Skip to content

docs(adr): add ADR 0161, repo config limits what a run artifact publishes - #9182

Merged
waynesun09 merged 7 commits into
mainfrom
fullsend-9122-adr
Nov 11, 2026
Merged

waynesun09 merged 7 commits into
mainfrom
fullsend-9122-adr

Conversation

@waynesun09

@waynesun09 waynesun09 commented Nov 7, 2026 •

Copy link
Copy Markdown
Member

Adds ADR 0161 for #9122. It amends ADR 0021: a repo-level artifacts setting in config.yaml limits what a run artifact publishes for each run source, so a public repo can take work from issue trackers that are not public without publishing what its agents read. Jira is the first such source; the setting is not Jira-specific.

artifacts:
  content: all          # every run: all (default) | metadata | none
  by_source:
    jira: metadata      # runs started from a Jira issue

Decision

Level Artifact holds
all Everything in output/, as today (default)
metadata Only run-level files: metrics.json, eval-measurements.jsonl, run-telemetry.jsonl without conversation content. security/findings.jsonl stays on the runner, because a finding's detail can quote tool output
none No artifact
  • The stricter of content and by_source[<run source>] wins. Keys are the run source names (github, gitlab, jira, manual, schedule, the same as event.source.system) and stay open strings for future tracker adapters.
  • No provider-keyed map: for the shipped agents jira-ro selects the same runs as jira, so one name is enough (recorded under Options).
  • metadata is an allowlist. Filtering builds a staged copy after eval-measure and post-scripts, and fails closed.
  • Relaxing toward all goes through the ADR 0122 safety gate.

Implementation lands separately via #9122 after this merges.

Files

  • docs/ADRs/0161-repo-config-limits-run-artifact-content.md: new ADR
  • docs/ADRs/0021-jsonl-reasoning-trace-exposure.md: "Amended by" note
  • docs/architecture.md, docs/problems/operational-observability.md: cross-references

Evidence (main at 5a9629d)

  • action.yml, step "Upload fullsend artifacts": uploads ${{ github.workspace }}/output under if: always(), with no skip or filter.
  • internal/scaffold/fullsend-repo-gitlab/.gitlab/ci/fullsend-agent.yml: artifacts: paths: [output/], expire_in: 1 week.
  • internal/cli/run.go: iteration-<N>/ holds output.jsonl (raw stream), transcripts/ and output/. Run-level files are metrics.json and security/findings.jsonl.
  • internal/cli/content_collector.go: conversation content enters run-telemetry.jsonl only when Level 3 capture is on, and that file is exempt from the host output scan.
  • internal/agentnew/roles.go: retro is the only role with the github-artifacts provider, so it reads past run artifacts.
  • No code implements ADR 0021's per-agent suppression.

🤖 Generated with Claude Code

@qodo-code-review

Copy link
Copy Markdown

PR Summary by Qodo

Document repo-level limits on published run artifacts

📝 Documentation 🕐 10-20 Minutes

Grey Divider

AI Description

• Add ADR 0161 defining repo-level artifact limits for runs that read private sources.
• Specify strictest-wins policy, metadata-only publishing, and fail-closed staging across forges.
• Amend ADR 0021 and link the decision from architecture and observability docs.
Diagram

graph TD
  Config["Repo config"] --> Resolve["Strictest policy"] --> Level{"Publish level"}
  Level -->|all| Full["Full output"] --> Stage["Staged copy"] --> Forge["Forge upload"]
  Level -->|metadata| Allow["Metadata allowlist"] --> Stage
  Level -->|none or error| Skip["Skip upload"]
Loading
High-Level Assessment

The following are alternative approaches to this PR:

1. Keep ADR 0021's per-agent opt-out
  • ➕ Allows different artifact policies for different agents.
  • ➖ Does not account reliably for private data introduced by a run's trigger source or attached providers.
  • ➖ Requires each agent configuration to anticipate its data sources.
2. Sanitize transcripts before upload
  • ➕ Could preserve more debugging and retro context.
  • ➖ Cannot reliably identify all private business text or personal data.
  • ➖ Makes the publication boundary harder to verify than an allowlist.

Recommendation: The proposed repo-level, strictest-wins policy with a staged metadata allowlist is the stronger publication boundary. Reviewers should assess its documented trade-off: metadata and none intentionally remove transcripts needed by retro, resumption, and follow-up workflows. Implementation remains separate.

