Skip to content

Unit 3: Distillery and Serena MCP infrastructure - #12

Merged
norrietaylor merged 3 commits into
mainfrom
sdd/unit-3-mcp
May 17, 2026
Merged

norrietaylor merged 3 commits into
mainfrom
sdd/unit-3-mcp

Conversation

@norrietaylor

Copy link
Copy Markdown
Owner

Implements Unit 3 of the issue-native SDD suite (docs/specs/01-spec-issue-native-sdd): shared MCP infrastructure for the SDD agents, configured not hardcoded.

Closes #3

What each requirement delivers

  • R3.1 shared/sdd-mcp-distillery.md: importable fragment declaring the Distillery MCP server over HTTP transport, authenticated via OAuth. Documents the search, find_similar, relations, and recall tools. The endpoint, OAuth credential, and project slug are read from repo or org variables and secrets (vars.DISTILLERY_MCP_URL, secrets.DISTILLERY_OAUTH_TOKEN, vars.DISTILLERY_PROJECT); no endpoint or org slug is a literal.
  • R3.2 The fragment states that every sdd-* Distillery query must be scoped via the project filter to this repository's own ingested content, so a shared store cannot leak unrelated or private knowledge into public artifacts. Scoping is documented as mandatory.
  • R3.3 .github/workflows/distillery-sync.md: scheduled (schedule: daily) agentic workflow that ingests this repo's docs/specs/, decisions/, and issues and PRs into Distillery via the gh-sync tool.
  • R3.4 shared/sdd-mcp-serena.md: importable fragment declaring the Serena MCP server (oraios/serena) over the checked-out working tree. Pins no language (the language-server set is resolved at install time) and states graceful degradation to text-level file reading when no language server exists for the stack.
  • R3.5 Neither fragment contains a literal hostname, org slug, bot name, or absolute path. The Distillery endpoint and credential are configuration expressions; Serena uses the runner's GITHUB_WORKSPACE.
  • R3.6 .github/workflows/mcp-smoke.md: a workflow_dispatch smoke workflow that resolves both MCP servers and returns one result from each, for install verification. docs/sdd/mcp-tools.md documents the MCP tooling and the dispatch procedure, and is added to the mkdocs.yml nav.

Deviations from the spec's literal paths

The spec's "Affected areas" places SDD workflow sources under workflows/. gh aw compile only processes .github/workflows/*.md (the task anticipated this). The two gh-aw workflow sources are therefore placed at .github/workflows/distillery-sync.md and .github/workflows/mcp-smoke.md so they genuinely compile.

gh-aw's import resolver rejects any import path outside .github/ for security, so a workflow cannot import a repo-root shared/*.md fragment. The two MCP fragments are delivered at shared/ per the R3.1/R3.4 deliverable text and matching the existing Unit 1 fragments; they contain valid gh-aw mcp-servers: frontmatter. Because they cannot yet be imported from a .github/-rooted workflow, distillery-sync and mcp-smoke declare their MCP servers inline (consistent with the fragments) rather than via imports:. Wiring the shared/ directory into the sdd-* agents as imports is Unit 4's concern; that unit will resolve the directory location for the whole shared/ tree.

Security review (gh-aw strict-mode)

gh aw compile strict mode flagged one new restricted secret: DISTILLERY_OAUTH_TOKEN. It is the OAuth bearer token for the Distillery HTTP MCP endpoint, referenced only as ${{ secrets.DISTILLERY_OAUTH_TOKEN }} in the Authorization header of the Distillery MCP server declaration. It is never logged and never written as a literal. No new actions were added; the existing pinned action set is reused. The change was approved into the gh-aw manifest with gh aw compile --approve.

Verification

  • gh aw compile: 3 workflows, 0 errors, 0 warnings. Both MCP server declarations compile; configuration expressions are preserved (no literals in the .lock.yml).
  • npx markdownlint-cli2 "**/*.md": 0 errors.
  • mkdocs build --strict: builds clean.
  • No em dashes in any hand-authored file. The generated .lock.yml files are committed as gh-aw produced them (the repo standard exempts toolchain-generated lock files; the already-merged sample.lock.yml carries the same gh-aw-generated content).

🤖 Generated with Claude Code

Unit 3 of the issue-native SDD suite. Makes two MCP servers available to
the SDD agents as configuration, not hardcoded literals.

- shared/sdd-mcp-distillery.md: importable fragment declaring the
  Distillery MCP server over HTTP transport with OAuth; documents the
  search, find_similar, relations, recall tools; endpoint and OAuth
  credentials read from repo or org variables and secrets; queries scoped
  via the project filter to this repository's own content.
- shared/sdd-mcp-serena.md: importable fragment declaring the Serena MCP
  server over the checked-out working tree; pins no language; degrades
  gracefully to text-level file reading when no language server exists.
- .github/workflows/distillery-sync.md: scheduled daily agentic workflow
  that ingests docs/specs/, decisions/, and issues and PRs via gh-sync.
- .github/workflows/mcp-smoke.md: workflow_dispatch smoke test that
  resolves both MCP servers and returns a result from each.
- docs/sdd/mcp-tools.md: MCP tooling reference and dispatch procedure,
  added to the mkdocs nav.

Neither fragment carries a literal hostname, org slug, bot name, or
absolute path. gh aw compile reports 0 errors.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@coderabbitai

coderabbitai Bot commented May 17, 2026 •

Copy link
Copy Markdown

Review Change Stack

📝 Walkthrough

Summary by CodeRabbit

  • New Features

    • Added automated daily workflow to keep repository knowledge in sync with specs, decisions, and issues.
    • Added manual testing workflow for validating code intelligence and semantic search servers.
  • Documentation

    • Added comprehensive guide documenting code intelligence and semantic search server configurations and tools.
    • Updated documentation navigation to include new MCP tools reference section.

Walkthrough

This PR introduces two Model Context Protocol server configurations (Distillery and Serena) and integrates them into two GitHub Actions workflows: distillery-sync for scheduled knowledge syncing, and mcp-smoke for manual integration testing. It includes shared MCP configuration fragments, complete workflow definitions with activation/agent/conclusion/safe-outputs orchestration, comprehensive design documentation, and updated site navigation.

Changes

MCP Servers and Workflows

Layer / File(s) Summary
MCP server configurations
shared/sdd-mcp-distillery.md, shared/sdd-mcp-serena.md
Distillery exposes search, find_similar, relations, recall tools over HTTP with OAuth, scoped to a project filter. Serena provides symbol-level code intelligence via container with LSP integration, degrading gracefully to text search when no language server is available.
MCP tools design documentation
docs/sdd/mcp-tools.md
Reference guide describing both MCP servers, their transports, tool definitions, required configuration via environment variables and secrets, graceful degradation behavior, and smoke-test/leak-scan verification steps.
Distillery sync scheduled workflow
.github/workflows/distillery-sync.md, .github/workflows/distillery-sync.lock.yml
Daily-scheduled workflow syncing Distillery knowledge store with repository specs, decisions, and artifacts. Activation validates secrets and builds agent prompt; agent runs Copilot CLI with Distillery MCP within AWF firewall; conclusion handles failures; safe_outputs processes results.
MCP smoke test manual workflow
.github/workflows/mcp-smoke.md, .github/workflows/mcp-smoke.lock.yml
Manual smoke-test workflow validating both Distillery and Serena MCPs within firewalled Copilot CLI. Activation and agent orchestrate MCP gateway, Safe Outputs server, and CLI execution; conclusion and safe_outputs handle results and failures. Verifies expected tool calls and outcomes.
Documentation navigation
mkdocs.yml
Adds "MCP tools" entry to SDD documentation section in site navigation.

