prreviewbuddy 0.25.13 → 0.27.2

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/CHANGELOG.md CHANGED
@@ -1,5 +1,83 @@
1
1
  # Changelog
2
2
 
3
+ ## 0.27.2
4
+
5
+ **Choose the model a review runs under.** `prreviewbuddy review --model <model>` asks the agent for
6
+ a particular model instead of whichever one it normally uses. It works with any agent:
7
+ `--agent codex --model gpt-5.3-codex`, or `--model opus` for Claude Code, with `--lens kiss` as well
8
+ as with the standard review, and with several pull requests at once. The name is passed straight
9
+ through, so anything your agent
10
+ accepts works here, including one released after this version of PR Review Buddy.
11
+ `prreviewbuddy --help` says where to find the names each agent takes, and a name the agent does not
12
+ know is answered by the agent itself, in its own words, along with where to look for one that
13
+ works.
14
+
15
+ **A review keeps the model it was pinned to.** Every agent call a review makes asks for the model
16
+ that review was pinned to: updating it, re-analysing it, running `--lens kiss` on it, asking the
17
+ assistant a question about it, and drawing a diagram of it. Only starting a new analysis changes
18
+ that, with `prreviewbuddy review --reanalyse --model <model>`. A review that never named a model
19
+ stays that way, and will not silently acquire one.
20
+
21
+ **Reviews now say which model made them, and only when they can.** Analysis details record what was
22
+ asked for and, where the agent reports it, what actually answered. Those are shown as separate
23
+ facts, because asking for a model is not proof of having got one: Codex never states which model it
24
+ used, so a Codex review says so rather than repeating the request back as though it were confirmed.
25
+ A review that pinned nothing still reads as it always did, naming just the agent. Those two facts
26
+ describe the run that last worked on the review, so bringing a review up to date re-states them
27
+ from the run that did the updating rather than carrying the earlier analysis's answers forward.
28
+ What the review asked for is not a fact about one run and survives, which is what keeps a pinned
29
+ review pinned.
30
+
31
+ ## 0.26.0
32
+
33
+ **Review several pull requests with one command.** `prreviewbuddy review --pr <url> <url> ...`
34
+ starts a review of each one. Every pull request gets an ordinary review of its own, with its own
35
+ link, exactly as if you had named it on its own. Two run at a time by default; `--concurrency <n>`
36
+ changes that. The link to all your reviews is printed as soon as the batch starts, so you can watch
37
+ the reviews appear there while they are being made, and one line per pull request shows the step
38
+ each has reached. At the end every pull request is listed with its own link. A pull request that
39
+ fails does not stop the others, and the command exits with 1 if any of them failed.
40
+
41
+ **Ctrl-C stops a review rather than failing it.** Pressing Ctrl-C during a batch stops the reviews
42
+ that are running and starts no more. A stopped review now says **Review stopped** on its page, with
43
+ a **Carry on** button, and **Analysis stopped** in the list of reviews. A review that genuinely went
44
+ wrong now says **Analysis failed** there instead. Running the same command again carries on from
45
+ where each review got to.
46
+
47
+ **Two pull requests from the same branch name are no longer mixed up.** Pull requests from two forks
48
+ that share a head branch name (such as `patch-1`) used to be handed each other's review. A review now
49
+ records its pull request number and is only handed back for that number. One consequence: a pull
50
+ request reviewed before this version, without its conversation attached, has no recorded number and
51
+ gets a fresh review the next time you ask for it.
52
+
53
+ ## 0.25.15
54
+
55
+ **Buddy AI answers one question at a time.** While Buddy AI was answering, a suggested question
56
+ or **Explain in simple terms** still started a second one. The conversation briefly showed two
57
+ questions, and then the page reloaded.
58
+
59
+ Those controls are now greyed out while a question is being answered, and nothing new starts until
60
+ it finishes or you press **Stop**. If you stop a question while something is already in the ask
61
+ field, that draft is kept. Diagrams are unchanged and can still be drawn while a question is being
62
+ answered.
63
+
64
+ After you press **Stop**, you can ask again right away. Before, a question asked in the moment
65
+ after Stop could be refused as a second one while the stopped question was still winding down, and
66
+ the page reloaded. The same applies to stopping a diagram and drawing another.
67
+
68
+ ## 0.25.14
69
+
70
+ **A question keeps being answered after you leave the review.** If you asked Buddy AI something
71
+ and then went to the reviews list or opened another review, the answer was thrown away. Coming
72
+ back showed an empty assistant, and your question had gone too. Drawing a diagram had the same
73
+ problem.
74
+
75
+ A question or a diagram now keeps going until it finishes, whichever page you are on. If you come
76
+ back while it is still working, the review shows your question with its progress, and the answer
77
+ appears when it is ready. **Stop** is the only thing that ends one early, and it works from any
78
+ page that has the review open. Anything you did on the review in the meantime, such as marking it
79
+ reviewed, is kept when the answer arrives.
80
+
3
81
  ## 0.25.13
4
82
 
5
83
  **Two updates of the same review no longer run over each other.** Pressing **Update review** on the