@agent-corpus/policy-manager 0.8.0 → 0.9.0
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 +24 -3
- package/dist/adapters.d.ts +9 -0
- package/dist/adapters.js +49 -15
- package/dist/cli.js +63 -18
- package/dist/flow.js +38 -4
- package/dist/grants.js +36 -7
- package/dist/permissive.d.ts +6 -0
- package/dist/permissive.js +69 -0
- package/dist/policy.js +10 -0
- package/dist/profile.d.ts +10 -0
- package/dist/profile.js +23 -0
- package/dist/review.d.ts +9 -0
- package/dist/review.js +16 -0
- package/dist/service.d.ts +14 -1
- package/dist/service.js +55 -4
- package/dist/session.d.ts +7 -0
- package/dist/session.js +34 -6
- package/dist/setup.d.ts +7 -0
- package/dist/setup.js +33 -5
- package/dist/shim.d.ts +24 -0
- package/dist/shim.js +114 -0
- package/dist/tools.d.ts +23 -0
- package/dist/tools.js +66 -0
- package/dist/types.d.ts +4 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -42,6 +42,8 @@ The canonical form is `policy-manager setup-hook <claude|codex|copilot>`. Each a
|
|
|
42
42
|
|
|
43
43
|
Setup merges only the managed hook definitions. Existing custom hooks, permissions, settings, allow rules, and deny rules remain. Repeated setup is idempotent. Package upgrades replace hooks carrying the managed marker; unmarked manual entries remain. Existing settings receive an owner-only backup, and updates use a temporary file with atomic replacement. Invalid JSON, unsupported schemas, symbolic links, concurrent setup, and detected concurrent edits fail without replacing the existing settings.
|
|
44
44
|
|
|
45
|
+
Setup also installs a small launcher named `pm` that runs this CLI, so a user can type `pm approve --last`: `~/.local/bin/pm` (a Node script, mode 0755) on macOS and Linux, `%LOCALAPPDATA%\agent-corpus\bin\pm.cmd` on Windows. It carries a marker with the version that wrote it. Setup replaces only a launcher it wrote for the same or an older version; a newer one, or a `pm` it did not write, is left alone and reported. Setup never edits `PATH`: the result's `shim.onPath` says whether the directory is on it, and the next steps say how to add it. `--shim-dir <directory>` puts the launcher elsewhere; with `--config-dir` and no `--shim-dir`, setup leaves the launcher alone.
|
|
46
|
+
|
|
45
47
|
`--dry-run` prints the target path, proposed managed hooks, and next steps without writing files or printing existing settings. `--config-dir <directory>` selects a harness configuration root for portable profiles or testing. Defaults respect `CLAUDE_CONFIG_DIR`, `CODEX_HOME`, and `COPILOT_HOME`, then use the standard user directories listed above. Setup refuses to activate an entrypoint inside a Git checkout, including an npm link into a checkout. Source builds can preview with `--dry-run`.
|
|
46
48
|
|
|
47
49
|
Start a new session after setup. Codex still requires explicit review and trust through `/hooks`; setup does not grant that trust. Existing sandbox controls and host permission rules continue to apply. Ambiguous requests retain the documented classification or human fallback; setup does not enable automatic AI fallback across unsupported native interfaces.
|
|
@@ -116,13 +118,24 @@ The report shows how many ambiguous requests were approved, denied, fell back to
|
|
|
116
118
|
|
|
117
119
|
## Approving from the terminal
|
|
118
120
|
|
|
119
|
-
Codex cannot ask in `PreToolUse`, so a request that needs a person is denied, and approving it in chat does not change the decision. The deny reason
|
|
121
|
+
Codex cannot ask in `PreToolUse`, so a request that needs a person is denied, and approving it in chat does not change the decision. The deny reason leads with what to do:
|
|
122
|
+
|
|
123
|
+
```text
|
|
124
|
+
⏸ Waiting for your approval. Not run: Protected path requires human approval.
|
|
125
|
+
Run in your own terminal, then say "retry":
|
|
126
|
+
pm approve --last
|
|
127
|
+
Add --session to also allow writes under /tmp/wt/.agent-config for the rest of this session.
|
|
128
|
+
Agent: stop now and end your turn; approving it in chat does not unblock it. Show the user the command above exactly, in a code block. Never run it yourself.
|
|
129
|
+
Request <64-character request hash>.
|
|
130
|
+
```
|
|
131
|
+
|
|
132
|
+
`pm approve --last` approves the newest request that any running policy session of this user sent to a person in the last 15 minutes. It shows the harness and session, the tool, the redacted request, the rule, and (with `--session`) the scope, then asks y/N; it refuses to run without an interactive terminal. To approve one exact request instead:
|
|
120
133
|
|
|
121
134
|
```sh
|
|
122
135
|
policy-manager approve <claude|codex|copilot> <session-id> <request-hash> [--session]
|
|
123
136
|
```
|
|
124
137
|
|
|
125
|
-
|
|
138
|
+
The deny reason uses `pm` when the managed launcher (see **Install native hooks**) for this version is installed and its directory is on `PATH`, and `node "<cli>" approve --last` otherwise. Then the agent retries the same request unchanged.
|
|
126
139
|
|
|
127
140
|
- **Once (default).** The next review of that exact request is approved, once per hook phase (`PreToolUse`, then `PermissionRequest`), and the grant is spent.
|
|
128
141
|
- **`--session`.** Also approves later requests in this session that hit the same rule for the same scope: a protected-path write under the same protected root of the same checkout (`<worktree>/.agent-config`, not `.claude` or another worktree), the same `humanPatterns` entries in the same checkout, or, for other rules, the exact same command in the same checkout. `approve --session` prints the scope before asking. Shell commands are covered only when they are a single simple command, so nothing else in a script hides behind the rule. Credential and secret reads, possible unrecoverable loss (force pushes, deleting unmerged work) and requests whose effect the engine could not determine (category `unknown`, such as an interpreter script) are approved once only, even with `--session`; the deny reason offers `--session` only when it applies.
