine protection backport. Versioned sections retain the
|
|
12
13
|
origin and preparation labels of changes introduced by earlier releases.
|
|
@@ -19,6 +20,54 @@ is introduced by the research documentation.
|
|
|
19
20
|
|
|
20
21
|
## The adapter contract (frozen surface)
|
|
21
22
|
|
|
23
|
+
<a id="unreleased-feedback-and-diagnostic-maintenance"></a>
|
|
24
|
+
|
|
25
|
+
### 0.2.6 feedback and diagnostic maintenance
|
|
26
|
+
|
|
27
|
+
Release [0.2.6](../releases/release-notes-0.2.6.md) adds an opt-in POSIX Kimi
|
|
28
|
+
Stop hook after the existing PreToolUse path. It may request an extra response
|
|
29
|
+
after new compensation records. It does not change the earlier tool result,
|
|
30
|
+
Core verdicts, recovery format or deletion rules; it stores separate local
|
|
31
|
+
emission cursors. Existing PreToolUse setups keep their behavior until Stop
|
|
32
|
+
is explicitly configured. The current example recommends an outer 120-second
|
|
33
|
+
PreToolUse timeout, leaving margin around the existing 90-second guard check.
|
|
34
|
+
|
|
35
|
+
DSH Lab version/config preflight errors gain a JSON diagnostic suffix after
|
|
36
|
+
the stage-specific text, with fixed reason categories, child exit status,
|
|
37
|
+
timing and captured byte counts. The Lab CLI still reports errors on stderr
|
|
38
|
+
and exits 1; normal receipts, supported host versions and the 10/15-second
|
|
39
|
+
budgets retain their contracts. Consumers should not match the entire older
|
|
40
|
+
generic error sentence. Raw host/configuration output is not included.
|
|
41
|
+
The Kimi CLI doctor adds the separate `feedback` result described below.
|
|
42
|
+
An absent optional Stop passes; a configured Stop that fails configuration
|
|
43
|
+
or a requested probe exits 1 and makes drift `BROKEN`. This is an
|
|
44
|
+
upgrade-visible diagnostic change. Existing top-level fields and the
|
|
45
|
+
importable `check_kimi()` wrapper retain PreToolUse scope; Claude output is
|
|
46
|
+
unchanged. Configured Stop fields/helper bytes join the existing fingerprints.
|
|
47
|
+
The runtime fingerprint also includes package metadata, so version changes
|
|
48
|
+
can produce `DRIFTED` against an older baseline. Model delivery remains
|
|
49
|
+
`UNVERIFIED` even after a Bash live sentinel.
|
|
50
|
+
|
|
51
|
+
The Kimi Bash profile also adds exact `2.3.0` alongside `0.42.0` and `2.1.1`
|
|
52
|
+
after bounded prompt-CLI/ACP root-Bash trials. This is a declaration change;
|
|
53
|
+
the Core, adapter and bridge stay unchanged. Unlisted versions remain
|
|
54
|
+
`STALE`; a changed profile fingerprint can make an older baseline `DRIFTED`.
|
|
55
|
+
The separately pinned 2.1.1 Lab helper and subagent coverage do not expand.
|
|
56
|
+
See the [2.3.0 evidence](../reports/test-report-kimi-code-block.md#kimi-230-acceptance).
|
|
57
|
+
|
|
58
|
+
The later DSH compatibility work adds `0.2.1-alpha.4` to the default deletion
|
|
59
|
+
adapter alongside the two existing exact versions. Top-level engines and an
|
|
60
|
+
optional DSH peer align with the nested declaration, so the reviewed loaders
|
|
61
|
+
can enforce the list. This installs no production dependency and changes no
|
|
62
|
+
Core policy. Optional native-read fingerprints and Lab host formats remain
|
|
63
|
+
separately pinned. See [DSH compatibility](dsh-compatibility.md) and the
|
|
64
|
+
[native report](../reports/test-report-dsh-alpha4.md).
|
|
65
|
+
|
|
66
|
+
The maintainer selected 0.2.6 for this bounded feedback/diagnostic maintenance;
|
|
67
|
+
the additive surfaces below are carried as an explicit maintenance-version
|
|
68
|
+
exception. This does not relax the general minor-release rules or authorize
|
|
69
|
+
Core policy changes. These additions are absent from published 0.2.5.
|
|
70
|
+
|
|
22
71
|
### 0.2.5 feedback maintenance
|
|
23
72
|
|
|
24
73
|
Deletion rules, wildcard refusal, Decision/reason codes, CLI flags and exit
|
|
@@ -115,6 +164,7 @@ must accept the additional refusal reason and ignore unknown optional fields.
|
|
|
115
164
|
| `.agent-guard/exfil-allow.toml` exemption file | minor | Read from the workspace root only; values exempted by `sha256:...`, never by value |
|
|
116
165
|
| `doctor.py --check-drift` report and adapter `compatibility.json` profiles | minor | Additive local preflight. Without drift flags the doctor keeps its previous process-execution and exit behavior; `CURRENT` never promotes live interception above `UNVERIFIED` |
|
|
117
166
|
| `doctor.py --live-sentinel` and hashed hook receipt | minor | Explicit, opt-in real-host/model probe only. Default doctor behavior is unchanged; raw command/model output is not retained, and incomplete evidence is `INCONCLUSIVE` rather than PASS |
|
|
167
|
+
| Kimi doctor `feedback` object (0.2.6) | additive diagnostic | Existing top-level fields retain PreToolUse scope; optional Stop has separate configuration/local results and always-unverified model delivery. Absent Stop passes; a configured Stop failure exits 1 and prevents baseline creation/live sentinel. Configured Stop fields/helper join drift fingerprints. `check_kimi()` retains its PreToolUse-only contract; Claude output is unchanged. |
|
|
118
168
|
| Cross-vocabulary mismatch floor (`0.2.3-rc1`) | minor safety fix | At a selected-dialect command boundary, a supported destructive shape that produced no operation becomes target-free `UNKNOWN` → `BLOCK_UNDETERMINABLE_EFFECT`; it never borrows a compensation plan from another grammar |
|
|
119
169
|
|
|
120
170
|
### 0.2.5-rc1 assessment contract clarification (source candidate)
|
|
@@ -0,0 +1,65 @@
|
|
|
1
|
+
# DSH compatibility
|
|
2
|
+
|
|
3
|
+
The default deletion adapter in Agent Guard 0.2.6 admits three
|
|
4
|
+
exact DSH versions:
|
|
5
|
+
|
|
6
|
+
- `0.1.5-rc.1`
|
|
7
|
+
- `0.2.0-rc.2`
|
|
8
|
+
- `0.2.1-alpha.4`
|
|
9
|
+
|
|
10
|
+
Version 0.2.5 retains its two-version declaration. For alpha.4, upgrade to
|
|
11
|
+
0.2.6 or use a reviewed checkout containing the new declaration.
|
|
12
|
+
|
|
13
|
+
## Separate feature boundaries
|
|
14
|
+
|
|
15
|
+
| Feature | Admitted hosts | Additional conditions |
|
|
16
|
+
|---|---|---|
|
|
17
|
+
| Default deletion interception, recovery tools and prompt guidance | The three exact versions above | Python 3.9+ and Git; successful plugin activation |
|
|
18
|
+
| Optional native text-read redaction | `0.1.5-rc.1`, `0.2.0-rc.2` | Node 22, reviewed SDK file hashes, tool/provider shape and explicit opt-in |
|
|
19
|
+
| Lab native capture and paired review | `0.1.5-rc.1`, `0.2.0-rc.2` | Separate native-format/config contracts and operator review |
|
|
20
|
+
|
|
21
|
+
Alpha.4 support concerns the default deletion adapter. It does not admit
|
|
22
|
+
alpha.4 to the read prototype or Lab. The other versions examined during SDK
|
|
23
|
+
research remain candidates, including alpha.1–alpha.3; adjacent prereleases
|
|
24
|
+
and future versions are not implicitly supported.
|
|
25
|
+
|
|
26
|
+
## Declarations and loading
|
|
27
|
+
|
|
28
|
+
[`adapters/dsh/compatibility.json`](../../adapters/dsh/compatibility.json)
|
|
29
|
+
records the default adapter's exact tested versions and scope. Manifest tests
|
|
30
|
+
require its list to match all three declarations in `package.json`:
|
|
31
|
+
|
|
32
|
+
- Top-level `engines.dsh`, used preferentially by alpha.4's loader.
|
|
33
|
+
- Optional `peerDependencies["@deepseek-ai/dsh"]`, used by the older rc.2
|
|
34
|
+
compatibility checker. npm does not install this optional peer for the user.
|
|
35
|
+
- Nested `dsh.engines.dsh`, retained as bundle metadata.
|
|
36
|
+
|
|
37
|
+
The nested field alone did not enforce host-version admission. The two
|
|
38
|
+
reviewed compatibility helpers accept the three declared versions and reject
|
|
39
|
+
the tested unlisted versions without exemptions. Older loaders without that
|
|
40
|
+
helper still require the user to check this list and successful activation.
|
|
41
|
+
No adapter fallback bypasses a host compatibility rejection.
|
|
42
|
+
|
|
43
|
+
Resolve SDK packages from the selected DSH package's module context: SDKs may
|
|
44
|
+
be hoisted, and their versions can differ from the CLI root. The reviewed
|
|
45
|
+
legacy installation pairs root `0.1.5-rc.1` with key SDK `0.1.5-rc.2` artifacts.
|
|
46
|
+
|
|
47
|
+
## Evidence and limits
|
|
48
|
+
|
|
49
|
+
The [alpha.4 report](../reports/test-report-dsh-alpha4.md) records real CLI
|
|
50
|
+
Profile/Boot, native Bash, recovery and scripted root/child-agent checks.
|
|
51
|
+
The same source was checked on both previously admitted versions. These runs
|
|
52
|
+
made no external model requests and used isolated homes/profiles/workspaces.
|
|
53
|
+
|
|
54
|
+
The existing shell bridge already selects `execute().result()` when available
|
|
55
|
+
and retains the legacy `run()` path. Verdicts, compensation, rm wildcard
|
|
56
|
+
refusal and recovery formats are unchanged. A checker failure after the hook
|
|
57
|
+
registers denies the matched call. Missing/failed plugin initialization still
|
|
58
|
+
does not stop the host's other tools.
|
|
59
|
+
|
|
60
|
+
Native policy-forwarding checks used `danger-full-access`; unit coverage also
|
|
61
|
+
checks distinct root/child policies. This does not certify OS sandbox
|
|
62
|
+
confinement. Interactive approval UI, arbitrary PTC calls, concurrent agents,
|
|
63
|
+
other tools, GUI activation and real-model behavior require separate evidence.
|
|
64
|
+
`agent_guard_status` continues to distinguish local registration from live
|
|
65
|
+
interception and does not promote itself to a host certificate.
|
|
@@ -10,17 +10,18 @@ Agent Guard 提供恢复保护、外发检测和用户控制的行为验测。
|
|
|
10
10
|
|
|
11
11
|
## Select the package root
|
|
12
12
|
|
|
13
|
-
The stable release line is [0.2.
|
|
13
|
+
The stable release line is [0.2.6](../releases/release-notes-0.2.6.md), and the
|
|
14
14
|
prerelease line remains [0.2.5-rc3](../releases/release-notes-0.2.5-rc3.md).
|
|
15
15
|
The optional [0.2.4-hotfix.1](https://github.com/mokuyoaxis/agent-guard/releases/tag/0.2.4-hotfix.1)
|
|
16
16
|
backports quarantine protection onto the stable line.
|
|
17
|
-
Version 0.2.
|
|
18
|
-
|
|
19
|
-
|
|
17
|
+
Version 0.2.6 adds Kimi recovery feedback and diagnostics to the 0.2.5 base,
|
|
18
|
+
plus reviewed DSH alpha.4 and Kimi 2.3.0 Bash compatibility.
|
|
19
|
+
Its [GitHub release](https://github.com/mokuyoaxis/agent-guard/releases/tag/0.2.6)
|
|
20
|
+
and [npm version](https://www.npmjs.com/package/@mokuyoaxis/agent-guard/v/0.2.6)
|
|
20
21
|
establish package availability. Use a user-selected stable prefix:
|
|
21
22
|
|
|
22
23
|
```sh
|
|
23
|
-
npm install --prefix /absolute/path/to/agent-guard-install @mokuyoaxis/agent-guard@0.2.
|
|
24
|
+
npm install --prefix /absolute/path/to/agent-guard-install @mokuyoaxis/agent-guard@0.2.6
|
|
24
25
|
```
|
|
25
26
|
|
|
26
27
|
The package root is
|
|
@@ -36,7 +37,7 @@ For a reviewed local checkout or explicitly selected local tarball, use a
|
|
|
36
37
|
separate prefix:
|
|
37
38
|
|
|
38
39
|
```sh
|
|
39
|
-
npm install --offline --ignore-scripts --no-audit --no-fund --prefix /absolute/path/to/agent-guard-review /absolute/path/to/mokuyoaxis-agent-guard-0.2.
|
|
40
|
+
npm install --offline --ignore-scripts --no-audit --no-fund --prefix /absolute/path/to/agent-guard-review /absolute/path/to/mokuyoaxis-agent-guard-0.2.6.tgz
|
|
40
41
|
```
|
|
41
42
|
|
|
42
43
|
The review package root is
|
|
@@ -45,6 +46,22 @@ Keep the selected package/checkout path consistent when configuring the host.
|
|
|
45
46
|
Do not infer publication from a manifest/main commit or use an unscoped
|
|
46
47
|
same-name package. A checkout's default branch can differ from a tagged stable release.
|
|
47
48
|
|
|
49
|
+
The [0.2.6 additions](../releases/unreleased.md) require an upgraded package
|
|
50
|
+
or a checkout containing the corresponding files. In particular, 0.2.5 lacks
|
|
51
|
+
`adapters/kimi-code/stop_feedback.py`. Check the selected root before configuring
|
|
52
|
+
the optional Stop hook. Installing a new copy does not update another existing
|
|
53
|
+
installation or its host configuration.
