jeffy-loop 1.26.4__tar.gz → 1.26.6__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (24) hide show
  1. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/PKG-INFO +5 -5
  2. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/README.md +4 -4
  3. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/pyproject.toml +1 -1
  4. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/hooks/stop-hook.sh +1 -1
  5. jeffy_loop-1.26.6/src/jeffy_loop/__init__.py +1 -0
  6. jeffy_loop-1.26.4/src/jeffy_loop/__init__.py +0 -1
  7. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/.gitignore +0 -0
  8. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/LICENSE +0 -0
  9. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/hatch_build.py +0 -0
  10. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/cancel-jeffy/SKILL.md +0 -0
  11. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/SKILL.md +0 -0
  12. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/hooks/lib/check-claims.sh +0 -0
  13. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/hooks/lib/detect-sandbox.sh +0 -0
  14. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/hooks/lib/measure-surface.sh +0 -0
  15. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/hooks/lib/quiet-verify.sh +0 -0
  16. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/hooks/lib/run-probe.sh +0 -0
  17. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/references/backlog-default.md +0 -0
  18. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/references/backlog-highs.md +0 -0
  19. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/references/iteration-prompt-highs.txt +0 -0
  20. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/references/iteration-prompt.txt +0 -0
  21. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/references/journal-default.md +0 -0
  22. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/references/plan-default.md +0 -0
  23. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/skills/jeffy/references/plan-highs.md +0 -0
  24. {jeffy_loop-1.26.4 → jeffy_loop-1.26.6}/src/jeffy_loop/cli.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.5
2
2
  Name: jeffy-loop
3
- Version: 1.26.4
3
+ Version: 1.26.6
4
4
  Summary: Jeffy Loop is an autonomous software-engineering control system that forces an LLM to continuously audit, act, verify, checkpoint, and prove convergence.
5
5
  Project-URL: Repository, https://github.com/lenamonj/jeffy-loop
6
6
  License-Expression: MIT
@@ -25,7 +25,7 @@ Description-Content-Type: text/markdown
25
25
 
26
26
  **[Quick Install](#quick-install)**  ·  **[Usage](https://github.com/lenamonj/jeffy-loop/blob/main/docs/usage.md)**  ·  **[How it works](https://github.com/lenamonj/jeffy-loop/blob/main/docs/how-it-works.md)**  ·  **[The receipts](https://github.com/lenamonj/jeffy-loop/blob/main/evals/README.md)**  ·  **[Headless](https://github.com/lenamonj/jeffy-loop/blob/main/docs/headless.md)**  ·  **[White paper](https://github.com/lenamonj/jeffy-loop/raw/main/The-Jeffy-Loop.pdf)**  ·  **[STE100 description](https://github.com/lenamonj/jeffy-loop/raw/main/Jeffy-Loop-STE100.pdf)**
27
27
 
28
- ## A Claude Code loop that finds bugs in your repo, fixes them, and proves every fix before it commits. Maintainers have merged <!-- count:merged -->68<!-- /count --> of its patches.
28
+ ## A Claude Code loop that finds bugs in your repo, fixes them, and proves every fix before it commits. Maintainers have merged <!-- count:merged -->70<!-- /count --> of its patches.
29
29
 
30
30
  </div>
31
31
 
@@ -33,7 +33,7 @@ The model writes the patch. The harness around it decides whether that patch can
33
33
 
34
34
  The harness is deliberately hard to fool. If a fix breaks your tests, it is undone. Nothing is ever pushed. A standard run counts as complete only when a fresh audit is clean, your tests pass again, and an adversarial review by a second AI agent with no part in the run signs off. The goal is fixes that survive scrutiny.
35
35
 
36
- There is a real-world test for that. Maintainers with no stake in this project have merged <!-- count:merged -->68<!-- /count --> of its pull requests, each filed from a local clone, into projects run by NVIDIA, Arm, Meta, Tesla, Google, Apple, Microsoft, Netflix, Apache, Palo Alto Networks, Oracle, IBM, HashiCorp, Cisco, Uber, Square, Cloudflare, and more. [See them all.](#independent-validation---the-receipts)
36
+ There is a real-world test for that. Maintainers with no stake in this project have merged <!-- count:merged -->70<!-- /count --> of its pull requests, each filed from a local clone, into projects run by NVIDIA, Arm, Meta, Tesla, Google, Apple, Microsoft, Netflix, Apache, Palo Alto Networks, Oracle, IBM, HashiCorp, Cisco, Uber, Square, Cloudflare, and more. [See them all.](#independent-validation---the-receipts)
37
37
 
38
38
  <div align="center">
39
39
 
@@ -50,7 +50,7 @@ Jeffy was run against <!-- count:tested -->132<!-- /count --> open-source projec
50
50
 