|
|
@@ -194,6 +207,14 @@ Every command that could run is judged, not only the first. Understood: `;`, new
|
|
|
194
207
|
- **Variables after an assignment chain.** `S=/abs && H=x; use $S $H` treats `H` as assigned: a bare assignment with no command substitution and no redirection cannot fail, so the `&&` chain always reaches `H=x`. This holds only for uppercase names the shell does not reserve. zsh's lowercase specials, read-only or numeric specials (`UID`, `SECONDS`, `BASH*`, `ZSH*`, ...), a value with `$(...)`, `export NAME=value` and a prefix assignment (`X=1 cmd`) can fail or do not persist, so the chain may stop there and a later name is still an environment variable. A value used as the program (`P=rm; $P -rf x`) is resolved and judged as that program. The remaining window is a `readonly` or `typeset -i` that the user's shell startup files set on a name outside that list (such as `HISTFILE`): bash 5 in default mode may then return 1 without exiting, so the chain could stop there. That is outside what the script controls and is accepted.
|
|
195
208
|
- **Still sent to a human:** brace expansion (`{a,b}`, `{1..3}`; `{}` and `@{u}` are literal), arithmetic (`$((`, `$[`, `(( ))`), arrays, other parameter forms (`${X:=y}`, `${!X}`, `${X/a/b}`), `function name` definitions, unquoted heredocs whose body expands, and scripts that expand to more than a few hundred commands. `cloudWrites: "allow"` also approves non-destructive cloud changes.
|
|
196
209
|
|
|
210
|
+
#### Harness tools approved by default
|
|
211
|
+
|
|
212
|
+
Under the permissive profile, a harness tool that is not a shell, file, patch or MCP tool is approved without a prompt or classification: task control (`TaskStop`, `TaskOutput`), scheduling the session's own wakeup, listing agents, loading tool schemas, asking the user, plan mode, and tools a harness adds later. Shell, file and patch tools (`Bash`, `exec_command`, `Read`, `Write`, `Edit`, `apply_patch`, `Grep`, `Glob`, `view_image`, and `Monitor`, which runs a command) always get the engine's checks. So does any tool that runs code, writes to a running command, or touches files, whether listed (Codex `shell_command`, `local_shell`, `write_stdin`; Copilot `write_bash`) or only named like one (a name containing `bash`, `shell`, `exec`, `stdin`, `command`, `repl`, `eval`, `python`, `run`, `file`, `delete`, `move`, `edit` and similar), so a new one fails closed. A false positive such as `BashOutput` only costs a classification. MCP tools follow `mcpReadOnly`. The strict profile approves none of them by default.
|
|
213
|
+
|
|
214
|
+
`toolsDeny` keeps chosen tools on today's path, an AI classification for each call: `{ "claude": ["SendMessage", "WebFetch"], "codex": [], "copilot": [] }`, exact names, at most 100 per harness. An unknown harness, a non-list, or a name that is not a tool name makes the profile invalid (strict). The built-in deny list is empty.
|
|
215
|
+
|
|
216
|
+
Each default approval's audit `decision` record carries `defaultTool` with the tool name. `review-classifications` lists these tools newest first by when each was first seen, so a tool a harness newly added is noticed and can be put in `toolsDeny`.
|
|
217
|
+
|
|
197
218
|
#### MCP read-only tools
|
|
198
219
|
|
|
199
220
|
`mcpReadOnly` lists MCP tools that run without a prompt, in any `mode`. Each entry is an exact `mcp__<server>__<tool>` name, or a name whose tool segment ends in `*` (`mcp__docs__search_*`). Neither segment may contain `__`, and a wildcard approves only a tool whose whole tool segment (after `mcp__<server>__`) is free of `__`, so it cannot reach another server such as `github__get`. Whole-server wildcards (`mcp__github__*`), regular expressions and other tool names are rejected, and the list holds at most 200 entries of 128 characters. List only tools that cannot change anything and cannot return credentials: the tool name is all the engine checks, not the arguments. Prefer exact names. A prefix also covers tools that a server adds later, and read-looking prefixes can include secret readers: the GitHub server's `get_*` and `list_*` cover its secret-scanning alert tools, which return the detected secret.
|
|
@@ -210,7 +231,7 @@ A listed tool is approved. Any other MCP tool gets no decision from the policy m
|
|
|
210
231
|
|
|
211
232
|
Measure a profile against real usage with `policy-manager replay ~/.claude/projects --profile policy.json`: it replays the Bash commands recorded in Claude Code transcripts through the evaluator (nothing is executed) and prints the approval rate with and without the profile, plus the most common reasons that still need a human. Reports include short command excerpts, so keep them local.
|
|
212
233
|
|
|
213
|
-
Protected names (`.claude`, `.agent-config`, `AGENTS.md`, ...) are judged relative to the repository root, so a linked worktree under `<repo>/.claude/worktrees/<name>` is ordinary code while `<worktree>/.claude/settings.json` stays protected. `git config` is limited to a short allowlist of local, non-executable keys; hooks, aliases, credential helpers, URLs and `--global` always need a human. Read-only cloud verbs (`list`, `show`, `describe`, `get-*`) and `az boards query` (a WIQL read) are approved beyond the exact catalog unless the arguments name credentials or override the endpoint.
|
|
234
|
+
Protected names (`.claude`, `.agent-config`, `AGENTS.md`, ...) are judged relative to the repository root, so a linked worktree under `<repo>/.claude/worktrees/<name>` is ordinary code while `<worktree>/.claude/settings.json` stays protected. `git config` is limited to a short allowlist of local, non-executable keys; hooks, aliases, credential helpers, URLs and `--global` always need a human. For `--session`, a single shell command's scope comes from every word that could name a file it touches: non-option arguments, `--option=value` and `-oVALUE` values, and redirect targets (`>`, `>>`, `<`), so `printf x >> .agent-config/README.md` and `tee -a .agent-config/a` are covered like a patch, while a command that also names `AGENTS.md` or `.claude` is not. A variable assigned a single-quoted literal that is not one plain word (`Q='query($t: ID!)'`) is known only inside double quotes, so `gh api graphql -f query="$Q"` is judged on its value; an unquoted `$Q` stays unknown. Read-only cloud verbs (`list`, `show`, `describe`, `get-*`) and `az boards query` (a WIQL read) are approved beyond the exact catalog unless the arguments name credentials or override the endpoint.
|
|
214
235
|
|
|
215
236
|
`git worktree remove --force <path>` is approved when `<path>` is a linked worktree of the repository (listed by `git worktree list`, never the main worktree), resolves strictly inside a `scratchRoots` entry or the system temp directory, lies outside the main checkout, and holds no other worktree; exactly one `-f`/`--force` may be given (a second one also removes a locked worktree), and not after a command that can create symlinks. A worktree under the main checkout (`.worktrees/x`) still needs a human. `git worktree prune` with only `-n`/`-v` is approved: it drops records of worktrees whose directories are already gone.
|
|
216
237
|
|
package/dist/adapters.d.ts
CHANGED
|
@@ -3,6 +3,8 @@ export declare function normalize(harness: Request["harness"], payload: Record<s
|
|
|
3
3
|
export interface HookContext {
|
|
4
4
|
cliPath: string;
|
|
5
5
|
sessionId: string;
|
|
6
|
+
/** A managed `pm` launcher for this CLI is installed and on PATH. */
|
|
7
|
+
pmOnPath?: boolean;
|
|
6
8
|
}
|
|
7
9
|
/**
|
|
8
10
|
* The exact command the model is told to run to record a classification. A here-string, not a
|
|
@@ -21,6 +23,13 @@ export declare function looksLikeClassifyRecord(command: string): boolean;
|
|
|
21
23
|
export declare function looksLikeApproveGrant(command: string): boolean;
|
|
22
24
|
/** The command the user runs in their own terminal to approve a human decision. */
|
|
23
25
|
export declare function approveCommand(harness: Request["harness"], requestHash: string, context?: HookContext): string;
|
|
26
|
+
/** The short command the user runs to approve the newest blocked request (`approve --last`). */
|
|
27
|
+
export declare function approveLastCommand(context?: HookContext): string;
|
|
28
|
+
/**
|
|
29
|
+
* What Codex shows for a decision that needs a person. Codex cannot ask, so the agent must stop
|
|
30
|
+
* and hand the user one command; the first line says so, and the command stands on its own line.
|
|
31
|
+
*/
|
|
32
|
+
export declare function approveInstruction(decision: Decision, context?: HookContext): string;
|
|
24
33
|
export declare function hookResponse(harness: Request["harness"], phase: string, decision: Decision, context?: HookContext): Record<string, unknown>;
|
|
25
34
|
/** The exact stdout of a PreToolUse or PermissionRequest hook. Codex gets no output for no decision. */
|
|
26
35
|
export declare function hookOutput(harness: Request["harness"], phase: string, decision: Decision, context?: HookContext): string;
|
package/dist/adapters.js
CHANGED
|
@@ -99,12 +99,32 @@ export function approveCommand(harness, requestHash, context) {
|
|
|
99
99
|
? `node "${cliPath}" approve ${harness} ${context.sessionId} ${requestHash}`
|
|
100
100
|
: `policy-manager approve ${harness} <session-id> ${requestHash}`;
|
|
101
101
|
}
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
|
|
102
|
+
/** The short command the user runs to approve the newest blocked request (`approve --last`). */
|
|
103
|
+
export function approveLastCommand(context) {
|
|
104
|
+
if (context?.pmOnPath)
|
|
105
|
+
return "pm approve --last";
|
|
106
|
+
const cliPath = context && /^[A-Za-z]:\\/.test(context.cliPath)
|
|
107
|
+
? context.cliPath.replace(/\\/g, "/")
|
|
108
|
+
: context?.cliPath;
|
|
109
|
+
return cliPath ? `node "${cliPath}" approve --last` : "policy-manager approve --last";
|
|
110
|
+
}
|
|
111
|
+
/**
|
|
112
|
+
* What Codex shows for a decision that needs a person. Codex cannot ask, so the agent must stop
|
|
113
|
+
* and hand the user one command; the first line says so, and the command stands on its own line.
|
|
114
|
+
*/
|
|
115
|
+
export function approveInstruction(decision, context) {
|
|
116
|
+
return [
|
|
117
|
+
`⏸ Waiting for your approval. Not run: ${decision.reason}.`,
|
|
118
|
+
'Run in your own terminal, then say "retry":',
|
|
119
|
+
` ${approveLastCommand(context)}`,
|
|
120
|
+
...(decision.sessionGrantable
|
|
121
|
+
? [
|
|
122
|
+
`Add --session to also allow ${decision.sessionScopeLabel ?? "the same rule for the same scope"} for the rest of this session.`,
|
|
123
|
+
]
|
|
124
|
+
: []),
|
|
125
|
+
"Agent: stop now and end your turn; approving it in chat does not unblock it. Show the user the command above exactly, in a code block. Never run it yourself.",
|
|
126
|
+
`Request ${decision.requestHash}.`,
|
|
127
|
+
].join("\n");
|
|
108
128
|
}
|
|
109
129
|
/** What a blocked ambiguous request tells the model to do. Never ask for human approval here. */
|
|
110
130
|
function classifyInstruction(harness, decision, context) {
|
|
@@ -142,11 +162,19 @@ export function hookResponse(harness, phase, decision, context) {
|
|
|
142
162
|
return decision.decision === "approve" ? { behavior: "allow" } : {};
|
|
143
163
|
return decision.decision === "approve"
|
|
144
164
|
? { permissionDecision: "allow" }
|
|
145
|
-
: {
|
|
165
|
+
: {
|
|
166
|
+
permissionDecision: "ask",
|
|
167
|
+
permissionDecisionReason: decision.reason,
|
|
168
|
+
};
|
|
146
169
|
}
|
|
147
170
|
if (phase === "PermissionRequest")
|
|
148
171
|
return decision.decision === "approve"
|
|
149
|
-
? {
|
|
172
|
+
? {
|
|
173
|
+
hookSpecificOutput: {
|
|
174
|
+
hookEventName: phase,
|
|
175
|
+
decision: { behavior: "allow" },
|
|
176
|
+
},
|
|
177
|
+
}
|
|
150
178
|
: {};
|
|
151
179
|
// Codex rejects PreToolUse `permissionDecision: "allow"` without `updatedInput` ("unsupported
|
|
152
180
|
// permissionDecision:allow") and marks the hook failed. An approval there is no decision at all;
|
|
@@ -154,7 +182,12 @@ export function hookResponse(harness, phase, decision, context) {
|
|
|
154
182
|
if (decision.decision === "approve")
|
|
155
183
|
return harness === "codex"
|
|
156
184
|
? {}
|
|
157
|
-
: {
|
|
185
|
+
: {
|
|
186
|
+
hookSpecificOutput: {
|
|
187
|
+
hookEventName: phase,
|
|
188
|
+
permissionDecision: "allow",
|
|
189
|
+
},
|
|
190
|
+
};
|
|
158
191
|
// Codex parses permissionDecision "ask" but does not support it: it marks the hook failed and
|
|
159
192
|
// runs the tool anyway (https://developers.openai.com/codex/hooks). Only "deny" stops a command,
|
|
160
193
|
// so a decision that needs a human is a deny. Approving it in chat does not change the decision;
|
|
@@ -162,16 +195,17 @@ export function hookResponse(harness, phase, decision, context) {
|
|
|
162
195
|
// ambiguous request (needsClassification) is classified, and a retry then sees the approval.