|
|
54
|
+
|
|
55
|
+
Version 0.2.6 adds DSH `0.2.1-alpha.4` for the default deletion adapter.
|
|
56
|
+
Version 0.2.5 retains its earlier host declaration. Optional native read and Lab keep
|
|
57
|
+
their separate two-version scope. Check [DSH compatibility](../design/dsh-compatibility.md)
|
|
58
|
+
before enabling a profile.
|
|
59
|
+
|
|
60
|
+
The 0.2.6 Kimi Bash profile also adds exact version `2.3.0`, based on
|
|
61
|
+
[prompt CLI and ACP trials](../reports/test-report-kimi-code-block.md#kimi-230-acceptance).
|
|
62
|
+
Published 0.2.5 retains its earlier list. The Kimi Lab capture helper remains
|
|
63
|
+
pinned to 2.1.1; updating the Bash profile does not update that separate path.
|
|
64
|
+
|
|
48
65
|
Core needs Python 3.9+ and Git, with no third-party Python packages. POSIX
|
|
49
66
|
examples/bridges require a POSIX shell. The optional pinned DSH read path uses
|
|
50
67
|
Node 22; Kimi TOML helpers need Python 3.11+. Windows Core evidence does not
|
|
@@ -52,24 +69,47 @@ establish Windows-native hook bridge or full-suite portability.
|
|
|
52
69
|
|
|
53
70
|
## Set up a coding agent
|
|
54
71
|
|
|
55
|
-
Replace the root path
|
|
72
|
+
Replace the root path below with your installation path, then give the prompt
|
|
73
|
+
to your host's official coding agent. The
|
|
74
|
+
[integration guide](../../adapters/INTEGRATION.md) covers the hook requirements
|
|
75
|
+
and checks it should follow for the installed version.
|
|
76
|
+
|
|
77
|
+
We currently focus on DSH and Kimi Code. The Claude Code adapter remains a
|
|
78
|
+
reference; testing new Claude versions is paused. Other hosts are configured
|
|
79
|
+
locally by their official agents.
|
|
56
80
|
|
|
57
81
|
```text
|
|
58
82
|
Set up Agent Guard for this workspace using /absolute/path/to/agent-guard.
|
|
83
|
+
Before changing anything, read adapters/INTEGRATION.md in full, including
|
|
84
|
+
its verification and evidence requirements. Do this even if an adapter exists.
|
|
85
|
+
Read this host's current official hook documentation and inspect its installed version.
|
|
59
86
|
Identify the actual host version, tool names and hook/skill capabilities.
|
|
60
87
|
Read the README, Skill contracts and matching adapter guide; check Python/Git.
|
|
61
88
|
Use the selected checkout/package version and preserve existing settings.
|
|
89
|
+
For a host outside the DSH/Kimi maintenance focus, keep any new bridge and
|
|
90
|
+
configuration local; reuse the shared Core and versioned references.
|
|
91
|
+
Check which verification files that root includes. The npm package omits
|
|
92
|
+
tests/; use its local doctor/probes and report source unit tests as NOT_INCLUDED.
|
|
62
93
|
Respect already-approved paths and configuration scope. Ask only for missing
|
|
63
94
|
information or changes beyond that scope, including new dependencies.
|
|
64
95
|
Install/reference the relevant Skills. Configure a native hook only where a
|
|
65
96
|
blocking event is supported; otherwise report Skill/CLI-only operation.
|
|
97
|
+
Reuse the shared Core and its decisions; do not copy or relax its policy.
|
|
98
|
+
Check required project/hook trust through the host's normal review flow
|
|
99
|
+
within the authorized scope. Report activation as pending until it is complete.
|
|
100
|
+
Keep the user's selected account/provider; report model checks that cannot run.
|
|
66
101
|
Claude: adapters/claude/README.md. Kimi: adapters/kimi-code/README.md.
|
|
67
102
|
DSH: adapters/dsh/README.md. Other hosts: adapters/INTEGRATION.md.
|
|
68
103
|
Verify a harmless call. Submit BLOCK-shaped commands only as data to check.py;
|
|
69
104
|
never execute deletion of real data as a test. For Claude/Kimi, run the local
|
|
70
105
|
doctor, but do not treat PASS as proof of actual host interception.
|
|
106
|
+
Finish configuration and local probes with a clear handoff before fresh-host
|
|
107
|
+
verification. Report startup/reload requirements and preserve a checkpoint if
|
|
108
|
+
the step budget ends. UNVERIFIED host-interception/model-delivery fields are
|
|
109
|
+
expected local-doctor results; repeating the same probes will not clear them.
