toll-free-harness 0.1.0
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/LICENSE +199 -0
- package/MIGRATION.md +283 -0
- package/README.md +127 -0
- package/dist/chunk-WSCMT67X.js +548 -0
- package/dist/claude_code/hook_client.d.ts +2 -0
- package/dist/claude_code/hook_client.js +32 -0
- package/dist/cli/main.d.ts +1 -0
- package/dist/cli/main.js +248 -0
- package/dist/index.d.ts +184 -0
- package/dist/index.js +208 -0
- package/package.json +54 -0
package/LICENSE
ADDED
|
@@ -0,0 +1,199 @@
|
|
|
1
|
+
|
|
2
|
+
Apache License
|
|
3
|
+
Version 2.0, January 2004
|
|
4
|
+
http://www.apache.org/licenses/
|
|
5
|
+
|
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
7
|
+
|
|
8
|
+
1. Definitions.
|
|
9
|
+
|
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
12
|
+
|
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
14
|
+
the copyright owner that is granting the License.
|
|
15
|
+
|
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
17
|
+
other entities that control, are controlled by, or are under common
|
|
18
|
+
control with that entity. For the purposes of this definition,
|
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
20
|
+
direction or management of such entity, whether by contract or
|
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
23
|
+
|
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
25
|
+
exercising permissions granted by this License.
|
|
26
|
+
|
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
28
|
+
including but not limited to software source code, documentation
|
|
29
|
+
source, and configuration files.
|
|
30
|
+
|
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
|
32
|
+
transformation or translation of a Source form, including but
|
|
33
|
+
not limited to compiled object code, generated documentation,
|
|
34
|
+
and conversions to other media types.
|
|
35
|
+
|
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
37
|
+
Object form, made available under the License, as indicated by a
|
|
38
|
+
copyright notice that is included in or attached to the work
|
|
39
|
+
(an example is provided in the Appendix below).
|
|
40
|
+
|
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
47
|
+
the Work and Derivative Works thereof.
|
|
48
|
+
|
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
|
50
|
+
the original version of the Work and any modifications or additions
|
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
52
|
+
submitted to the Licensor for inclusion in the Work by the copyright owner
|
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
62
|
+
|
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
64
|
+
on behalf of whom a Contribution has been received by the Licensor and
|
|
65
|
+
subsequently incorporated within the Work.
|
|
66
|
+
|
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
|
73
|
+
|
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
79
|
+
where such license applies only to those patent claims licensable
|
|
80
|
+
by such Contributor that are necessarily infringed by their
|
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
83
|
+
institute patent litigation against any entity (including a
|
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
86
|
+
or contributory patent infringement, then any patent licenses
|
|
87
|
+
granted to You under this License for that Work shall terminate
|
|
88
|
+
as of the date such litigation is filed.
|
|
89
|
+
|
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
92
|
+
modifications, and in Source or Object form, provided that You
|
|
93
|
+
meet the following conditions:
|
|
94
|
+
|
|
95
|
+
(a) You must give any other recipients of the Work or
|
|
96
|
+
Derivative Works a copy of this License; and
|
|
97
|
+
|
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
|
99
|
+
stating that You changed the files; and
|
|
100
|
+
|
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
|
103
|
+
attribution notices from the Source form of the Work,
|
|
104
|
+
excluding those notices that do not pertain to any part of
|
|
105
|
+
the Derivative Works; and
|
|
106
|
+
|
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
|
109
|
+
include a readable copy of the attribution notices contained
|
|
110
|
+
within such NOTICE file, excluding any notices that do not
|
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
|
112
|
+
of the following places: within a NOTICE text file distributed
|
|
113
|
+
as part of the Derivative Works; within the Source form or
|
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
|
115
|
+
within a display generated by the Derivative Works, if and
|
|
116
|
+
wherever such third-party notices normally appear. The contents
|
|
117
|
+
of the NOTICE file are for informational purposes only and
|
|
118
|
+
do not modify the License. You may add Your own attribution
|
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
121
|
+
that such additional attribution notices cannot be construed
|
|
122
|
+
as modifying the License.