|
|
163
196
|
// Codex's own approval prompt (PermissionRequest, above) still handles the requests it asks about.
|
|
164
197
|
if (harness === "codex") {
|
|
165
|
-
const
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
|
|
169
|
-
|
|
198
|
+
const classify = decision.needsClassification === true && decision.classification !== "fallback";
|
|
199
|
+
const reason = !classify && !decision.userOnly
|
|
200
|
+
? approveInstruction(decision, context)
|
|
201
|
+
: `Policy manager: ${decision.reason}. This needs a human decision and was not run. ${classify
|
|
202
|
+
? "Classify it with the session policy-manager agent and retry. If it is not classified as approved, the retry is blocked with the command the user runs to approve it."
|
|
203
|
+
: "Do not run approve yourself: ask the user to approve the original request from their own terminal."} Request ${decision.requestHash}.`;
|
|
170
204
|
return {
|
|
171
205
|
hookSpecificOutput: {
|
|
172
206
|
hookEventName: phase,
|
|
173
207
|
permissionDecision: "deny",
|
|
174
|
-
permissionDecisionReason:
|
|
208
|
+
permissionDecisionReason: reason,
|
|
175
209
|
},
|
|
176
210
|
};
|
|
177
211
|
}
|
package/dist/cli.js
CHANGED
|
@@ -11,16 +11,18 @@ import { HUMAN_REVIEW_PRINCIPLE } from "./principle.js";
|
|
|
11
11
|
import { defaultProfilePath, loadProfile, parseProfile } from "./profile.js";
|
|
12
12
|
import { replayTranscripts } from "./replay.js";
|
|
13
13
|
import { formatReview, reviewClassifications, sessionDirectories } from "./review.js";
|
|
14
|
-
import { send, serve, start, stop } from "./service.js";
|
|
14
|
+
import { latestHumanDecision, send, sendTo, serve, start, stop } from "./service.js";
|
|
15
15
|
import { SetupError, setupHook } from "./setup.js";
|
|
16
|
+
import { cliVersion, inspectShim, shimDirectory } from "./shim.js";
|
|
16
17
|
const usage = `policy-manager usage [--json]
|
|
17
18
|
policy-manager hook <claude|codex|copilot> <SessionStart|PreToolUse|PermissionRequest|PostToolUse|PostToolUseFailure|SessionEnd>
|
|
18
19
|
policy-manager review <claude|codex|copilot> <session-id> # normalized request JSON on stdin
|
|
19
20
|
policy-manager classify <claude|codex|copilot> <session-id> # {requestHash,category,confidence} on stdin
|
|
20
21
|
policy-manager record <claude|codex|copilot> <session-id> # host-reported human response or execution result JSON
|
|
21
|
-
policy-manager approve
|
|
22
|
-
policy-manager
|
|
23
|
-
policy-manager setup-hook
|
|
22
|
+
policy-manager approve --last [--session] # the user, in their own terminal: allow the newest blocked request once, or its rule and scope for the session
|
|
23
|
+
policy-manager approve <claude|codex|copilot> <session-id> <request-hash> [--session] # the same for one exact request
|
|
24
|
+
policy-manager setup-hook <claude|codex|copilot> [--dry-run] [--config-dir <harness-config-directory>] [--shim-dir <directory>]
|
|
25
|
+
policy-manager setup-hook-claude|setup-hook-codex|setup-hook-copilot [--dry-run] [--config-dir <directory>] [--shim-dir <directory>]
|
|
24
26
|
policy-manager config <claude|codex|copilot> <absolute-installed-cli-path>
|
|
25
27
|
policy-manager profile validate <file> # check a policy profile without installing it
|
|
26
28
|
policy-manager profile install <file> # install it to the user config directory outside Git
|
|
@@ -50,6 +52,16 @@ const args = process.argv.slice(2);
|
|
|
50
52
|
const [action, harnessArg, phase] = args;
|
|
51
53
|
const harness = harnessArg;
|
|
52
54
|
const cliPath = fileURLToPath(import.meta.url);
|
|
55
|
+
/** Whether a managed `pm` launcher for this CLI is installed and on PATH. */
|
|
56
|
+
function pmReady() {
|
|
57
|
+
try {
|
|
58
|
+
const status = inspectShim(shimDirectory(), cliPath, cliVersion(cliPath));
|
|
59
|
+
return status.state === "current" && status.onPath;
|
|
60
|
+
}
|
|
61
|
+
catch {
|
|
62
|
+
return false;
|
|
63
|
+
}
|
|
64
|
+
}
|
|
53
65
|
try {
|
|
54
66
|
if (action === "usage" || !action)
|
|
55
67
|
console.log(args.includes("--json") ? JSON.stringify({ usage }) : usage);
|
|
@@ -58,11 +70,16 @@ try {
|
|
|
58
70
|
const selected = (alias ?? harnessArg);
|
|
59
71
|
const { values } = parseArgs({
|
|
60
72
|
args: args.slice(alias ? 1 : 2),
|
|
61
|
-
options: {
|
|
73
|
+
options: {
|
|
74
|
+
"dry-run": { type: "boolean" },
|
|
75
|
+
"config-dir": { type: "string" },
|
|
76
|
+
"shim-dir": { type: "string" },
|
|
77
|
+
},
|
|
62
78
|
});
|
|
63
79
|
console.log(JSON.stringify(setupHook(selected, cliPath, {
|
|
64
80
|
dryRun: values["dry-run"],
|
|
65
81
|
configDirectory: values["config-dir"],
|
|
82
|
+
shimDirectory: values["shim-dir"],
|
|
66
83
|
}), null, 2));
|
|
67
84
|
}
|
|
68
85
|
else if (action === "config")
|
|
@@ -75,6 +92,7 @@ try {
|
|
|
75
92
|
mode: profile.mode,
|
|
76
93
|
cloudWrites: profile.cloudWrites,
|
|
77
94
|
mcpReadOnly: profile.mcpReadOnly.length,
|
|
95
|
+
toolsDeny: Object.values(profile.toolsDeny).reduce((n, list) => n + list.length, 0),
|
|
78
96
|
digest: profile.digest,
|
|
79
97
|
};
|
|
80
98
|
if (harnessArg === "install") {
|
|
@@ -123,19 +141,37 @@ try {
|
|
|
123
141
|
else if (action === "approve") {
|
|
124
142
|
const { values, positionals } = parseArgs({
|
|
125
143
|
args: args.slice(1),
|
|
126
|
-
options: { session: { type: "boolean" } },
|
|
144
|
+
options: { session: { type: "boolean" }, last: { type: "boolean" } },
|
|
127
145
|
allowPositionals: true,
|
|
128
146
|
});