Sequence Diagrams

sequenceDiagram
  participant Cron
  participant Activation
  participant Agent
  participant Distillery
  participant Conclusion
  participant SafeOutputs
  Cron->>Activation: trigger daily
  Activation->>Activation: setup gh-aw, validate secrets
  Activation->>Activation: build/render agent prompt
  Activation->>Agent: upload activation artifacts
  Agent->>Agent: restore artifacts, install Copilot CLI
  Agent->>Distillery: query search/recall tools (MCP)
  Distillery->>Agent: return semantic results
  Agent->>Agent: run within AWF firewall sandbox
  Agent->>Agent: redact logs, upload agent artifacts
  Conclusion->>Conclusion: check agent outcome
  Conclusion->>Conclusion: report failures if configured
  SafeOutputs->>SafeOutputs: process and upload safe output items
Loading
sequenceDiagram
  participant Manual
  participant Activation
  participant Agent
  participant Gateway
  participant Distillery as Distillery MCP
  participant Serena as Serena MCP
  participant CopilotCLI as Copilot CLI
  participant Conclusion
  Manual->>Activation: workflow_dispatch
  Activation->>Activation: setup gh-aw, validate secrets
  Activation->>Agent: upload activation artifacts
  Agent->>Agent: restore artifacts, install Copilot/AWF
  Agent->>Gateway: start MCP gateway (HTTP/container)
  Gateway->>Distillery: expose via guard policy
  Gateway->>Serena: expose via guard policy
  Agent->>CopilotCLI: mount MCP servers as CLIs
  CopilotCLI->>Distillery: call search tool
  CopilotCLI->>Serena: call symbol/project tools
  CopilotCLI->>CopilotCLI: execute within AWF firewall
  Agent->>Agent: stop gateway, redact logs
  Agent->>Agent: upload agent artifacts
  Conclusion->>Conclusion: check outcomes, handle failures
Loading

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

Possibly related issues

Poem

🐰 Two servers join the fray—one learns, one knows,
Distillery whispers what the repo shows,
Serena sees the symbols, deep and true,
In workflows orchestrated, safe and new! ✨

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title 'Unit 3: Distillery and Serena MCP infrastructure' accurately reflects the main objective: implementing Unit 3 with Distillery and Serena MCP server infrastructure. It is specific, clear, and directly tied to the changeset.
Description check ✅ Passed The description is comprehensive and directly related to the changeset, detailing each requirement delivery, deviations from spec, security review, and verification steps. It clearly explains what was added and why.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch sdd/unit-3-mcp

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@norrietaylor norrietaylor left a comment

Copy link
Copy Markdown
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Review: Unit 3 (Distillery and Serena MCP infrastructure)

Verdict: minor-only. All six Unit 3 requirements (R3.1 to R3.6) are met, the diff compiles clean (gh aw compile: 3 workflows, 0 errors), markdownlint is clean, lock files are byte-identical to a fresh recompile (no hand-editing), and no private literals or em dashes appear in hand-authored files. The two accepted deviations (workflow sources at .github/workflows/, inline MCP declarations rather than imports:) are implemented soundly. The findings below are all Minor or Nit; none block merge.

Spec compliance

All requirements verified against the diff:

  • R3.1: shared/sdd-mcp-distillery.md declares HTTP transport, OAuth via Authorization: Bearer, documents search/find_similar/relations/recall, endpoint and credential as vars/secrets expressions. Met.
  • R3.2: project scoping documented as mandatory with the project filter; "An agent that cannot scope a query does not run the query" is a strong, testable rule. Met.
  • R3.3: distillery-sync.md is a daily-cron agentic workflow ingesting docs/specs/, decisions/, and issues/PRs via gh-sync. Met.
  • R3.4: shared/sdd-mcp-serena.md declares oraios/serena over the working tree, pins no language, documents graceful degradation. Met.
  • R3.5: no literal hostname, org slug, bot name, or absolute path in either fragment; verified. Met.
  • R3.6: mcp-smoke.md is a workflow_dispatch workflow resolving both servers; docs/sdd/mcp-tools.md documents the dispatch procedure and is in mkdocs.yml nav. Met.

Proof artifacts (fragment files exist and pass leak-scan; gh aw compile succeeds with both MCP declarations) are present or achievable.

Minor

  1. Source docs claim "opens no issue" but the compiled workflow grants issues: write and a create_issue tool. .github/workflows/distillery-sync.md:46 states "adds no comment, opens no issue, and opens no pull request"; .github/workflows/mcp-smoke.md:53 makes the same claim. Neither source declares a safe-outputs: block, so gh-aw injects its default create_issue safe-output: distillery-sync.lock.yml and mcp-smoke.lock.yml both compile a safe_outputs job with issues: write and hand the agent a create_issue tool ({"create_issue":{"labels":[...],"max":1,...}}). The prose and the compiled grant disagree. This is gh-aw default behavior also present in the already-merged sample.lock.yml, so it is not newly introduced, but these two sources are the first to assert the opposite in prose. Fix: either declare an explicit empty safe-outputs: {} (or whatever gh-aw's suppress form is) so the read-only claim and the issues: permission match, or soften the prose to acknowledge the default error-reporting issue path. The first is better for least privilege: a read-only smoke/sync workflow should not carry issues: write.