Files changed (4) +131 / -2

Documentation (4) +131 / -2
0021-jsonl-reasoning-trace-exposure.mdMark the per-agent suppression decision as amended +4/-0

Mark the per-agent suppression decision as amended

• Links ADR 0161 and clarifies that repo-level artifact controls replace ADR 0021's per-agent suppression opt-out.

docs/ADRs/0021-jsonl-reasoning-trace-exposure.md

0161-repo-config-limits-run-artifact-content.mdDefine repo-level run artifact publication policy +125/-0

Define repo-level run artifact publication policy

• Specifies all, metadata, and none levels; strictest-wins source and provider overrides; layered configuration; and fail-closed staging. Records forge scope and the effect of withholding transcripts from downstream consumers. No runtime behavior changes in this PR.

docs/ADRs/0161-repo-config-limits-run-artifact-content.md

architecture.mdLink artifact limits from the architecture overview +1/-1

Link artifact limits from the architecture overview

• Adds ADR 0161 alongside the existing trace-exposure decision and notes that repo-level controls replace the per-agent opt-out.

docs/architecture.md

operational-observability.mdRecord the artifact-access decision in observability notes +1/-1

Record the artifact-access decision in observability notes

• Links ADR 0161 in the trace-access discussion while leaving broader observability access and retention questions open.

docs/problems/operational-observability.md

@qodo-code-review

qodo-code-review Bot commented Nov 7, 2026 •

Copy link
Copy Markdown

Code Review by Qodo

🐞 Bugs (0) 📘 Rule violations (0) 🔗 Cross-repo conflicts (0) 📜 Skill insights (1)

Grey Divider


Remediation recommended

1. ADR context runs past three paragraphs ✗ Dismissed
Description
The Context section of ADR 0161 is four prose paragraphs plus two bullets, and it restates
upload-path, telemetry and provider detail that ADR 0021, ADR 0050 and the operational-observability
problem doc already cover. The checklist caps Context at one to three short paragraphs, so the
section drifts from the ADR template and becomes harder for later readers to scan.

2. ADR upload claims lack provenance links 📜 Skill insight ⚙ Maintainability
Description
The ADR Context states current behavior as fact: every agent run uploads its whole output/
directory with no skip or filter, and GitLab uses artifacts: paths: [output/]. Neither statement
links to the PR, issue, or ADR that introduced that upload behavior, and the only ADR links (0021
and 0050) cover transcript exposure and telemetry content rather than the upload step.
Code

docs/ADRs/0161-repo-config-limits-run-artifact-content.md[R25-27]

+Every agent run uploads its whole `output/` directory as the run artifact:
+`fullsend-<agent>` on GitHub Actions, and job artifacts on GitLab CI. Each run
+directory holds one `iteration-<N>/` directory per iteration, with the raw
Relevance

●● Moderate

No close accepted or rejected precedent for provenance-link requests on ADR current-behavior claims.

PR-#5244
PR-#7812

ⓘ Recommendations generated based on similar findings in past PRs

Evidence
The added Context paragraph describes current upload behavior without any link to the change that
introduced it, which Compliance rule 4443994 requires for each current-behavior description in an
ADR. The PR description's file-level evidence does not substitute for that provenance link.

docs/ADRs/0161-repo-config-limits-run-artifact-content.md[25-34]
Skill: writing-adrs

Agent prompt
The issue below was found during a code review. Follow the provided context and guidance below and implement a solution

Issue description
The ADR Context in docs/ADRs/0161-repo-config-limits-run-artifact-content.md states current upload behavior (whole `output/` uploaded under `if: always()` on GitHub, and `artifacts: paths: [output/]` on GitLab) without linking to the PR, issue, or ADR that introduced that behavior. Compliance rule 4443994 requires such a provenance link; an implementation-file citation alone does not satisfy it.

Fix Focus Areas
- docs/ADRs/0161-repo-config-limits-run-artifact-content.md[25-34]

Recommended Fix
Add a link to the PR, issue, or ADR that introduced the run-artifact upload behavior next to the sentence describing it. If no such record exists, say so explicitly in the ADR so the claim is clearly marked as unattributed.

ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools

Dismiss ↗ | View ↗


3. Metadata artifact may still leak conversation content ✓ Resolved

Resolving commit: d48ffcb

Resolution reason
N/A
Description
The metadata level promises run-telemetry.jsonl with conversation content removed, but the ADR
never defines how content is identified or stripped, and its fail-closed guarantee covers only level
resolution, not the content scrub. If the scrub misses a gen_ai content attribute, such as tool
arguments or input messages that ADR 0050 and ADR 0108 record at Level 3, the private text the
setting is meant to withhold is still published in the artifact.

Grey Divider

Context sources
❌ Tickets: failed to load — Ticket collection could not establish complete evidence
✅ Compliance rules (platform): 96 rules
✅ Skills: 5 invoked
  writing-user-docs
  writing-adrs
  check-patch-coverage
  cutting-releases
  adr-corner
✅ Cross-repo context — repo relationships
✅ REVIEW.md
Review mode: Auto: 🚀 Fast: Docs-only ADR and cross-references; no runtime code changes, so no extended review.