|
|
129
|
-
const [
|
|
130
|
-
|
|
131
|
-
|
|
132
|
-
|
|
133
|
-
|
|
134
|
-
|
|
135
|
-
|
|
136
|
-
|
|
137
|
-
|
|
138
|
-
|
|
147
|
+
const usageText = "Usage: policy-manager approve --last [--session], or approve <claude|codex|copilot> <session-id> <request-hash> [--session]";
|
|
148
|
+
let directory;
|
|
149
|
+
let requestHash;
|
|
150
|
+
if (values.last) {
|
|
151
|
+
if (positionals.length)
|
|
152
|
+
throw new ApproveError(usageText);
|
|
153
|
+
if (!process.stdin.isTTY || !process.stdout.isTTY)
|
|
154
|
+
throw new ApproveError("Run approve yourself in an interactive terminal; it asks you to confirm the request.");
|
|
155
|
+
const latest = await latestHumanDecision();
|
|
156
|
+
if (!latest)
|
|
157
|
+
throw new ApproveError("No running policy session has a request waiting for approval from the last 15 minutes. Have the agent retry so it is blocked again.");
|
|
158
|
+
({ directory, requestHash } = latest);
|
|
159
|
+
console.log(`Session: ${latest.harness} ${latest.sessionId}`);
|
|
160
|
+
}
|
|
161
|
+
else {
|
|
162
|
+
const [target, sessionId, hashArg] = positionals;
|
|
163
|
+
if (!["claude", "codex", "copilot"].includes(target) ||
|
|
164
|
+
!/^[A-Za-z0-9_.-]+$/.test(sessionId ?? "") ||
|
|
165
|
+
!/^[a-f0-9]{64}$/.test(hashArg ?? ""))
|
|
166
|
+
throw new ApproveError(usageText);
|
|
167
|
+
if (!process.stdin.isTTY || !process.stdout.isTTY)
|
|
168
|
+
throw new ApproveError("Run approve yourself in an interactive terminal; it asks you to confirm the request.");
|
|
169
|
+
if (!existsSync(sessionDirectoryPath(target, sessionId)))
|
|
170
|
+
throw new ApproveError("No policy service is running for that session.");
|
|
171
|
+
directory = sessionDirectoryPath(target, sessionId);
|
|
172
|
+
requestHash = hashArg;
|
|
173
|
+
}
|
|
174
|
+
const ask = (confirm) => sendTo(directory, {
|
|
139
175
|
action: "grant",
|
|
140
176
|
grant: { requestHash, confirm, session: values.session === true },
|
|
141
177
|
});
|
|
@@ -147,7 +183,10 @@ try {
|
|
|
147
183
|
console.log("This request can only be approved once: credential reads, possible unrecoverable loss and requests whose effect could not be determined are never approved for a session.");
|
|
148
184
|
if (preview.scope === "session" && preview.sessionScope)
|
|
149
185
|
console.log(`Scope: ${preview.sessionScope}`);
|
|
150
|
-
const prompt = createInterface({
|
|
186
|
+
const prompt = createInterface({
|
|
187
|
+
input: process.stdin,
|
|
188
|
+
output: process.stdout,
|
|
189
|
+
});
|
|
151
190
|
const answer = await prompt.question(preview.scope === "session"
|
|
152
191
|
? "Allow this and later requests in this session that hit the same rule for the same scope? [y/N] "
|
|
153
192
|
: "Allow this request once? [y/N] ");
|
|
@@ -188,7 +227,12 @@ try {
|
|
|
188
227
|
const context = `Policy service started. Audit log: ${join(directory, "audit.jsonl")}. Native hooks route tool and permission requests directly to the deterministic service. An ambiguous request is blocked once with instructions to have the policy-manager agent classify it and then retry; the person is asked only if classification fails. ${HUMAN_REVIEW_PRINCIPLE} If .agent-config/agents/policy-manager.md exists, read it before creating a read-only policy-manager agent. Never ask an agent to approve its own tools.`;
|
|
189
228
|
console.log(JSON.stringify(harness === "copilot"
|
|
190
229
|
? { additionalContext: context }
|
|
191
|
-
: {
|
|
230
|
+
: {
|
|
231
|
+
hookSpecificOutput: {
|
|
232
|
+
hookEventName: phase,
|
|
233
|
+
additionalContext: context,
|
|
234
|
+
},
|
|
235
|
+
}));
|
|
192
236
|
}
|
|
193
237
|
else if (phase === "PostToolUse" || phase === "PostToolUseFailure") {
|
|
194
238
|
await send(harness, request.sessionId, {
|
|
@@ -206,6 +250,7 @@ try {
|
|
|
206
250
|
const output = hookOutput(harness, phase, decision, {
|
|
207
251
|
cliPath,
|
|
208
252
|
sessionId: request.sessionId,
|
|
253
|
+
pmOnPath: decision.decision === "human" && harness === "codex" && pmReady(),
|
|
209
254
|
});
|
|
210
255
|
if (output)
|
|
211
256
|
console.log(output);
|
package/dist/flow.js
CHANGED
|
@@ -68,6 +68,16 @@ function replace(target, source) {
|
|
|
68
68
|
}
|
|
69
69
|
// --- words ------------------------------------------------------------------------------------
|
|
70
70
|
const isKnown = (values) => !!values?.length && values.every((v) => SIMPLE_VALUE.test(v));
|
|
71
|
+
/** The one literal value of a variable, usable only inside double quotes. */
|
|
72
|
+
function literalValue(values) {
|
|
73
|
+
const value = values?.length === 1 ? values[0] : undefined;
|
|
74
|
+
return value !== undefined &&
|
|
75
|
+
value.length <= 4096 &&
|
|
76
|
+
!value.includes("\0") &&
|
|
77
|
+
!value.includes(SUBSTITUTION)
|
|
78
|
+
? value
|
|
79
|
+
: undefined;
|
|
80
|
+
}
|
|
71
81
|
/**
|
|
72
82
|
* Environment variables whose value is harmless to print or pass on. Any other variable the script
|
|
73
83
|
* did not assign could hold a credential (`$GITHUB_TOKEN`, `$AWS_SECRET_ACCESS_KEY`), so using it
|
|
@@ -202,6 +212,9 @@ function instantiate(word, known, env, state) {
|
|
|
202
212
|
}
|
|
203
213
|
else if (known.has(part.name))
|
|
204
214
|
text += applyParamOp(env[part.name] ?? "", part.op);
|
|
215
|
+
else if (part.quoted && !part.op && literalValue(state?.vars.get(part.name)) !== undefined)
|
|
216
|
+
// Inside double quotes a literal value is one word with no further expansion.