|
|
123
|
+
|
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
|
125
|
+
may provide additional or different license terms and conditions
|
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
129
|
+
the conditions stated in this License.
|
|
130
|
+
|
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
134
|
+
this License, without any additional terms or conditions.
|
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
136
|
+
the terms of any separate license agreement you may have executed
|
|
137
|
+
with Licensor regarding such Contributions.
|
|
138
|
+
|
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
141
|
+
except as required for reasonable and customary use in describing the
|
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
143
|
+
|
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
|
153
|
+
|
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
|
159
|
+
incidental, or consequential damages of any character arising as a
|
|
160
|
+
result of this License or out of the use or inability to use the
|
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
163
|
+
other commercial damages or losses), even if such Contributor
|
|
164
|
+
has been advised of the possibility of such damages.
|
|
165
|
+
|
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
169
|
+
or other liability obligations and/or rights consistent with this
|
|
170
|
+
License. However, in accepting such obligations, You may act only
|
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
175
|
+
of your accepting any such warranty or additional liability.
|
|
176
|
+
|
|
177
|
+
END OF TERMS AND CONDITIONS
|
|
178
|
+
|
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
180
|
+
|
|
181
|
+
To apply the Apache License to your work, attach the following
|
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
183
|
+
replaced with your own identifying information. (Don't include
|
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
185
|
+
comment syntax for the file format.
|
|
186
|
+
|
|
187
|
+
Copyright 2026 WeZZard
|
|
188
|
+
|
|
189
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
190
|
+
you may not use this file except in compliance with the License.
|
|
191
|
+
You may obtain a copy of the License at
|
|
192
|
+
|
|
193
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
194
|
+
|
|
195
|
+
Unless required by applicable law or agreed to in writing, software
|
|
196
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
197
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
198
|
+
See the License for the specific language governing permissions and
|
|
199
|
+
limitations under the License.
|
package/MIGRATION.md
ADDED
|
@@ -0,0 +1,283 @@
|
|
|
1
|
+
# Migrating from `claude -p` to toll-free-harness
|
|
2
|
+
|
|
3
|
+
This guide shows how to convert scripts that use `claude -p` (with `--output-format json`, `--output-format stream-json`, or `--input-format stream-json`) to the toll-free-harness library API. Each section shows a Before (shell command) and After (TypeScript using toll-free-harness).
|
|
4
|
+
|
|
5
|
+
## 1. Simple prompt
|
|
6
|
+
|
|
7
|
+
### Before
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
claude -p "Fix the failing tests" --model opus
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
### After
|
|
14
|
+
|
|
15
|
+
```typescript
|
|
16
|
+
import { ClaudeCodeSession } from "toll-free-harness";
|
|
17
|
+
|
|
18
|
+
const session = new ClaudeCodeSession({
|
|
19
|
+
args: ["--model", "opus"],
|
|
20
|
+
cwd: process.cwd(),
|
|
21
|
+
prompt: "Fix the failing tests",
|
|
22
|
+
});
|
|
23
|
+
|
|
24
|
+
const result = await session.run();
|
|
25
|
+
console.log(`Exit code: ${result.exitCode}`);
|
|
26
|
+
```
|
|
27
|
+
|
|
28
|
+
The `prompt` option replaces the positional argument to `claude -p`. Additional CLI flags go in `args`.
|
|
29
|
+
|
|
30
|
+
## 2. JSON output (`--output-format json`)
|
|
31
|
+
|
|
32
|
+
With `claude -p --output-format json`, you get a single JSON blob after the session finishes. The typical use is to capture what tools ran and the final result.