51
51
  | Projects tested | Converged | Failed | PRs merged | PRs open | Issues filed |
52
52
  |:---:|:---:|:---:|:---:|:---:|:---:|
53
- | **<!-- count:tested -->132<!-- /count -->** | **<!-- count:converged -->103<!-- /count -->** | **<!-- count:failed -->28<!-- /count -->** | **<!-- count:merged -->68<!-- /count -->** | **<!-- count:prs-open -->17<!-- /count -->** | **<!-- count:issues -->4<!-- /count -->** |
53
+ | **<!-- count:tested -->132<!-- /count -->** | **<!-- count:converged -->103<!-- /count -->** | **<!-- count:failed -->28<!-- /count -->** | **<!-- count:merged -->70<!-- /count -->** | **<!-- count:prs-open -->17<!-- /count -->** | **<!-- count:issues -->4<!-- /count -->** |
54
54
 
55
55
  **Converged:** the closing audit came back clean and the loop's adversarial evaluator, a fresh-context sub-agent, countersigned it, a standard this repository set and checks itself. That happened in <!-- count:converged -->103<!-- /count --> projects across <!-- count:languages -->13<!-- /count --> languages with no language-specific analyzer. **Failed:** the run spent the budget declared before it started without converging, or, for libuv, was abandoned before it had one. That leaves PapaParse, an audit held to the same method rather than a loop run, which the receipts page counts as Fixed alongside the 103.
56
56
 
@@ -204,7 +204,7 @@ Each finding below was accepted upstream by the project's own maintainers.
204
204
  </tr>
205
205
  <tr>
206
206
  <td><img src="https://github.com/apache.png" width="20" height="20" alt="" align="absmiddle"> Apache</td>
207
- <td><a href="https://github.com/apache/commons-text/pull/768">commons-text #768</a> - merged in 2 days<br>A <code>StringMatcher</code> overload forwarded the buffer end as its start<br><br><a href="https://github.com/apache/commons-csv/pull/633">commons-csv #633</a> - merged in 3 days<br>The record counter's Javadoc said headers were not counted while the constructor's header was<br><br><a href="https://github.com/apache/commons-lang/pull/1784">commons-lang #1784</a> - merged in 1 day<br><code>Fraction.add</code> and <code>subtract</code> overflowed on operands not in lowest terms, or returned them unreduced<br><br><a href="https://github.com/apache/commons-lang/pull/1783">commons-lang #1783</a> - merged in 1 day<br><code>MethodUtils.invokeMethod</code> threw on an instance of any non-public class, every JDK collection factory result included<br><br><a href="https://github.com/apache/commons-lang/pull/1787">commons-lang #1787</a> - merged in 6 hours<br><code>Fraction</code>'s zero shortcuts returned the other operand unreduced, and threw where the reduced result fits<br><br><a href="https://github.com/apache/commons-codec/pull/443">commons-codec #443</a> - merged in 9 days<br>The Git tree-id builder sorted entries by UTF-16 code units where Git sorts UTF-8 bytes, so a name outside the Basic Multilingual Plane gave a different id from <code>git write-tree</code></td>
207
+ <td><a href="https://github.com/apache/commons-text/pull/768">commons-text #768</a> - merged in 2 days<br>A <code>StringMatcher</code> overload forwarded the buffer end as its start<br><br><a href="https://github.com/apache/commons-csv/pull/633">commons-csv #633</a> - merged in 3 days<br>The record counter's Javadoc said headers were not counted while the constructor's header was<br><br><a href="https://github.com/apache/commons-lang/pull/1784">commons-lang #1784</a> - merged in 1 day<br><code>Fraction.add</code> and <code>subtract</code> overflowed on operands not in lowest terms, or returned them unreduced<br><br><a href="https://github.com/apache/commons-lang/pull/1783">commons-lang #1783</a> - merged in 1 day<br><code>MethodUtils.invokeMethod</code> threw on an instance of any non-public class, every JDK collection factory result included<br><br><a href="https://github.com/apache/commons-lang/pull/1787">commons-lang #1787</a> - merged in 6 hours<br><code>Fraction</code>'s zero shortcuts returned the other operand unreduced, and threw where the reduced result fits<br><br><a href="https://github.com/apache/commons-codec/pull/443">commons-codec #443</a> - merged in 9 days<br>The Git tree-id builder sorted entries by UTF-16 code units where Git sorts UTF-8 bytes, so a name outside the Basic Multilingual Plane gave a different id from <code>git write-tree</code><br><br><a href="https://github.com/apache/commons-io/pull/875">commons-io #875</a> - merged in 48 days<br><code>MemoryMappedFileInputStream.read()</code> returned 0xFF80 to 0xFFFF for every byte from 0x80 to 0xFF, outside the 0 to 255 that the <code>InputStream.read()</code> contract promises<br><br><a href="https://github.com/apache/commons-io/pull/877">commons-io #877</a> - merged in 48 days<br><code>FileWriterWithEncoding.Builder</code> seeded its encoder from the default Charset and <code>get()</code> threw when the Charset and the encoder disagreed, so the builder could write nothing but the platform default encoding</td>
208
208
  </tr>
209
209
  <tr>
210
210
  <td><img src="https://github.com/PaloAltoNetworks.png" width="20" height="20" alt="" align="absmiddle"> Palo Alto Networks</td>
@@ -13,7 +13,7 @@
13
13
 