|
|
217
|
+
text += literalValue(state?.vars.get(part.name));
|
|
205
218
|
else {
|
|
206
219
|
text += SUBSTITUTION;
|
|
207
220
|
// "$@" is one word per parameter even when quoted.
|
|
@@ -458,7 +471,11 @@ function splitAssignment(word) {
|
|
|
458
471
|
return undefined;
|
|
459
472
|
return {
|
|
460
473
|
name,
|
|
461
|
-
value: {
|
|
474
|
+
value: {
|
|
475
|
+
...word,
|
|
476
|
+
parts: [first.slice(eq + 1), ...word.parts.slice(1)],
|
|
477
|
+
subs: [],
|
|
478
|
+
},
|
|
462
479
|
};
|
|
463
480
|
}
|
|
464
481
|
/** grep and rg options whose value is a file-name glob. */
|
|
@@ -607,6 +624,13 @@ function runSimple(ctx, node, state, stage, piped) {
|
|
|
607
624
|
continue;
|
|
608
625
|
}
|
|
609
626
|
}
|
|
627
|
+
// A single literal value that is not one plain word (`Q='query($t: ID!)'`) is kept for
|
|
628
|
+
// double-quoted use only: isKnown rejects it, so an unquoted `$Q` stays unknown.
|
|
629
|
+
const set = [...new Set(texts)];
|
|
630
|
+
if (set.length === 1 && literalValue(set) !== undefined) {
|
|
631
|
+
state.vars.set(a.name, set);
|
|
632
|
+
continue;
|
|
633
|
+
}
|
|
610
634
|
state.vars.set(a.name, null);
|
|
611
635
|
}
|
|
612
636
|
ctx.box.last = result(request, "code-read", "Variable assignment", true);
|
|
@@ -672,7 +696,10 @@ function runSimple(ctx, node, state, stage, piped) {
|
|
|
672
696
|
}
|
|
673
697
|
/** In a loop, a pipeline or a background job, a later command can run first. */
|
|
674
698
|
function fillFor(ctx, piped) {
|
|
675
|
-
return {
|
|
699
|
+
return {
|
|
700
|
+
script: ctx.box.script,
|
|
701
|
+
reorder: ctx.loop > 0 || piped || !!ctx.reorder,
|
|
702
|
+
};
|
|
676
703
|
}
|
|
677
704
|
/**
|
|
678
705
|
* Programs that create no symlink: they read, print, or write regular files only. Shells are here
|
|
@@ -1500,13 +1527,20 @@ export function commandDecision(request, command, profile, depth = 0, start = [r
|
|
|
1500
1527
|
loop: 0,
|
|
1501
1528
|
calls: 0,
|
|
1502
1529
|
positional: !/argv/.test(command),
|
|
1503
|
-
box: {
|
|
1530
|
+
box: {
|
|
1531
|
+
calls: 0,
|
|
1532
|
+
script: fill?.script ?? { tainted: false, approved: false, jobs: 0 },
|
|
1533
|
+
},
|
|
1504
1534
|
...(fill?.reorder ? { reorder: true } : {}),
|
|
1505
1535
|
};
|
|
1506
1536
|
const opening = script.items[0];
|
|
1507
1537
|
if (depth === 0 && opening && !opening.background)
|
|
1508
1538
|
ctx.box.first = opening.node.first;
|
|
1509
|
-
const refusal = runList(ctx, script, {
|
|
1539
|
+
const refusal = runList(ctx, script, {
|
|
1540
|
+
cwds: [...start],
|
|
1541
|
+
vars: new Map(),
|
|
1542
|
+
funcs: new Map(),
|
|
1543
|
+
});
|
|
1510
1544
|
return refusal ?? ctx.box.last ?? human(request, "unknown", "Empty command");
|
|
1511
1545
|
}
|
|
1512
1546
|
//# sourceMappingURL=flow.js.map
|
package/dist/grants.js
CHANGED
|
@@ -2,6 +2,7 @@ import { existsSync, statSync } from "node:fs";
|
|
|
2
2
|
import { dirname, join, relative } from "node:path";
|
|
3
3
|
import { canonical, git, inside, policyState, protectedPath, resolveWord, sensitive, } from "./evidence.js";
|
|
4
4
|
import { SHELL_TOOLS, words } from "./policy.js";
|
|
5
|
+
import { parseShell, SUBSTITUTION } from "./shell.js";
|
|
5
6
|
export const PROTECTED_PATH = "Protected path requires human approval";
|
|
6
7
|
export const HUMAN_PATTERN = "Matches an organization human-approval pattern";
|
|
7
8
|
const FILE_TOOLS = new Set(["Write", "create", "write_file", "Edit", "edit", "MultiEdit"]);
|
|
@@ -41,6 +42,40 @@ function targets(request) {
|
|
|
41
42
|
}
|
|
42
43
|
return undefined;
|
|
43
44
|
}
|
|
45
|
+
/**
|
|
46
|
+
* Every word of a single shell command that could name a file it touches: non-option arguments,
|
|
47
|
+
* the value of `--option=value` or `-oVALUE`, and redirect targets (`> f`, `>> f`, `< f`). One program, no
|
|
48
|
+
* operators, pipes, substitutions or variables. A word that is not a path only adds a scope, so
|
|
49
|
+
* treating it as one fails closed.