|
|
71
110
|
Report the host/version, installed paths, configuration scope, covered tools,
|
|
72
111
|
observed interception and unverified paths separately.
|
|
112
|
+
Use the handoff format in section 4 of adapters/INTEGRATION.md.
|
|
73
113
|
guard-lab is the user's controller, not a Skill to install into the tested
|
|
74
114
|
agent. Run real-host/model experiments only in an explicitly selected scope.
|
|
75
115
|
```
|
|
@@ -104,6 +144,14 @@ its result covers one sampled root-agent Bash call. See
|
|
|
104
144
|
[host drift](host-drift.md) and the
|
|
105
145
|
[capability matrix](harness-capabilities.md).
|
|
106
146
|
|
|
147
|
+
For Kimi's optional Stop feedback, choose whether the extra response is
|
|
148
|
+
wanted, follow the [separate setup](../../adapters/kimi-code/README.md#optional-recovery-feedback-unreleased-checkout-addition),
|
|
149
|
+
and start a new session. In 0.2.6, the doctor reports Stop
|
|
150
|
+
configuration and local execution separately under `feedback`. An absent Stop
|
|
151
|
+
is optional; a configured but invalid or failing Stop exits 1. `--probe` uses
|
|
152
|
+
synthetic records in temporary storage. `feedback.model_delivery` remains
|
|
153
|
+
`UNVERIFIED`; local PASS does not establish model receipt.
|
|
154
|
+
|
|
107
155
|
## Try the three paths
|
|
108
156
|
|
|
109
157
|
- **Recovery:** use the [delete Skill](../../skills/delete-guard/SKILL.md).
|
|
@@ -1,13 +1,18 @@
|
|
|
1
1
|
# Harness capability and evidence matrix
|
|
2
2
|
|
|
3
|
-
Stable release line: [0.2.
|
|
4
|
-
It retains RC1–RC3 and
|
|
5
|
-
|
|
3
|
+
Stable release line: [0.2.6](../releases/release-notes-0.2.6.md).
|
|
4
|
+
It retains RC1–RC3 and 0.2.5 feedback, with the additions described below.
|
|
5
|
+
Published prerelease, checked on 2026-10-19:
|
|
6
6
|
[0.2.5-rc3](../releases/release-notes-0.2.5-rc3.md).
|
|
7
7
|
Rows below retain their tested source/host versions and do not automatically
|
|
8
8
|
certify a later release. Local regression or package checks are separate from
|
|
9
9
|
new native-host/model evidence.
|
|
10
10
|
|
|
11
|
+
[0.2.6](../releases/release-notes-0.2.6.md) adds optional Kimi Stop
|
|
12
|
+
feedback, separate doctor checks, DSH Lab diagnostics, alpha.4 default
|
|
13
|
+
deletion compatibility and Kimi 2.3.0 root-Bash compatibility. These additions
|
|
14
|
+
are absent from 0.2.5. See [maintenance details](../releases/unreleased.md).
|
|
15
|
+
|
|
11
16
|
The new [research notes](../research/README.md) describe bounded private
|
|
12
17
|
experiments; their disclosure/delegation methods do not change the supported
|
|
13
18
|
production coverage in this matrix.
|
|
@@ -18,6 +23,10 @@ host does **not** mean that host intercepts tool calls, and an adapter returning
|
|
|
18
23
|
For an unlisted host, use the [self-adaptation guide](../../adapters/INTEGRATION.md)
|
|
19
24
|
and keep its native-interception status `UNVERIFIED` until independently tested.
|
|
20
25
|
|
|
26
|
+
We currently focus on DSH and Kimi Code. Claude Code's adapter and past
|
|
27
|
+
results remain available; testing new Claude versions is paused. For other
|
|
28
|
+
hosts, ask the official agent to configure and test the integration locally.
|
|
29
|
+
|
|
21
30
|
## Evidence levels
|
|
22
31
|
|
|
23
32
|
| Level | Meaning |
|
|
@@ -39,6 +48,12 @@ host-settings check; `local_probe: PASS` is not host interception. The doctor
|
|
|
39
48
|
always reports `host_interception: UNVERIFIED`. Only a separate real-host
|
|
40
49
|
trial with an independent non-execution check can establish the bounded
|
|
41
50
|
"Enforcement observed" level above. Neither doctor mode starts a model.
|
|
51
|
+
In 0.2.6, a separate Kimi `feedback` object checks optional
|
|
52
|
+
Stop configuration and, with `--probe`, synthetic feedback in temporary
|
|
53
|
+
storage. Missing Stop is `NOT_CONFIGURED` and does not fail the doctor;
|
|
54
|
+
configured Stop failures exit 1. Unreadable configuration is `UNVERIFIED`.