|
|
33
|
+
|
|
34
|
+
### Before
|
|
35
|
+
|
|
36
|
+
```bash
|
|
37
|
+
result=$(claude -p "Fix the failing tests" --output-format json)
|
|
38
|
+
echo "$result" | jq '.result'
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
### After
|
|
42
|
+
|
|
43
|
+
```typescript
|
|
44
|
+
import { ClaudeCodeSession } from "toll-free-harness";
|
|
45
|
+
|
|
46
|
+
const toolResults: Array<{ tool: string; input: unknown }> = [];
|
|
47
|
+
|
|
48
|
+
const session = new ClaudeCodeSession({
|
|
49
|
+
args: ["--model", "opus"],
|
|
50
|
+
cwd: process.cwd(),
|
|
51
|
+
prompt: "Fix the failing tests",
|
|
52
|
+
});
|
|
53
|
+
|
|
54
|
+
// Collect tool results as they complete (replaces parsing the JSON blob)
|
|
55
|
+
session.onPostToolUse("*", (event) => {
|
|
56
|
+
toolResults.push({
|
|
57
|
+
tool: event.toolName ?? "unknown",
|
|
58
|
+
input: event.toolInput,
|
|
59
|
+
});
|
|
60
|
+
});
|
|
61
|
+
|
|
62
|
+
// Capture the final stop event (replaces reading .result from the JSON)
|
|
63
|
+
let stopPayload: Record<string, unknown> = {};
|
|
64
|
+
session.onStop((payload) => {
|
|
65
|
+
stopPayload = payload;
|
|
66
|
+
});
|
|
67
|
+
|
|
68
|
+
const result = await session.run();
|
|
69
|
+
console.log("Tools used:", toolResults);
|
|
70
|
+
console.log("Stop payload:", stopPayload);
|
|
71
|
+
console.log("Exit code:", result.exitCode);
|
|
72
|
+
```
|
|
73
|
+
|
|
74
|
+
Instead of parsing a JSON blob after the fact, you receive structured events as they happen through `onPostToolUse` and `onStop`.
|
|
75
|
+
|
|
76
|
+
## 3. Stream-json output (`--output-format stream-json`)
|
|
77
|
+
|
|
78
|
+
With `claude -p --output-format stream-json`, you get newline-delimited JSON events as the session runs. The typical use is to observe tool calls in real time.
|
|
79
|
+
|
|
80
|
+
### Before
|
|
81
|
+
|
|
82
|
+
```bash
|
|
83
|
+
claude -p "Refactor the auth module" --output-format stream-json | while read -r line; do
|
|
84
|
+
type=$(echo "$line" | jq -r '.type')
|
|
85
|
+
case "$type" in
|
|
86
|
+
tool_use)
|
|
87
|
+
tool=$(echo "$line" | jq -r '.tool')
|
|
88
|
+
echo "Using tool: $tool"
|
|
89
|
+
;;
|
|
90
|
+
tool_result)
|
|
91
|
+
tool=$(echo "$line" | jq -r '.tool')
|
|
92
|
+
echo "Tool done: $tool"
|
|
93
|
+
;;
|
|
94
|
+
result)
|
|
95
|
+
echo "Finished"
|
|
96
|
+
;;
|
|
97
|
+
esac
|
|
98
|
+
done
|
|
99
|
+
```
|
|
100
|
+
|
|
101
|
+
### After
|
|
102
|
+
|
|
103
|
+
```typescript
|
|
104
|
+
import { ClaudeCodeSession } from "toll-free-harness";
|
|
105
|
+
|
|
106
|
+
const session = new ClaudeCodeSession({
|
|
107
|
+
args: ["--model", "opus"],
|
|
108
|
+
cwd: process.cwd(),
|
|
109
|
+
prompt: "Refactor the auth module",
|
|
110
|
+
});
|
|
111
|
+
|
|
112
|
+
// Fires before each tool call (replaces stream-json tool_use events)
|
|
113
|
+
session.onPreToolUse("*", (event) => {
|
|
114
|
+
console.log(`Using tool: ${event.toolName}`);
|
|
115
|
+
if (event.toolName === "Bash") {
|
|
116
|
+
console.log(` Command: ${(event.toolInput as Record<string, unknown>)?.command}`);
|
|
117
|
+
}
|
|
118
|
+
});
|
|
119
|
+
|
|
120
|
+
// Fires after each tool call (replaces stream-json tool_result events)
|
|
121
|
+
session.onPostToolUse("*", (event) => {
|
|
122
|
+
console.log(`Tool done: ${event.toolName}`);
|
|
123
|
+
});
|
|
124
|
+
|
|
125
|
+
// Fires when the session ends (replaces stream-json result event)
|
|
126
|
+
session.onStop(() => {
|
|
127
|
+
console.log("Finished");
|
|
128
|
+
});
|
|
129
|
+
|
|
130
|
+
const result = await session.run();
|
|
131
|
+
```
|
|
132
|
+
|
|
133
|
+
You can also filter listeners by tool name instead of matching on `"*"`:
|
|
134
|
+
|
|
135
|
+
```typescript
|
|
136
|
+
session.onPreToolUse("Bash", (event) => {
|
|
137
|
+
console.log(`Running command: ${(event.toolInput as Record<string, unknown>)?.command}`);
|
|
138
|
+
});
|
|
139
|
+
|
|
140
|
+
session.onPreToolUse("Read", (event) => {
|
|
141
|
+
console.log(`Reading file: ${(event.toolInput as Record<string, unknown>)?.file_path}`);
|
|
142
|
+
});
|
|
143
|
+
```
|
|
144
|
+
|
|
145
|
+
## 4. Stream-json input (`--input-format stream-json`)
|
|
146
|
+
|
|
147
|
+
With `claude -p --input-format stream-json`, you pipe structured messages into the agent and handle its questions and plan reviews programmatically.