|
|
50
|
+
*/
|
|
51
|
+
function shellPaths(request) {
|
|
52
|
+
const command = request.input.command ?? request.input.cmd;
|
|
53
|
+
if (!SHELL_TOOLS.has(request.tool) || typeof command !== "string")
|
|
54
|
+
return undefined;
|
|
55
|
+
const pipelines = parseShell(command);
|
|
56
|
+
const only = pipelines?.length === 1 && pipelines[0]?.length === 1 ? pipelines[0][0] : undefined;
|
|
57
|
+
if (!only || only.env.length || only.subs.length || only.stdin !== undefined)
|
|
58
|
+
return undefined;
|
|
59
|
+
const texts = [...only.argv, ...only.redirects.map((r) => r.target)];
|
|
60
|
+
if (texts.some((text) => text.includes(SUBSTITUTION)))
|
|
61
|
+
return undefined;
|
|
62
|
+
const paths = [];
|
|
63
|
+
for (const word of only.argv.slice(1)) {
|
|
64
|
+
if (!word.startsWith("-"))
|
|
65
|
+
paths.push(word);
|
|
66
|
+
else if (word.startsWith("--")) {
|
|
67
|
+
if (word.includes("="))
|
|
68
|
+
paths.push(word.slice(word.indexOf("=") + 1));
|
|
69
|
+
}
|
|
70
|
+
// `-oFILE` attaches a value to a short option; flags like `-rf` only add a harmless path.
|
|
71
|
+
else if (word.length > 2)
|
|
72
|
+
paths.push(word.slice(2).replace(/^=/, ""));
|
|
73
|
+
}
|
|
74
|
+
for (const redirect of only.redirects)
|
|
75
|
+
if (redirect.op !== ">&" && redirect.target !== "/dev/null")
|
|
76
|
+
paths.push(redirect.target);
|
|
77
|
+
return paths.filter((path) => path.length > 0);
|
|
78
|
+
}
|
|
44
79
|
/** A simple command (one program, no operators, expansions or redirects) as words. */
|
|
45
80
|
function simple(request) {
|
|
46
81
|
const command = request.input.command ?? request.input.cmd;
|
|
@@ -62,13 +97,7 @@ function simple(request) {
|
|
|
62
97
|
export function grantScope(request, decision, profile) {
|
|
63
98
|
try {
|
|
64
99
|
if (decision.reason === PROTECTED_PATH) {
|
|
65
|
-
|
|
66
|
-
if (!paths) {
|
|
67
|
-
const argv = simple(request);
|
|
68
|
-
paths = argv
|
|
69
|
-
?.slice(1)
|
|
70
|
-
.filter((word) => !word.startsWith("-") && (word.includes("/") || word.startsWith(".")));
|
|
71
|
-
}
|
|
100
|
+
const paths = targets(request) ?? shellPaths(request);
|
|
72
101
|
if (!paths?.length)
|
|
73
102
|
return undefined;
|
|
74
103
|
const roots = new Set();
|
package/dist/permissive.d.ts
CHANGED
|
@@ -3,6 +3,12 @@ import { commandDecision } from "./flow.js";
|
|
|
3
3
|
import type { Profile } from "./profile.js";
|
|
4
4
|
import { type Redirect, type SimpleCommand } from "./shell.js";
|
|
5
5
|
import type { Decision, Request } from "./types.js";
|
|
6
|
+
/**
|
|
7
|
+
* The files `sort` writes: its `-o`/`--output` file and its `-T`/`--temporary-directory`. Options
|
|
8
|
+
* are parsed as GNU getopt does (clustered short options, exact or unique long prefixes).
|
|
9
|
+
* Undefined when it may run another program (`--compress-program`) or an option is unknown.
|
|
10
|
+
*/
|
|
11
|
+
export declare function sortWrites(args: string[]): string[] | undefined;
|
|
6
12
|
export declare const BANNED_ENV: RegExp;
|
|
7
13
|
export declare function human(request: Request, category: Decision["category"], reason: string): Decision;
|
|
8
14
|
export declare function permissiveRead(cwd: string, input: string): {
|
package/dist/permissive.js
CHANGED
|
@@ -51,6 +51,65 @@ const WRITERS = new Set([
|
|
|
51
51
|
"chown",
|
|
52
52
|
]);
|
|
53
53
|
const WRAPPERS = new Set(["env", "nohup", "time", "command", "nice", "timeout", "xargs"]);
|
|
54
|
+
const SORT_LONG = [
|
|
55
|
+
...["ignore-leading-blanks", "dictionary-order", "ignore-case", "general-numeric-sort"],
|
|
56
|
+
...["ignore-nonprinting", "month-sort", "human-numeric-sort", "numeric-sort", "random-sort"],
|
|
57
|
+
...["random-source", "reverse", "sort", "version-sort", "batch-size", "check", "debug"],
|
|
58
|
+
...["compress-program", "files0-from", "key", "merge", "output", "stable", "buffer-size"],
|
|
59
|
+
...["field-separator", "temporary-directory", "parallel", "unique", "zero-terminated"],
|
|
60
|
+
...["help", "version"],
|
|
61
|
+
];
|
|
62
|
+
const SORT_LONG_VALUE = new Set([
|
|
63
|
+
...["random-source", "sort", "batch-size", "compress-program", "files0-from", "key"],
|
|
64
|
+
...["output", "buffer-size", "field-separator", "temporary-directory", "parallel"],
|
|
65
|
+
]);
|
|
66
|
+
/**
|
|
67
|
+
* The files `sort` writes: its `-o`/`--output` file and its `-T`/`--temporary-directory`. Options
|
|
68
|
+
* are parsed as GNU getopt does (clustered short options, exact or unique long prefixes).