|
|
55
|
+
`feedback.model_delivery` stays `UNVERIFIED`, including after a Bash live
|
|
56
|
+
sentinel. See the [Stop doctor fields](../../adapters/kimi-code/README.md#stop-doctor-checks-unreleased).
|
|
42
57
|
The optional `--check-drift` mode additionally compares the installed host
|
|
43
58
|
version with a shipped compatibility profile and computes privacy-safe
|
|
44
59
|
configuration/runtime fingerprints. Its `CURRENT` status is static preflight
|
|
@@ -58,7 +73,10 @@ bounded "Enforcement observed" evidence only for that root-agent Bash call.
|
|
|
58
73
|
| DSH 0.1.5-rc.1 | `tools/pre-execute` for `bash`, plus model tools and prompt section | `kind: ask` | [Real host, no-model packaged-plugin probe](../reports/test-report-dsh-0.1.5-rc.1.md): benign execution, Core `BLOCK`, absent bypass marker, durable audit, and loaded-adapter Core-startup failure. A separate [real-model Lab baseline](../reports/test-report-dsh-guard-lab.md) stayed quiet with guard off, so it produced no L2 claim. | Model-proposed destructive `bash` enforcement, subagents, concurrency, ASK UI, hook absence and host upgrades remain unverified. The opt-in read path has separate evidence below. |
|
|
59
74
|
| DSH CLI 0.1.5-rc.1 / tools and FS 0.1.5-rc.2 / Node 22 | Default-off prototype for complete native text `read`; replaces structured value | Core ASK/BLOCK withheld | [Zero-model native probe](../reports/test-report-dsh-read-redaction.md): next request and durable JSONL. [Official Flash direct-read off/on](../reports/test-report-dsh-real-followup.md): supported synthetic secrets absent from guarded content/meta/session; useful config and line numbers preserved | Injection L2, pagination, custom finalizers/providers, PTC, early events, original tool arguments and other tools are outside this claim. Outgoing real-provider request bytes were not independently captured. |
|
|
60
75
|
| DSH 0.2.0-rc.2 / Node 22 | Default deletion adapter; optional complete text-read protection on reviewed local/sandbox FS; sampled PTC SDK Bash calls | Native ASK; Core read ASK/BLOCK withheld | [0.2.3 native review](../reports/test-report-release-readiness-0.2.3.md): deletion/read/next synthetic request/JSONL checks, zero external model calls. [0.2.4 official Flash PTC](../reports/test-report-dsh-0.2.4-ptc.md): real root and one child submit inner Bash reset collisions; matching refusal audits and intact files | Original root PTC task did not complete; a separate summary did. Arbitrary PTC Node APIs, other model-proposed calls, concurrency, ASK UI, Web activation and injection L2 remain unverified. Historical pending captures remain inconclusive. |
|
|
61
|
-
|
|
|
76
|
+
| DSH 0.2.1-alpha.4 / Node 22 (Agent Guard 0.2.6) | Default deletion adapter; three recovery tools and prompt guidance | Native approval service; sampled rejection and fixed answerer grant | [Native CLI report](../reports/test-report-dsh-alpha4.md): actual Profile/Boot, Bash allow/block, quarantine/restore, root/child BLOCK and ASK, per-session policy forwarding; no external model calls | No optional read or Lab admission. Interactive approval UI, OS sandbox confinement, arbitrary PTC, concurrent agents, GUI activation and real-model behavior are unverified. |
|
|
77
|
+
| Kimi Code 0.42.0 / 2.1.1 | `PreToolUse` for `Bash`; reuses Claude mapping with a host-specific ASK override | Adapter hard-denies ASK; live ASK sampled on 0.42.0 | [Bounded report](../reports/test-report-kimi-code-block.md): authenticated 2.1.1 root-Bash sentinels; older 0.42.0 root/subagent enforcement; later actual-CLI fixed-loopback fault cases on both versions | 2.1.1 subagents, concurrency and live ASK UI remain unverified. Missing/timed-out hooks allowed tools in the fault cases; other tools and arbitrary spawn failures remain uncovered. Client route labels do not identify remote model weights. |
|
|
78
|
+
| Kimi Code 2.3.0 (Agent Guard 0.2.6) | Root `Bash` PreToolUse in prompt CLI and ACP; ACP uses Kimi's local executor | Adapter hard-denies ASK | [Sixteen actual-host loopback trials](../reports/test-report-kimi-code-block.md#kimi-230-acceptance): allow/BLOCK/ASK, Python startup refusal, absence control, recovery; ACP process/payload cwd matched the session workspace despite a different service startup cwd | No external model calls. Subagents, other tools, client-provided terminals, concurrency, background execution and host-timeout behavior remain unverified. Hook absence allowed the inert marker. Web checks covered startup/status/shutdown only. |
|
|
79
|
+
| Kimi optional Stop, 0.42.0 / 2.1.1 / 2.3.0; Agent Guard 0.2.6 | Recovery guidance after the initial answer; separately configured POSIX hook | No additional approval path | [Feedback follow-up](../reports/test-report-kimi-code-block.md#recovery-feedback-follow-up-2026-10-20-unreleased-source): actual-CLI fixed-loopback delivery and one bounded 2.1.1 real-model session. [2.3.0 prompt/ACP follow-up](../reports/test-report-kimi-code-block.md#kimi-230-acceptance): actual txids, storage/GC guidance and byte-exact recovery with fixed responses | Adds a response after new compensation records. The initial answer may be inaccurate; emission is not acknowledgement. Shared-session actors, exhausted budgets and broader model/scheduling behavior retain their limits. |
|
|
62
80
|
| Codex CLI 0.154.0 (tested session) | Skill and production CLI on older source; no native interception adapter in this repository | CLI reports ASK; agent/user must decide | CLI acceptance only; see [report](../reports/test-report-codex-gpt-6-astra-high.md) | No automatic tool-call enforcement claim. |
|
|
63
81
|
| ZCode (Windows session; host version unrecorded) | Historical Skill/CLI and process-type `PreToolUse` trial | One ASK prompted the user; persistent approval then skipped the hook | [Windows evaluation](../reports/test-report-zcode-glm-flash.md) | No current-version native enforcement claim; the observed permission bypass and real Windows end-to-end gaps remain. |
|
|
64
82
|
| Other / unlisted hosts | No supported adapter by default | Host-specific | [Self-adaptation checklist](../../adapters/INTEGRATION.md), not a verification result | Requires a blocking pre-tool contract and independent host evidence; otherwise Skill/CLI only. |
|
|
@@ -18,6 +18,17 @@ that reliability problem; it is not a sandbox or a live-interception proof.
|
|
|
18
18
|
3. It fingerprints the local enforcement path (profile, bridge, adapter,
|
|
19
19
|
shared guard entry point, and Core Python files).
|
|
20
20
|
|
|
21
|
+
In [0.2.6](../releases/release-notes-0.2.6.md), a
|
|
22
|
+
configured optional Kimi Stop adds its normalized
|
|
23
|
+
fields to the configuration fingerprint and `stop_feedback.py` to the runtime
|
|
24
|
+
fingerprint. Adding, removing or changing it can therefore yield `DRIFTED`
|
|
25
|
+
against an earlier baseline. Without agent-guard Stop, the original
|
|
26
|
+
PreToolUse fingerprint remains unchanged. Unrelated Stop commands are ignored.
|
|
27
|
+
|
|
28
|
+
The runtime fingerprint includes `package.json`, so a package version change
|
|
29
|
+
also changes the fingerprint. Compare with the old baseline first; after an
|
|
30
|
+
intentional update, review the change and use a new baseline path.
|
|
31
|
+
|
|
21
32
|
This does not start a model or edit host configuration. The ordinary doctor
|
|
22
33
|
does not execute the host at all; host version discovery is opt-in through
|
|
23
34
|
`--check-drift`, `--baseline`, `--write-baseline`, or `--host-executable`.
|
|
@@ -31,6 +42,10 @@ python3 doctor.py kimi --probe --check-drift --json
|
|
|
31
42
|
when a host is installed under a wrapper name. The selected executable is run
|
|
32
43
|
only with the compatibility profile's version arguments.
|
|
33
44
|
|
|
45
|
+
Automatic discovery uses the doctor's current PATH. An interactive shell or
|
|
46
|
+
wrapper can select another installation. Check the user's actual launcher
|
|
47
|
+
and use `--host-executable` for the intended binary when those paths differ.
|
|
48
|
+
|
|
34
49
|
## Status vocabulary
|
|
35
50
|
|
|
36
51
|
| Status | Meaning |
|
|
@@ -48,6 +63,12 @@ it suitable for a local preflight. `CURRENT` is deliberately weaker than
|
|
|
48
63
|
version command, and local adapter process cannot prove that a live host
|
|
49
64
|
loaded or enforced the hook.
|
|
50
65
|
|
|
66
|
+
A configured Kimi Stop that fails configuration or a requested local probe
|
|
67
|
+
also makes drift `BROKEN`. Absent optional Stop is not a failure. Baseline
|
|
68
|
+
creation requires those requested Stop probes to pass as well; it does not
|
|
69
|
+
certify delivery. The separate `feedback.model_delivery` remains `UNVERIFIED`
|
|
70
|
+
even if the root-agent Bash live sentinel below passes.
|
|
71
|
+
|
|
51
72
|
## Privacy-minimal baselines
|
|
52
73
|
|
|
53
74
|
A baseline is optional. Create one only after reviewing a passing installation:
|
|
@@ -78,6 +99,17 @@ same OS privileges.
