fix: skills-sh install fails for deeply nested repo structures (#2980)

* fix(run_agent): ensure _fire_first_delta() is called for tool generation events

Added calls to _fire_first_delta() in the AIAgent class to improve the handling of tool generation events, ensuring timely notifications during the processing of function calls and tool usage.

* fix(run_agent): improve timeout handling for chat completions

Enhanced the timeout configuration for chat completions in the AIAgent class by introducing customizable connection, read, and write timeouts using environment variables. This ensures more robust handling of API requests during streaming operations.

* fix(run_agent): reduce default stream read timeout for chat completions

Updated the default stream read timeout from 120 seconds to 60 seconds in the AIAgent class, enhancing the timeout configuration for chat completions. This change aims to improve responsiveness during streaming operations.

* fix(run_agent): enhance streaming error handling and retry logic

Improved the error handling and retry mechanism for streaming requests in the AIAgent class. Introduced a configurable maximum number of stream retries and refined the handling of transient network errors, allowing for retries with fresh connections. Non-transient errors now trigger a fallback to non-streaming only when appropriate, ensuring better resilience during API interactions.

* fix: skills-sh install fails for deeply nested repo structures

Skills in repos with deep directory nesting (e.g.
cli-tool/components/skills/development/senior-backend/) could not be
installed because the candidate path generation and shallow root-dir
scan never reached them.

Added GitHubSource._find_skill_in_repo_tree() which uses the GitHub
Trees API to recursively search the entire repo tree in a single API
call. This is used as a final fallback in
SkillsShSource._discover_identifier() when the standard candidate
paths and shallow scan both fail.

Fixes installation of skills from repos like davila7/claude-code-templates
where skills are nested 4+ levels deep.

Reported by user Samuraixheart.

tools/skills_hub.py

@@ -434,6 +434,56 @@ class GitHubSource(SkillSource):
 
         return files
 
+    def _find_skill_in_repo_tree(self, repo: str, skill_name: str) -> Optional[str]:
+        """Use the GitHub Trees API to find a skill directory anywhere in the repo.
+
+        Returns the full identifier (``repo/path/to/skill``) or ``None``.
+        This is a single API call regardless of repo depth, so it efficiently
+        handles deeply nested directory structures like
+        ``cli-tool/components/skills/development/<skill>/SKILL.md``.
+        """
+        # Get default branch
+        try:
+            resp = httpx.get(
+                f"https://api.github.com/repos/{repo}",
+                headers=self.auth.get_headers(),
+                timeout=15,
+                follow_redirects=True,
+            )
+            if resp.status_code != 200:
+                return None
+            default_branch = resp.json().get("default_branch", "main")
+        except (httpx.HTTPError, json.JSONDecodeError):
+            return None
+
+        # Get recursive tree (single API call for the entire repo)
+        try:
+            resp = httpx.get(
+                f"https://api.github.com/repos/{repo}/git/trees/{default_branch}",
+                params={"recursive": "1"},
+                headers=self.auth.get_headers(),
+                timeout=30,
+                follow_redirects=True,
+            )
+            if resp.status_code != 200:
+                return None
+            tree_data = resp.json()
+        except (httpx.HTTPError, json.JSONDecodeError):
+            return None
+
+        # Look for SKILL.md files inside directories named <skill_name>
+        skill_md_suffix = f"/{skill_name}/SKILL.md"
+        for entry in tree_data.get("tree", []):
+            if entry.get("type") != "blob":
+                continue
+            path = entry.get("path", "")
+            if path.endswith(skill_md_suffix) or path == f"{skill_name}/SKILL.md":
+                # Strip /SKILL.md to get the skill directory path
+                skill_dir = path[: -len("/SKILL.md")]
+                return f"{repo}/{skill_dir}"
+
+        return None
+
     def _fetch_file_content(self, repo: str, path: str) -> Optional[str]:
         """Fetch a single file's content from GitHub."""
         url = f"https://api.github.com/repos/{repo}/contents/{path}"
@@ -1014,6 +1064,14 @@ class SkillsShSource(SkillSource):
         except Exception:
             pass
 
+        # Final fallback: use the GitHub Trees API to find the skill anywhere
+        # in the repo tree.  This handles deeply nested structures like
+        # cli-tool/components/skills/development/<skill>/ that the shallow
+        # scan above can't reach.
+        tree_result = self.github._find_skill_in_repo_tree(repo, skill_token)
+        if tree_result:
+            return tree_result
+
         return None
 
     def _finalize_inspect_meta(self, meta: SkillMeta, canonical: str, detail: Optional[dict]) -> SkillMeta: