fix: wire after_tasks and after_implement hook events into command templates

[mnriem]

Summary

Fixes #1701.

The HookExecutor class in extensions.py was fully implemented but check_hooks_for_event() was never invoked - the core command templates had no instructions to check .specify/extensions.yml. Hooks silently did nothing after every command run.

Changes

• templates/commands/tasks.md: added step 6 - after_tasks hook check
• templates/commands/implement.md: added step 10 - after_implement hook check
• pyproject.toml: version bump 0.1.6 to 0.1.7
• CHANGELOG.md: entry for [0.1.7]

Testing

1. Create an extension with an after_tasks hook and install it
2. Confirm hook is registered in .specify/extensions.yml
3. Run /speckit.tasks - the hook message should now appear at the end of the output

[Copilot]

Pull request overview

This PR fixes issue #1701 by wiring extension hooks into command templates. The HookExecutor class in extensions.py was fully implemented but never invoked - core command templates had no instructions to check .specify/extensions.yml. This meant hooks silently did nothing after command completion. The fix adds step-by-step instructions to tasks.md and implement.md templates to read the extensions config, filter enabled hooks, evaluate conditions, and output the appropriate hook messages (including EXECUTE_COMMAND: markers for mandatory hooks).

Changes:

• Added hook checking instructions to tasks.md (step 6) and implement.md (step 10) templates
• Version bump from 0.1.6 to 0.1.7 with corresponding changelog entry
• Templates now parse .specify/extensions.yml and output formatted hook messages for AI agents to execute

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 4 comments.

File	Description
templates/commands/tasks.md	Added step 6 to check for after_tasks hooks after task generation completes
templates/commands/implement.md	Added step 10 to check for after_implement hooks after implementation validation
pyproject.toml	Version bump from 0.1.6 to 0.1.7
CHANGELOG.md	Added entry for version 0.1.7 documenting the hook wiring fix

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 5 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[dhilipkumars]

a QQ.

[dhilipkumars]

I have pushed two new commits directly addressing the review comments!

1. feat(templates): implement before-hooks check as pre-execution phase: Added the new before_implement and before_tasks blocks to the templates. Crucially, to prevent breaking the API continuity of the Outline numbering, this was implemented as a new ## Pre-Execution Checks block immediately prior to the Outline.
2. test(hooks): create scenario for LLMs/Agents on hooks: Created tests/hooks/ mapping mock extension logic that explicitly tests evaluating both pre-hooks and post-hooks. You can use Copilot on this directory according to the TESTING.md specs to verify.

[Copilot]

Pull request overview

Copilot reviewed 7 out of 7 changed files in this pull request and generated 8 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 7 out of 7 changed files in this pull request and generated 5 comments.

Comments suppressed due to low confidence (2)

templates/commands/implement.md:180

• This section also skips hooks with non-empty condition, which will disable all conditional after_implement hooks unless condition evaluation is implemented somewhere else. Align behavior with HookExecutor’s condition support instead of skipping.

    - For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:
      - If the hook has no `condition` field, or it is null/empty, treat the hook as executable
      - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation

templates/commands/tasks.md:35

• These instructions skip any hook with a non-empty condition, but the templates never invoke HookExecutor.check_hooks_for_event(). That means conditional hooks will never execute. Either implement condition evaluation here (matching HookExecutor’s supported patterns) or include conditional hooks in the output so they can still be executed when conditions are met.

- For each remaining hook, do **not** attempt to interpret or evaluate hook `condition` expressions:
  - If the hook has no `condition` field, or it is null/empty, treat the hook as executable
  - If the hook defines a non-empty `condition`, skip the hook and leave condition evaluation to the HookExecutor implementation
- For each executable hook, output the following based on its `optional` flag:

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[mnriem]

@dhilipkumars Thanks for the help! Appreciate it bunches.