|
|
|
78
99
|
Profiles live beside their adapters as `compatibility.json`. They describe
|
|
79
100
|
only the host-facing version command and the narrow contract already covered
|
|
80
101
|
by that adapter. Core policy remains shared and is not copied into profiles.
|
|
102
|
+
|
|
103
|
+
The 0.2.6 Kimi profile lists exact versions `0.42.0`, `2.1.1` and
|
|
104
|
+
`2.3.0`. The [2.3.0 prompt/ACP root-Bash evidence](../reports/test-report-kimi-code-block.md#kimi-230-acceptance)
|
|
105
|
+
does not extend the separately pinned Lab helper, subagent coverage or real-model
|
|
106
|
+
claims. A valid 2.3.0 setup can now be `CURRENT` without a baseline; live
|
|
107
|
+
interception and feedback delivery still retain their independent status.
|
|
108
|
+
Updating the profile changes its runtime fingerprint, so an old baseline can
|
|
109
|
+
report `DRIFTED`. Review that change before selecting a new private baseline;
|
|
110
|
+
the update does not overwrite an existing one. Published 0.2.5 retains its
|
|
111
|
+
earlier list, and unlisted versions remain `STALE`.
|
|
112
|
+
|
|
81
113
|
Adding a profile for an unlisted host does not make it supported: the host
|
|
82
114
|
still needs a blocking pre-tool event and the bounded acceptance evidence in
|
|
83
115
|
the [capability matrix](harness-capabilities.md).
|
|
@@ -1,9 +1,11 @@
|
|
|
1
1
|
# Reading guard status and cleanup results
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
The CLI/DSH feedback below is included in
|
|
4
4
|
[0.2.5](../releases/release-notes-0.2.5.md).
|
|
5
5
|
They do not change deletion policy, wildcard handling, retention thresholds,
|
|
6
6
|
or the recovery format.
|
|
7
|
+
The final Kimi section describes the additions in
|
|
8
|
+
[0.2.6](../releases/release-notes-0.2.6.md).
|
|
7
9
|
|
|
8
10
|
## What the status establishes
|
|
9
11
|
|
|
@@ -96,3 +98,29 @@ Review the plan and selected transactions before choosing a purge. A manual
|
|
|
96
98
|
`--txid` selection is not limited to age/capacity eligibility. The 30-day and
|
|
97
99
|
5-GiB thresholds do not run GC automatically. `--execute` alone selects
|
|
98
100
|
nothing; GC does not prune Git stash snapshots.
|
|
101
|
+
|
|
102
|
+
## Kimi: tool success and recovery feedback
|
|
103
|
+
|
|
104
|
+
In the sampled Kimi 0.42.0, 2.1.1 and 2.3.0 paths, successful PreToolUse recovery
|
|
105
|
+
explanations did not enter the next model request. A successful Bash result
|
|
106
|
+
alone therefore does not tell the model that files were retained.
|
|
107
|
+
The [2.3.0 observations](../reports/test-report-kimi-code-block.md#kimi-230-acceptance)
|
|
108
|
+
used fixed responses through the actual prompt CLI and ACP host, with no
|
|
109
|
+
external model calls.
|
|
110
|
+
|
|
111
|
+
Version 0.2.6 provides a separate, opt-in POSIX Stop hook. It supplies
|
|
112
|
+
actual transaction IDs, state/restore commands, retained-storage guidance and
|
|
113
|
+
full GC commands, then asks for one extra response after the initial answer.
|
|
114
|
+
The initial answer may already be inaccurate, and the model can still omit
|
|
115
|
+
details. Emission cursors track notices, not model acknowledgement.
|
|
116
|
+
|
|
117
|
+
Restoring files returns them to their original location; it does not free
|
|
118
|
+
total disk space. GC permanently removes recovery copies and remains an
|
|
119
|
+
explicit operation. The Stop hook itself executes no restore or GC.
|
|
120
|
+
Published 0.2.5 lacks the Stop helper. See [setup and limits](../../adapters/kimi-code/README.md#optional-recovery-feedback-unreleased-checkout-addition)
|
|
121
|
+
and the [bounded real-host report](../reports/test-report-kimi-code-block.md).
|
|
122
|
+
In 0.2.6, the doctor separates PreToolUse from Stop
|
|
123
|
+
configuration and local feedback probes. `--probe` uses isolated synthetic
|
|
124
|
+
records and leaves existing recovery data alone. Stop's `model_delivery`
|
|
125
|
+
remains `UNVERIFIED`; local PASS does not establish model receipt. See the
|
|
126
|
+
[Stop doctor fields](../../adapters/kimi-code/README.md#stop-doctor-checks-unreleased).
|
|
@@ -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.
|