|
|
148
|
+
|
|
149
|
+
### Before
|
|
150
|
+
|
|
151
|
+
```bash
|
|
152
|
+
# Pipe a prompt and handle conversation interactively
|
|
153
|
+
echo '{"type":"user","content":"Refactor the auth module"}' | \
|
|
154
|
+
claude -p --input-format stream-json --output-format stream-json | \
|
|
155
|
+
while read -r line; do
|
|
156
|
+
type=$(echo "$line" | jq -r '.type')
|
|
157
|
+
if [ "$type" = "ask_user_question" ]; then
|
|
158
|
+
# Pick the first option
|
|
159
|
+
echo '{"type":"user","content":"1"}'
|
|
160
|
+
elif [ "$type" = "plan" ]; then
|
|
161
|
+
# Approve the plan
|
|
162
|
+
echo '{"type":"user","content":"yes"}'
|
|
163
|
+
fi
|
|
164
|
+
done
|
|
165
|
+
```
|
|
166
|
+
|
|
167
|
+
### After
|
|
168
|
+
|
|
169
|
+
```typescript
|
|
170
|
+
import { ClaudeCodeSession } from "toll-free-harness";
|
|
171
|
+
|
|
172
|
+
const session = new ClaudeCodeSession({
|
|
173
|
+
args: ["--model", "opus"],
|
|
174
|
+
cwd: process.cwd(),
|
|
175
|
+
prompt: "Refactor the auth module",
|
|
176
|
+
});
|
|
177
|
+
|
|
178
|
+
// Handle the agent's questions (replaces parsing ask_user_question and sending a choice)
|
|
179
|
+
session.onAskUserQuestion(async (event) => {
|
|
180
|
+
console.log(`Question: ${event.text}`);
|
|
181
|
+
for (const q of event.questions) {
|
|
182
|
+
console.log(` Options: ${q.options.map((o) => o.label).join(", ")}`);
|
|
183
|
+
}
|
|
184
|
+
// Select the first option (0-indexed)
|
|
185
|
+
return { selectedIndex: 0 };
|
|
186
|
+
});
|
|
187
|
+
|
|
188
|
+
// Handle plan review (replaces parsing plan events and sending yes/no)
|
|
189
|
+
session.onExitPlanMode(async (event) => {
|
|
190
|
+
console.log(`Plan: ${event.planText.slice(0, 200)}...`);
|
|
191
|
+
// Approve the plan
|
|
192
|
+
return { decision: "approve" };
|
|
193
|
+
});
|
|
194
|
+
|
|
195
|
+
const result = await session.run();
|
|
196
|
+
```
|
|
197
|
+
|
|
198
|
+
To reject a plan and provide feedback:
|
|
199
|
+
|
|
200
|
+
```typescript
|
|
201
|
+
session.onExitPlanMode(async (event) => {
|
|
202
|
+
if (event.planText.includes("delete")) {
|
|
203
|
+
return { decision: "reject", feedback: "Do not delete any files." };
|
|
204
|
+
}
|
|
205
|
+
return { decision: "approve" };
|
|
206
|
+
});
|
|
207
|
+
```
|
|
208
|
+
|
|
209
|
+
To send follow-up prompts after the initial run:
|
|
210
|
+
|
|
211
|
+
```typescript
|
|
212
|
+
const session = new ClaudeCodeSession({
|
|
213
|
+
args: ["--model", "opus"],
|
|
214
|
+
cwd: process.cwd(),
|
|
215
|
+
prompt: "Fix the failing tests",
|
|
216
|
+
});
|
|
217
|
+
|
|
218
|
+
session.onStop(() => {
|
|
219
|
+
// Send a follow-up prompt when the first task finishes
|
|
220
|
+
session.sendPrompt("Now add tests for the fix");
|
|
221
|
+
});
|
|
222
|
+
|
|
223
|
+
// sendPrompt also supports attaching images
|
|
224
|
+
session.sendPrompt("What does this UI look like?", {
|
|
225
|
+
images: ["/tmp/screenshot.png"],
|
|
226
|
+
});
|
|
227
|
+
```
|
|
228
|
+
|
|
229
|
+
## 5. Feature comparison
|
|
230
|
+
|
|
231
|
+
| Capability | `claude -p` | toll-free-harness |
|
|
232
|
+
|---|---|---|
|
|
233
|
+
| Run a prompt | `claude -p "prompt"` | `new ClaudeCodeSession({ prompt })` then `session.run()` |
|
|
234
|
+
| Get final result | `--output-format json` | `session.onStop(callback)` |
|
|
235
|
+
| Stream tool events | `--output-format stream-json` | `session.onPreToolUse` / `session.onPostToolUse` |
|
|
236
|
+
| Answer questions | `--input-format stream-json` + manual parsing | `session.onAskUserQuestion(handler)` |
|
|
237
|
+
| Review plans | `--input-format stream-json` + manual parsing | `session.onExitPlanMode(handler)` |
|
|
238
|
+
| Send follow-up prompts | Not supported | `session.sendPrompt(text, options?)` |
|
|
239
|
+
| Attach images | Not supported | `session.sendPrompt(text, { images: [...] })` |
|
|
240
|
+
| Filter by tool name | Parse JSON and check `.tool` field | `session.onPreToolUse("Bash", callback)` |
|
|
241
|
+
| Wait for specific events | Manual loop over stream | `session.guardrail.expect({ kind, toolName }, timeout)` |
|
|
242
|
+
| Typed event payloads | Raw JSON | `AskUserQuestionEvent`, `ExitPlanModeEvent`, `HookRequest` |
|
|
243
|
+
| Permission observation | Parse stream events | `session.onPermissionRequest(toolName, callback)` |
|
|
244
|
+
| Multi-turn conversation | Requires external orchestration | Built-in via `sendPrompt` |
|
|
245
|
+
|
|
246
|
+
## 6. Installation
|
|
247
|
+
|
|
248
|
+
```bash
|
|
249
|
+
npm install toll-free-harness node-pty
|
|
250
|
+
```
|
|
251
|
+
|
|
252
|
+
Or with pnpm:
|
|
253
|
+
|
|
254
|
+
```bash
|
|
255
|
+
pnpm add toll-free-harness node-pty
|
|
256
|
+
```
|
|
257
|
+
|
|
258
|
+
`node-pty` is a peer dependency that provides the PTY (pseudo-terminal) used to spawn the agent. It requires a native build toolchain (Xcode command-line tools on macOS, build-essential on Linux).