|
|
69
|
+
* Undefined when it may run another program (`--compress-program`) or an option is unknown.
|
|
70
|
+
*/
|
|
71
|
+
export function sortWrites(args) {
|
|
72
|
+
const writes = [];
|
|
73
|
+
for (let i = 0; i < args.length; i++) {
|
|
74
|
+
const arg = args[i] ?? "";
|
|
75
|
+
if (arg === "--")
|
|
76
|
+
break;
|
|
77
|
+
if (arg.startsWith("--")) {
|
|
78
|
+
const [given = "", inline] = arg.slice(2).split(/=(.*)/s, 2);
|
|
79
|
+
const exact = SORT_LONG.includes(given)
|
|
80
|
+
? [given]
|
|
81
|
+
: SORT_LONG.filter((n) => n.startsWith(given));
|
|
82
|
+
if (exact.length !== 1)
|
|
83
|
+
return undefined;
|
|
84
|
+
const name = exact[0] ?? "";
|
|
85
|
+
if (!SORT_LONG_VALUE.has(name))
|
|
86
|
+
continue;
|
|
87
|
+
const value = inline ?? args[++i];
|
|
88
|
+
if (value === undefined)
|
|
89
|
+
return undefined;
|
|
90
|
+
if (name === "compress-program")
|
|
91
|
+
return undefined;
|
|
92
|
+
if (name === "output" || name === "temporary-directory")
|
|
93
|
+
writes.push(value);
|
|
94
|
+
}
|
|
95
|
+
else if (arg.startsWith("-") && arg.length > 1) {
|
|
96
|
+
for (let j = 1; j < arg.length; j++) {
|
|
97
|
+
const flag = arg[j] ?? "";
|
|
98
|
+
if ("ktSTo".includes(flag)) {
|
|
99
|
+
const value = arg.slice(j + 1) || args[++i];
|
|
100
|
+
if (value === undefined)
|
|
101
|
+
return undefined;
|
|
102
|
+
if (flag === "o" || flag === "T")
|
|
103
|
+
writes.push(value);
|
|
104
|
+
break;
|
|
105
|
+
}
|
|
106
|
+
if (!"bdfgiMhnRrVcCmsuz".includes(flag))
|
|
107
|
+
return undefined;
|
|
108
|
+
}
|
|
109
|
+
}
|
|
110
|
+
}
|
|
111
|
+
return writes;
|
|
112
|
+
}
|
|
54
113
|
/**
|
|
55
114
|
* Programs whose behaviour cannot be changed by an unknown argument: they only print or compare
|
|
56
115
|
* strings. The output of a command substitution may be an argument of these and of nothing else,
|
|
@@ -1611,6 +1670,16 @@ export function simpleDecision(request, command, profile, depth, stageIndex, cwd
|
|
|
1611
1670
|
if (program === "find" &&
|
|
1612
1671
|
args.some((arg) => ["-delete", "-exec", "-execdir", "-ok", "-okdir", "-fprint", "-fprintf", "-fls"].includes(arg)))
|
|
1613
1672
|
return human(request, "destructive", "find with actions requires human review");
|
|
1673
|
+
if (program === "sort") {
|
|
1674
|
+
const outputs = sortWrites(args);
|
|
1675
|
+
if (outputs === undefined)
|
|
1676
|
+
return human(request, "unknown", "sort with an option that runs a program requires review");
|
|
1677
|
+
for (const file of outputs) {
|
|
1678
|
+
const check = permissiveWrite(cwd, file, profile, fill);
|
|
1679
|
+
if (!check.allowed)
|
|
1680
|
+
return human(request, check.category, check.reason);
|
|
1681
|
+
}
|
|
1682
|
+
}
|
|
1614
1683
|
if (["chmod", "chown"].includes(program) && args.some((arg) => /^-[a-zA-Z]*R/.test(arg)))
|
|
1615
1684
|
return human(request, "destructive", "Recursive permission changes require human approval");
|
|
1616
1685
|
if ((program === "sed" &&
|
package/dist/policy.js
CHANGED
|
@@ -5,6 +5,7 @@ import { branchEvidence, canonical, git, inside, pathEvidence } from "./evidence
|
|
|
5
5
|
import { commandDecision, permissiveRead, permissiveWrite, WORKTREE_DELETION, } from "./permissive.js";
|
|
6
6
|
import { mcpReadOnly, strictProfile } from "./profile.js";
|
|
7
7
|
import { redactText } from "./redact.js";
|
|
8
|
+
import { defaultAllowed } from "./tools.js";
|
|
8
9
|
import { CATEGORIES, } from "./types.js";
|
|
9
10
|
export function hash(value) {
|
|
10
11
|
return createHash("sha256").update(JSON.stringify(value)).digest("hex");
|
|
@@ -315,6 +316,15 @@ function evaluateCore(request, profile) {
|
|
|
315
316
|
...result(request, "unknown", "MCP tool not listed as read-only; left to the harness"),
|
|
316
317
|
decision: "native",
|
|
317
318
|
};
|
|
319
|
+
// Harness tools that are not shell, file, patch or MCP tools (task control, plan mode, asking
|
|
320
|
+
// the user, loading tool schemas) are approved by default under the permissive profile; the
|
|
321
|
+
// profile's toolsDeny keeps chosen ones on the classification path. Each approval names the tool.
|
|
322
|
+
if (profile.mode === "permissive" &&
|
|
323
|
+
defaultAllowed(request.harness, request.tool, profile.toolsDeny[request.harness] ?? []))
|
|
324
|
+
return {
|
|
325
|
+
...result(request, "code-read", "Harness tool approved by default", true),
|
|
326
|
+
defaultTool: request.tool,
|
|
327
|
+
};
|
|
318
328
|
const cwd = input.workdir ?? input.cwd ?? request.cwd;
|
|
319
329
|
if (typeof cwd !== "string" || cwd !== request.cwd)
|
|
320
330
|
return result(request, "unknown", "Execution directory differs from the reviewed directory");
|