14
14
  **[Quick Install](#quick-install)** &nbsp;·&nbsp; **[Usage](docs/usage.md)** &nbsp;·&nbsp; **[How it works](docs/how-it-works.md)** &nbsp;·&nbsp; **[The receipts](evals/README.md)** &nbsp;·&nbsp; **[Headless](docs/headless.md)** &nbsp;·&nbsp; **[White paper](https://github.com/lenamonj/jeffy-loop/raw/main/The-Jeffy-Loop.pdf)** &nbsp;·&nbsp; **[STE100 description](https://github.com/lenamonj/jeffy-loop/raw/main/Jeffy-Loop-STE100.pdf)**
15
15
 
16
- ## A Claude Code loop that finds bugs in your repo, fixes them, and proves every fix before it commits. Maintainers have merged <!-- count:merged -->68<!-- /count --> of its patches.
16
+ ## A Claude Code loop that finds bugs in your repo, fixes them, and proves every fix before it commits. Maintainers have merged <!-- count:merged -->70<!-- /count --> of its patches.
17
17
 
18
18
  </div>
19
19
 
@@ -21,7 +21,7 @@ The model writes the patch. The harness around it decides whether that patch can
21
21
 
22
22
  The harness is deliberately hard to fool. If a fix breaks your tests, it is undone. Nothing is ever pushed. A standard run counts as complete only when a fresh audit is clean, your tests pass again, and an adversarial review by a second AI agent with no part in the run signs off. The goal is fixes that survive scrutiny.
23
23
 
24
- There is a real-world test for that. Maintainers with no stake in this project have merged <!-- count:merged -->68<!-- /count --> of its pull requests, each filed from a local clone, into projects run by NVIDIA, Arm, Meta, Tesla, Google, Apple, Microsoft, Netflix, Apache, Palo Alto Networks, Oracle, IBM, HashiCorp, Cisco, Uber, Square, Cloudflare, and more. [See them all.](#independent-validation---the-receipts)
24
+ There is a real-world test for that. Maintainers with no stake in this project have merged <!-- count:merged -->70<!-- /count --> of its pull requests, each filed from a local clone, into projects run by NVIDIA, Arm, Meta, Tesla, Google, Apple, Microsoft, Netflix, Apache, Palo Alto Networks, Oracle, IBM, HashiCorp, Cisco, Uber, Square, Cloudflare, and more. [See them all.](#independent-validation---the-receipts)
25
25
 
26
26
  <div align="center">
27
27
 
@@ -38,7 +38,7 @@ Jeffy was run against <!-- count:tested -->132<!-- /count --> open-source projec
38
38
 
39
39
  | Projects tested | Converged | Failed | PRs merged | PRs open | Issues filed |
40
40
  |:---:|:---:|:---:|:---:|:---:|:---:|
41
- | **<!-- count:tested -->132<!-- /count -->** | **<!-- count:converged -->103<!-- /count -->** | **<!-- count:failed -->28<!-- /count -->** | **<!-- count:merged -->68<!-- /count -->** | **<!-- count:prs-open -->17<!-- /count -->** | **<!-- count:issues -->4<!-- /count -->** |
41
+ | **<!-- count:tested -->132<!-- /count -->** | **<!-- count:converged -->103<!-- /count -->** | **<!-- count:failed -->28<!-- /count -->** | **<!-- count:merged -->70<!-- /count -->** | **<!-- count:prs-open -->17<!-- /count -->** | **<!-- count:issues -->4<!-- /count -->** |
42
42
 
43
43
  **Converged:** the closing audit came back clean and the loop's adversarial evaluator, a fresh-context sub-agent, countersigned it, a standard this repository set and checks itself. That happened in <!-- count:converged -->103<!-- /count --> projects across <!-- count:languages -->13<!-- /count --> languages with no language-specific analyzer. **Failed:** the run spent the budget declared before it started without converging, or, for libuv, was abandoned before it had one. That leaves PapaParse, an audit held to the same method rather than a loop run, which the receipts page counts as Fixed alongside the 103.
44
44
 
@@ -192,7 +192,7 @@ Each finding below was accepted upstream by the project's own maintainers.
192
192
  </tr>
193
193
  <tr>
194
194
  <td><img src="https://github.com/apache.png" width="20" height="20" alt="" align="absmiddle"> Apache</td>
195
- <td><a href="https://github.com/apache/commons-text/pull/768">commons-text #768</a> - merged in 2 days<br>A <code>StringMatcher</code> overload forwarded the buffer end as its start<br><br><a href="https://github.com/apache/commons-csv/pull/633">commons-csv #633</a> - merged in 3 days<br>The record counter's Javadoc said headers were not counted while the constructor's header was<br><br><a href="https://github.com/apache/commons-lang/pull/1784">commons-lang #1784</a> - merged in 1 day<br><code>Fraction.add</code> and <code>subtract</code> overflowed on operands not in lowest terms, or returned them unreduced<br><br><a href="https://github.com/apache/commons-lang/pull/1783">commons-lang #1783</a> - merged in 1 day<br><code>MethodUtils.invokeMethod</code> threw on an instance of any non-public class, every JDK collection factory result included<br><br><a href="https://github.com/apache/commons-lang/pull/1787">commons-lang #1787</a> - merged in 6 hours<br><code>Fraction</code>'s zero shortcuts returned the other operand unreduced, and threw where the reduced result fits<br><br><a href="https://github.com/apache/commons-codec/pull/443">commons-codec #443</a> - merged in 9 days<br>The Git tree-id builder sorted entries by UTF-16 code units where Git sorts UTF-8 bytes, so a name outside the Basic Multilingual Plane gave a different id from <code>git write-tree</code></td>
195
+ <td><a href="https://github.com/apache/commons-text/pull/768">commons-text #768</a> - merged in 2 days<br>A <code>StringMatcher</code> overload forwarded the buffer end as its start<br><br><a href="https://github.com/apache/commons-csv/pull/633">commons-csv #633</a> - merged in 3 days<br>The record counter's Javadoc said headers were not counted while the constructor's header was<br><br><a href="https://github.com/apache/commons-lang/pull/1784">commons-lang #1784</a> - merged in 1 day<br><code>Fraction.add</code> and <code>subtract</code> overflowed on operands not in lowest terms, or returned them unreduced<br><br><a href="https://github.com/apache/commons-lang/pull/1783">commons-lang #1783</a> - merged in 1 day<br><code>MethodUtils.invokeMethod</code> threw on an instance of any non-public class, every JDK collection factory result included<br><br><a href="https://github.com/apache/commons-lang/pull/1787">commons-lang #1787</a> - merged in 6 hours<br><code>Fraction</code>'s zero shortcuts returned the other operand unreduced, and threw where the reduced result fits<br><br><a href="https://github.com/apache/commons-codec/pull/443">commons-codec #443</a> - merged in 9 days<br>The Git tree-id builder sorted entries by UTF-16 code units where Git sorts UTF-8 bytes, so a name outside the Basic Multilingual Plane gave a different id from <code>git write-tree</code><br><br><a href="https://github.com/apache/commons-io/pull/875">commons-io #875</a> - merged in 48 days<br><code>MemoryMappedFileInputStream.read()</code> returned 0xFF80 to 0xFFFF for every byte from 0x80 to 0xFF, outside the 0 to 255 that the <code>InputStream.read()</code> contract promises<br><br><a href="https://github.com/apache/commons-io/pull/877">commons-io #877</a> - merged in 48 days<br><code>FileWriterWithEncoding.Builder</code> seeded its encoder from the default Charset and <code>get()</code> threw when the Charset and the encoder disagreed, so the builder could write nothing but the platform default encoding</td>
196
196
  </tr>
197
197
  <tr>
198
198
  <td><img src="https://github.com/PaloAltoNetworks.png" width="20" height="20" alt="" align="absmiddle"> Palo Alto Networks</td>
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
4
4
 
5
5
  [project]
6
6
  name = "jeffy-loop"
7
- version = "1.26.4"
7
+ version = "1.26.6"
8
8
  description = "Jeffy Loop is an autonomous software-engineering control system that forces an LLM to continuously audit, act, verify, checkpoint, and prove convergence."
9
9
  dynamic = ["readme"]
10
10
  license = "MIT"
@@ -10,7 +10,7 @@
10
10
  # directory Claude Code was started in, so Bash-tool cwd drift mid-iteration
11
11
  # cannot kill the loop.
12
12
  set -u
13
- JEFFY_VERSION="1.26.4"
13
+ JEFFY_VERSION="1.26.6"
14
14
 
15
15
  # 1.21.0 (P1-70): `stop-hook.sh --lint [project root]` derives every check
16
16
  # the declaration path enforces and prints the first refusal, or clean,
@@ -0,0 +1 @@
1
+ __version__ = "1.26.6"
@@ -1 +0,0 @@
1
- __version__ = "1.26.4"
File without changes
File without changes
File without changes