|
|
259
|
+
|
|
260
|
+
## 7. Event guardrail for deterministic flows
|
|
261
|
+
|
|
262
|
+
If your `claude -p` script waited for specific tool calls before proceeding, use the guardrail API:
|
|
263
|
+
|
|
264
|
+
```typescript
|
|
265
|
+
// Wait for a specific tool call with a timeout
|
|
266
|
+
const event = await session.guardrail.expect(
|
|
267
|
+
{ kind: "pre_tool_use", toolName: "Bash" },
|
|
268
|
+
10_000, // 10 second timeout
|
|
269
|
+
);
|
|
270
|
+
console.log("Bash tool was called:", event.payload);
|
|
271
|
+
```
|
|
272
|
+
|
|
273
|
+
This replaces patterns like:
|
|
274
|
+
|
|
275
|
+
```bash
|
|
276
|
+
claude -p "..." --output-format stream-json | while read -r line; do
|
|
277
|
+
tool=$(echo "$line" | jq -r '.tool')
|
|
278
|
+
if [ "$tool" = "Bash" ]; then
|
|
279
|
+
echo "Got it"
|
|
280
|
+
break
|
|
281
|
+
fi
|
|
282
|
+
done
|
|
283
|
+
```
|
package/README.md
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
1
|
+
# toll-free-harness
|
|
2
|
+
|
|
3
|
+
Full-featured user interaction simulator for terminal-based coding agents.
|
|
4
|
+
|
|
5
|
+
`toll-free-harness` models the complete user interaction surface of a coding agent CLI — prompting, answering questions, reviewing plans — as typed APIs. It spawns the agent in a local PTY, observes events through read-only hooks, and responds through the same keystroke channel a real user would.
|
|
6
|
+
|
|
7
|
+
Currently supports **Claude Code**. The framework is designed to add support for other coding agents whose headless modes do not fully expose the interactive user experience.
|
|
8
|
+
|
|
9
|
+
The name is a joke about toll booths around developer workflows.
|
|
10
|
+
|
|
11
|
+
## What this project is not
|
|
12
|
+
|
|
13
|
+
Not an API proxy, credential-sharing service, or billing workaround. Users run their own local tools with their own accounts and must comply with those tools' terms.
|
|
14
|
+
|
|
15
|
+
## Install
|
|
16
|
+
|
|
17
|
+
```bash
|
|
18
|
+
pnpm add toll-free-harness node-pty
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
## Quick start
|
|
22
|
+
|
|
23
|
+
```typescript
|
|
24
|
+
import { ClaudeCodeSession } from "toll-free-harness";
|
|
25
|
+
|
|
26
|
+
const session = new ClaudeCodeSession({
|
|
27
|
+
args: ["--model", "opus"],
|
|
28
|
+
cwd: "/path/to/project",
|
|
29
|
+
prompt: "Fix the failing tests",
|
|
30
|
+
});
|
|
31
|
+
|
|
32
|
+
// Handle the agent's questions — return which option to select
|
|
33
|
+
session.onAskUserQuestion(async (event) => {
|
|
34
|
+
console.log(event.text);
|
|
35
|
+
console.log(event.questions[0]?.options.map((o, i) => `${i}: ${o.label}`));
|
|
36
|
+
return { selectedIndex: 0 };
|
|
37
|
+
});
|
|
38
|
+
|
|
39
|
+
// Handle plan review — approve or reject with feedback
|
|
40
|
+
session.onExitPlanMode(async (event) => {
|
|
41
|
+
console.log(event.planText.slice(0, 200));
|
|
42
|
+
return { decision: "approve" };
|
|
43
|
+
});
|
|
44
|
+
|
|
45
|
+
const result = await session.run();
|
|
46
|
+
|
|
47
|
+
// Send a follow-up prompt (with optional images)
|
|
48
|
+
session.sendPrompt("Now add tests for the fix", {
|
|
49
|
+
images: ["/tmp/screenshot.png"],
|
|
50
|
+
});
|
|
51
|
+
```
|
|
52
|
+
|
|
53
|
+
## User interactions
|
|
54
|
+
|
|
55
|
+
The framework models three user interactions as dedicated typed APIs:
|
|
56
|
+
|
|
57
|
+
| Interaction | API | You provide | Library does |
|
|
58
|
+
|---|---|---|---|
|
|
59
|
+
| **Prompting** | `sendPrompt(text, options?)` | Text + optional image paths | Injects keystrokes into PTY |
|
|
60
|
+
| **Answering questions** | `onAskUserQuestion(handler)` | `{ selectedIndex }` | Navigates and selects the option |
|
|
61
|
+
| **Reviewing plans** | `onExitPlanMode(handler)` | `{ decision: "approve" }` or `{ decision: "reject", feedback }` | Approves or rejects via keystrokes |
|
|
62
|
+
|
|
63
|
+
There is no raw `write()` — the library translates your typed decisions into the correct keystrokes internally.
|
|
64
|
+
|
|
65
|
+
## Hook listeners (read-only)
|
|
66
|
+
|
|
67
|
+
Observe agent events without sending data back:
|
|
68
|
+
|
|
69
|
+
```typescript
|
|
70
|
+
session.onPreToolUse("Bash", (event) => {
|
|
71
|
+
console.log(`Running: ${event.toolInput?.command}`);
|
|
72
|
+
});
|
|
73
|
+
|
|
74
|
+
session.onPostToolUse("*", (event) => {
|
|
75
|
+
console.log(`Tool ${event.toolName} completed`);
|
|
76
|
+
});
|
|
77
|
+
|
|
78
|
+
session.onStop(() => {
|
|
79
|
+
console.log("Session ended");
|
|
80
|
+
});
|
|
81
|
+
```
|
|
82
|
+
|
|
83
|
+
Available: `onPreToolUse`, `onPostToolUse`, `onPermissionRequest`, `onStop`, `onUserPromptSubmit`. All are read-only — hooks return `{}` internally and never send data back to the agent.
|
|
84
|
+
|
|
85
|
+
## Event guardrail
|
|
86
|
+
|
|
87
|
+
Wait for specific events with timeouts for deterministic test flows:
|
|
88
|
+
|
|
89
|
+
```typescript
|
|
90
|
+
const event = await session.guardrail.expect(
|
|
91
|
+
{ kind: "pre_tool_use", toolName: "Bash" },
|
|
92
|
+
10_000,
|
|
93
|
+
);
|
|
94
|
+
```
|
|
95
|
+
|
|
96
|
+
## Timing model
|
|
97
|
+
|
|
98
|
+
`PreToolUse` and `Stop` hooks are **blocking** — the agent waits for them. Keystrokes injected during a blocking hook callback buffer in PTY stdin and are consumed by the UI after the hook returns. `PermissionRequest` is **non-blocking** — the dialog renders in parallel.
|
|
99
|
+
|
|
100
|
+
## How it works
|
|
101
|
+
|
|
102
|
+
1. `run()` generates a temporary plugin in `/tmp/toll-free-plugin-<uuid>/` containing a manifest, hook definitions, and a bundled hook client
|
|
103
|
+
2. Starts an HTTP server on a Unix domain socket (`/tmp/toll-free-<uuid>.sock`)
|
|
104
|
+
3. Spawns the agent in a PTY with `--plugin-dir /tmp/toll-free-plugin-<uuid>/` plus your args and prompt
|
|
105
|
+
4. The agent loads the plugin and fires hooks as it runs. The hook client posts events to the socket.
|
|
106
|
+
5. Your interaction handlers and listeners receive events; responses go through PTY keystrokes
|
|
107
|
+
6. On exit, the socket and plugin directory are cleaned up
|
|
108
|
+
|
|
109
|
+
No user-scope settings are modified. The plugin is self-contained and session-scoped.
|
|
110
|
+
|
|
111
|
+
## Cross-platform
|
|
112
|
+
|
|
113
|
+
Uses Node.js `http.request({ socketPath })` for IPC — works on macOS, Linux, and Windows 10 1803+.
|
|
114
|
+
|
|
115
|
+
## Migrating from claude -p
|
|
116
|
+
|
|
117
|
+
Ask your coding agent to help you migrate:
|
|
118
|
+
|
|
119
|
+
```
|
|
120
|
+
curl -s https://raw.githubusercontent.com/WeZZard/toll-free-harness/main/MIGRATION.md | pbcopy
|
|
121
|
+
```
|
|
122
|
+
|
|
123
|
+
Paste the content to your agent and ask it to convert your `claude -p` scripts to use toll-free-harness.
|
|
124
|
+
|
|
125
|
+
## License
|
|
126
|
+
|
|
127
|
+
Apache-2.0
|