issue-flow 0.3.3__tar.gz → 0.3.4__tar.gz

{issue_flow-0.3.3 → issue_flow-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: issue-flow
-Version: 0.3.3
+Version: 0.3.4
 Summary: Agents should behave. Let them follow the issue flow.
 Keywords: cursor,ai,agents,issue-tracking,workflow
 Author: jepegit

{issue_flow-0.3.3 → issue_flow-0.3.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "issue-flow"
-version = "0.3.3"
+version = "0.3.4"
 description = "Agents should behave. Let them follow the issue flow."
 readme = "README.md"
 license = "MIT"

{issue_flow-0.3.3 → issue_flow-0.3.4}/src/issue_flow/templates/commands/issue-init.md.j2

@@ -9,6 +9,11 @@ The user may provide one of:
 
 The text after this slash command is the **issue reference**. It may also be **empty or only whitespace** (user ran `/issue-init` with no arguments).
 
+## Agent efficiency
+- Run the flow once; do not re-fetch or re-run tools only to diff the written file against the API (for example, no extra `gh` calls or scripts to compare bytes).
+- Do **not** spend effort on trailing newlines, byte-identical file endings, or CRLF vs LF. A normal markdown file with a final newline is fine.
+- "Preserve the issue body exactly as returned by GitHub" means the **body text** from the fetch: paste it into the template in **step 5** and move on. No second-pass verification or newline normalization.
+
 ## Steps
 
 0. Check that the required folders exist (`{{ issueflows_dir }}/{{ tools_folder }}`, `{{ issueflows_dir }}/{{ current_issues_folder }}`, `{{ issueflows_dir }}/{{ partly_solved_folder }}`, `{{ issueflows_dir }}/{{ solved_folder }}`). If not, create them after asking for permission.
@@ -34,6 +39,7 @@ The text after this slash command is the **issue reference**. It may also be **e
    - `gh issue view <N> --repo owner/repo --json title,body,url,number,comments`
    - `comments` returns an array where each entry has at least `author.login`, `body`, and `createdAt`.
    - Confirm resolved `owner/repo` to the user.
+   - Change the chat/agent tab title to reflect the issue topic on the form "Issue <issue number> <short description of issue>", for example "Issue 74 cell info".
 
 2a. **Triage comments** (only if the `comments` array is non-empty).
    - Follow the `issueflow-issue-comments` skill (`{{ agent_dir }}/skills/issueflow-issue-comments/SKILL.md`) for the rules; summary:
@@ -103,7 +109,7 @@ Report:
 - whether the operation succeeded
 
 ## Constraints
-- Preserve the issue **body** exactly as returned by GitHub (the `## Original issue text` section is byte-for-byte). Only the `## Comments (curated summary)` section is interpretive.
+- Preserve the issue **body** text exactly as returned by GitHub (the `## Original issue text` section reflects the fetched body; see **Agent efficiency** — do not optimize for trailing newlines or line-ending style). Only the `## Comments (curated summary)` section is interpretive.
 - Use UTF-8 markdown.
 - Allowed file modifications for this command:
   - create/update the target `issue<number>_original.md`

{issue_flow-0.3.3 → issue_flow-0.3.4}/src/issue_flow/templates/skills/issueflow_issue_comments/SKILL.md.j2

@@ -17,7 +17,7 @@ It is the playbook that `/issue-init` (and the `issueflow-issue-init` skill) del
 ## When to use
 
 - `/issue-init` just fetched an issue with a non-empty `comments` array and needs to write the `## Comments (curated summary)` section.
-- You are re-running triage on an already-captured issue because new comments have arrived (the issue body must stay byte-for-byte; only the curated section is rewritten).
+- You are re-running triage on an already-captured issue because new comments have arrived (the issue body text must stay unchanged; only the curated section is rewritten).
 - Any workflow that needs to understand "what does the comment thread actually ask us to do?" without pasting the raw thread into a file.
 
 ## Inputs

{issue_flow-0.3.3 → issue_flow-0.3.4}/src/issue_flow/templates/skills/issueflow_issue_init/SKILL.md.j2

@@ -28,7 +28,7 @@ Follow this skill when the user wants to **capture a GitHub issue locally** usin
    - **Empty / whitespace** — Run `git branch --show-current`. If empty or `main`/`master` (case-insensitive), **stop** and ask for a number, URL, or `owner/repo/#n`. If the branch matches `^\d+-.+`, ask once whether to use that leading issue number; do not proceed without a clear yes/no.
    - **Archived-issue guard** — Before writing, check `{{ issueflows_dir }}/{{ partly_solved_folder }}/` and `{{ issueflows_dir }}/{{ solved_folder }}/` for existing `issue<n>_*` files. If the issue is already archived, warn and require a second explicit confirmation before re-opening it in `{{ issueflows_dir }}/{{ current_issues_folder }}/`.
 
-3. **Fetch** — `gh issue view <n> --repo owner/repo --json title,body,url,number,comments`. The `comments` field returns an array of `{author.login, body, createdAt, ...}` that step 3a consumes. On failure, report the error and suggest `gh auth login`.
+3. **Fetch** — `gh issue view <n> --repo owner/repo --json title,body,url,number,comments`. The `comments` field returns an array of `{author.login, body, createdAt, ...}` that step 3a consumes. On failure, report the error and suggest `gh auth login`. After confirming `owner/repo`, change the chat/agent tab title to reflect the issue topic on the form "Issue <issue number> <short description of issue>" (e.g. "Issue 74 cell info").
 
 3a. **Triage comments** (skip if `comments` is empty). Follow the [`issueflow-issue-comments`](../issueflow-issue-comments/SKILL.md) skill. Summary of rules:
    - Process comments chronologically; **later comments win conflicts** with earlier ones.
@@ -62,7 +62,7 @@ Follow this skill when the user wants to **capture a GitHub issue locally** usin
    _Note: this section is an interpretive summary of the comment thread, not a verbatim dump. Source comments: <count>, last comment by @<login> on <date>._
    ```
 
-   Preserve the body **byte-for-byte** (including trailing newlines). The `## Comments (curated summary)` section is **optional** — include it only when step 3a produced at least one bullet, and drop any of the three bullet groups that have no content.
+   Preserve the body **text** faithfully as returned by GitHub — don't paraphrase or edit it, but don't waste effort on trailing newlines or CRLF vs LF either (no second-pass byte-diffing). The `## Comments (curated summary)` section is **optional** — include it only when step 3a produced at least one bullet, and drop any of the three bullet groups that have no content.
 
 6. **Conflicts** — If `issue<number>_original.md` already exists, do not overwrite silently; ask the user.