  2. Serena working-tree mount is :rw in the read-only smoke test. .github/workflows/mcp-smoke.md:25 mounts ${GITHUB_WORKSPACE}:${GITHUB_WORKSPACE}:rw while the smoke test's allowed list is read-only only (activate_project, find_symbol, get_project_structure). For an install-verification smoke run, :ro is sufficient and tighter (least privilege, shared/principles.md surgical-changes). The shared fragment sdd-mcp-serena.md:32 correctly keeps :rw because executing agents need symbol edits; the smoke test does not. Fix: change the smoke test mount to :ro.

Nit

  1. vars.DISTILLERY_MCP_URL flows into the firewall allowDomains list verbatim. In both lock files the gh-aw firewall config embeds ${{ vars.DISTILLERY_MCP_URL }} as an allowed domain. If an operator sets that variable to a full URL (https://host/path) rather than a bare hostname, the firewall allowlist entry may not match as intended. Not a defect in this PR (it is gh-aw's handling of an mcp-servers.url), but worth a one-line note in docs/sdd/mcp-tools.md that DISTILLERY_MCP_URL should be set so its host component is resolvable, so an operator does not misconfigure it.

Notes (no action needed)

  • The two accepted deviations are handled cleanly: the fragments carry valid mcp-servers: frontmatter and the inline declarations in the two workflows are consistent with the fragments, so Unit 4's relocation will be a move plus an imports: swap, not a rewrite.
  • engine: copilot is consistent across all three workflow sources and matches the merged sample.md.
  • The "untrusted input" framing in both fragments (sdd-mcp-distillery.md:70-75, sdd-mcp-serena.md:85-89) is a good, spec-aligned addition (Security Considerations: "MCP outputs are untrusted input").
  • DISTILLERY_OAUTH_TOKEN is referenced only as a secrets. expression and is in the firewall --exclude-env list in the lock files; secret handling is sound.

norrietaylor and others added 2 commits May 16, 2026 21:54
mcp-smoke's Serena tools (activate_project, find_symbol, get_project_structure) are all read-only, so the working-tree mount needs no write access. Addresses a least-privilege finding from the PR #12 review.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Units 2 and 3 both added an SDD nav entry. Resolved into one SDD section listing both the pipeline guide and the MCP tools page.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 4

🧹 Nitpick comments (1)
shared/sdd-mcp-serena.md (1)

20-20: ⚡ Quick win

Pin the Serena image to an immutable version (tag+digest) for workflow reproducibility.

Using :latest makes workflow behavior non-deterministic across runs. Pin to a specific version and digest (e.g., ghcr.io/github/serena-mcp-server:v1.x.x@sha256:...) from the GitHub Container Registry to keep MCP behavior reproducible and auditable.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@shared/sdd-mcp-serena.md` at line 20, Replace the floating image tag
"ghcr.io/github/serena-mcp-server:latest" with an immutable tag+digest (for
example "ghcr.io/github/serena-mcp-server:vX.Y.Z@sha256:...") so the container
reference in the container field is pinned and reproducible; locate the
container: "ghcr.io/github/serena-mcp-server:latest" line in the
shared/sdd-mcp-serena.md file and update it to the specific release tag and its
sha256 digest obtained from the GitHub Container Registry.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In @.github/workflows/distillery-sync.md:
- Around line 43-45: Reword the “read-only” claim for gh-sync or remove the
workflow's issue-creation paths: locate references to gh-sync and the workflow’s
failure-reporting/issue-write steps (the compiled workflow paths that create or
report an issue on failure) and either disable those issue-creation/reporting
steps or change the markdown text to say the run is read-only for content
changes but may report failures to GitHub (i.e., clarify it does not modify
repository content like issues/PRs only if issue-creation is removed; otherwise
explicitly state failure-reporting issues may be created).
- Around line 49-60: The workflow currently calls gh-sync without explicitly
passing the Distillery project, leaving project selection to inference; update
the gh-sync invocation(s) that process docs/specs/, decisions/, issues and pull
requests to include the explicit project variable (vars.DISTILLERY_PROJECT) so
the sync is deterministic; ensure the repository is derived from the workflow
context (github.repository or github.repository_owner/github.event) and passed
as the scope to gh-sync as before, and add a short summary log that references
vars.DISTILLERY_PROJECT when reporting counts of spec files, decision files,
issues, and pull requests ingested/refreshed.

In @.github/workflows/mcp-smoke.md:
- Around line 49-52: The workflow requires distillery.search to be scoped by a
project but does not provide a concrete slug; update the workflow to supply a
deterministic project slug (e.g., set vars.DISTILLERY_PROJECT) or use a known
source such as the repository slug (github.repository) when calling
distillery.search; specifically, ensure the action that invokes
distillery.search references the chosen variable (vars.DISTILLERY_PROJECT or
github.repository) so the project filter is always populated and the smoke test
queries the intended project.
- Around line 61-62: The README/description line "This workflow is read-only. It
posts no comment, opens no issue, and opens no pull request." is inaccurate
because the compiled workflow still contains issue-write failure/reporting
paths; update the workflow description or the workflow logic: either
remove/disable the failure-reporting steps that create issues/comments/PRs (the
steps that run on error and call issue/comment/PR actions), or edit the sentence
to narrow it (e.g., "This workflow is read-only except for optional
failure-reporting paths that may open issues or post comments"). Locate the
failure-reporting steps by searching for actions that create issues/comments/PRs
and the description text in the workflow and make the corresponding change.

---

Nitpick comments:
In `@shared/sdd-mcp-serena.md`:
- Line 20: Replace the floating image tag
"ghcr.io/github/serena-mcp-server:latest" with an immutable tag+digest (for
example "ghcr.io/github/serena-mcp-server:vX.Y.Z@sha256:...") so the container
reference in the container field is pinned and reproducible; locate the
container: "ghcr.io/github/serena-mcp-server:latest" line in the
shared/sdd-mcp-serena.md file and update it to the specific release tag and its
sha256 digest obtained from the GitHub Container Registry.
🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

  • Push a commit to this branch (recommended)
  • Create a new PR with the fixes

ℹ️ Review info
⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: e1fce270-d44f-4411-b34a-a8dc73ef9d78

📥 Commits

Reviewing files that changed from the base of the PR and between ffb4507 and c29bdde.

📒 Files selected for processing (8)
  • .github/workflows/distillery-sync.lock.yml
  • .github/workflows/distillery-sync.md
  • .github/workflows/mcp-smoke.lock.yml
  • .github/workflows/mcp-smoke.md
  • docs/sdd/mcp-tools.md
  • mkdocs.yml
  • shared/sdd-mcp-distillery.md
  • shared/sdd-mcp-serena.md

Comment on lines +43 to +45
`gh-sync` is incremental: it indexes new and changed content and leaves
unchanged content alone. The run is read-only with respect to GitHub; it adds
no comment, opens no issue, and opens no pull request.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

“Read-only” wording conflicts with actual workflow behavior.

This text says no issue is opened, but the compiled workflow has issue-write failure/reporting paths. Either disable failure issue creation or reword this section to avoid a false guarantee.

🧰 Tools
🪛 LanguageTool

[style] ~44-~44: ‘with respect to’ might be wordy. Consider a shorter alternative.
Context: ...ged content alone. The run is read-only with respect to GitHub; it adds no comment, opens no is...

(EN_WORDINESS_PREMIUM_WITH_RESPECT_TO)

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In @.github/workflows/distillery-sync.md around lines 43 - 45, Reword the
“read-only” claim for gh-sync or remove the workflow's issue-creation paths:
locate references to gh-sync and the workflow’s failure-reporting/issue-write
steps (the compiled workflow paths that create or report an issue on failure)
and either disable those issue-creation/reporting steps or change the markdown
text to say the run is read-only for content changes but may report failures to
GitHub (i.e., clarify it does not modify repository content like issues/PRs only
if issue-creation is removed; otherwise explicitly state failure-reporting
issues may be created).

Comment on lines +49 to +60
All ingested content is filed under this repository's own Distillery project
(the configured project slug). The store may be shared, so this workflow
ingests only this repository's content and files it under this repository's
project. It never ingests, reads, or writes another project's content.

## Procedure

1. Determine the repository from the workflow context.
2. Call `gh-sync` for the `docs/specs/` path, the `decisions/` path, and this
repository's issues and pull requests, scoped to this repository's project.
3. Log a short summary: how many spec files, decision files, issues, and pull
requests were ingested or refreshed.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major | ⚡ Quick win

Make Distillery project scoping explicit and deterministic.

This workflow requires project-scoped gh-sync, but it never references vars.DISTILLERY_PROJECT, so project selection is left to inference. That can ingest into the wrong Distillery project.

🔧 Suggested patch
 ## Procedure

 1. Determine the repository from the workflow context.
-2. Call `gh-sync` for the `docs/specs/` path, the `decisions/` path, and this
-   repository's issues and pull requests, scoped to this repository's project.
+2. Resolve the Distillery project slug from `${{ vars.DISTILLERY_PROJECT }}`.
+3. Call `gh-sync` for the `docs/specs/` path, the `decisions/` path, and this
+   repository's issues and pull requests, with a mandatory `project` filter set
+   to that slug.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In @.github/workflows/distillery-sync.md around lines 49 - 60, The workflow
currently calls gh-sync without explicitly passing the Distillery project,
leaving project selection to inference; update the gh-sync invocation(s) that
process docs/specs/, decisions/, issues and pull requests to include the
explicit project variable (vars.DISTILLERY_PROJECT) so the sync is
deterministic; ensure the repository is derived from the workflow context
(github.repository or github.repository_owner/github.event) and passed as the
scope to gh-sync as before, and add a short summary log that references
vars.DISTILLERY_PROJECT when reporting counts of spec files, decision files,
issues, and pull requests ingested/refreshed.

Comment on lines +49 to +52
1. **Distillery.** Call the Distillery `search` tool with a short query (for
example, the repository name or a term from a known spec), scoped to this
repository's project via the `project` filter. Confirm the call returns a
result set.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major | ⚡ Quick win

Project filter requirement needs an explicit slug source.

You require distillery.search to be scoped by project, but this workflow does not expose vars.DISTILLERY_PROJECT. Without a concrete slug source, the smoke test can query the wrong project and give misleading pass/fail results.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In @.github/workflows/mcp-smoke.md around lines 49 - 52, The workflow requires
distillery.search to be scoped by a project but does not provide a concrete
slug; update the workflow to supply a deterministic project slug (e.g., set
vars.DISTILLERY_PROJECT) or use a known source such as the repository slug
(github.repository) when calling distillery.search; specifically, ensure the
action that invokes distillery.search references the chosen variable
(vars.DISTILLERY_PROJECT or github.repository) so the project filter is always
populated and the smoke test queries the intended project.

Comment on lines +61 to +62
This workflow is read-only. It posts no comment, opens no issue, and opens no
pull request.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

Read-only claim is not strictly true in the generated workflow.

The compiled workflow contains issue-write failure/reporting paths, so “opens no issue” is inaccurate as written. Please either disable that path or narrow this claim.

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In @.github/workflows/mcp-smoke.md around lines 61 - 62, The README/description
line "This workflow is read-only. It posts no comment, opens no issue, and opens
no pull request." is inaccurate because the compiled workflow still contains
issue-write failure/reporting paths; update the workflow description or the
workflow logic: either remove/disable the failure-reporting steps that create
issues/comments/PRs (the steps that run on error and call issue/comment/PR
actions), or edit the sentence to narrow it (e.g., "This workflow is read-only
except for optional failure-reporting paths that may open issues or post
comments"). Locate the failure-reporting steps by searching for actions that
create issues/comments/PRs and the description text in the workflow and make the
corresponding change.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Unit 3: Shared agent infrastructure (Distillery and Serena MCP)

1 participant