Grey Divider

Tip of the day
💡 Did you know, you can import rules and skills only from the repositories your team follows

More tips ↗ | Customize Qodo ↗ | Qodo docs ↗

Grey Divider

Qodo Logo

@fullsend-ai-review

fullsend-ai-review Bot commented Nov 7, 2026 •

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 1:34 AM UTC · Completed 1:48 AM UTC

Commit: c2309c1 · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $2.41

@github-actions

github-actions Bot commented Nov 7, 2026 •

Copy link
Copy Markdown

Site preview

Preview: https://214b01a2-site.fullsend-ai.workers.dev

Commit: d48ffcb89d143a3dd8fde31723dee4b5b3abc522

@fullsend-ai-review fullsend-ai-review Bot added the risk/moderate PR risk: moderate label Nov 7, 2026
@fullsend-ai-review

fullsend-ai-review Bot commented Nov 7, 2026 •

Copy link
Copy Markdown

Risk Assessment: moderate (2/5)

Details

Documentation-only addition of ADR 0161 with no protected paths or code modifications, elevated to moderate due to high recent commit churn and multi-author contention on touched architecture documentation.

Previous run

Risk Assessment: moderate (2/5)

Details

Documentation-only addition of ADR 0161 with no protected paths or code modifications, elevated to moderate due to high recent commit churn and multi-author contention on touched architecture documentation.

Previous run (2)

Risk Assessment: moderate (2/5)

Details

Documentation-only addition of ADR 0161 with no protected paths, elevated to moderate due to high recent commit churn and multi-author contention on touched architecture documentation.

Previous run (3)

Risk Assessment: moderate (2/5)

Details

Documentation-only addition of ADR 0161 with no protected paths, elevated to moderate due to high recent commit churn and multi-author contention on touched architecture documentation.

Previous run (4)

Risk Assessment: moderate (2/5)

Details

Documentation-only addition of ADR 0161 with no protected paths or code modifications, elevated to moderate due to high recent commit churn and multi-author contention on touched architecture documentation.

Previous run (5)

Risk Assessment: moderate (2/5)

Details

Documentation-only addition of ADR 0161 with no protected paths or code modifications, elevated to moderate due to high recent commit churn and multi-author contention on touched architecture documentation.

@fullsend-ai-review

fullsend-ai-review Bot commented Nov 7, 2026 •

Copy link
Copy Markdown

Looks good to me

Previous run

<!-- fullsend:review-findings-v2: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 -->

Looks good to me


Labels: PR adds an ADR and amends related documentation.

Previous run (2)

<!-- fullsend:review-findings-v2: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 -->

Looks good to me

Previous run (3)

<!-- fullsend:review-findings-v2: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 -->

Looks good to me

Earlier findings

  • docs/ADRs/0161-repo-config-limits-run-artifact-content.md:93, logic-error, resolved — the metadata row no longer lists security/findings.jsonl and the allowlist bullet explains why it stays on the runner.
  • docs/architecture.md:718, incomplete-doc, resolved — the observability open question now links ADR 0161.
Previous run (4)

<!-- fullsend:review-findings-v2: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 -->

Review

Findings

Medium

  • [logic-error] docs/ADRs/0161-repo-config-limits-run-artifact-content.md:93 — The metadata allowlist treats security/findings.jsonl as free of content, but it can hold source or tool-response text. internal/security/hooks/unicode_posttool.py adds decoded hidden tag-character text to each finding's detail, and that is written to findings.jsonl. A Jira issue body containing hidden text could reach a metadata-level artifact, defeating that level's purpose. Still present in this push (the table row is unchanged).
    Remediation: Under metadata, either require a content-free projection of security findings (keep structural fields and counts, drop content-bearing detail text) or leave security/findings.jsonl out of the allowlist.

Low

  • [incomplete-doc] docs/architecture.md:718 — The Observability open question about agent log access still cites only ADR 0021. ADR 0161 amends it and decides part of the question; the matching question in docs/problems/operational-observability.md was updated, this one was not.
    Remediation: Annotate the open question with a link to ADR 0161, matching the wording used in docs/problems/operational-observability.md.

Next steps:

  • /fs-fix — agent addresses review findings automatically
  • /fs-fix <your instruction> — agent fixes with your specific guidance
  • Push commits directly — review re-runs automatically on push
  • /fs-fix-stop — disable automatic fix runs for this PR
Previous run (5)

<!-- fullsend:review-findings-v2:eyJ2ZXJzaW9uIjoyLCJhY3Rpb24iOiJyZXF1ZXN0LWNoYW5nZXMiLCJmaW5kaW5ncyI6W3sic2V2ZXJpdHkiOiJtZWRpdW0iLCJjYXRlZ29yeSI6ImxvZ2ljLWVycm9yIiwiZmlsZSI6ImRvY3MvQURScy8wMTYxLXJlcG8tY29uZmlnLWxpbWl0cy1ydW4tYXJ0aWZhY3QtY29udGVudC5tZCIsImlkIjoiZl84MjljNTllMjY0NzI4MDI2IiwibGluZSI6NzMsImFjdGlvbmFibGUiOnRydWUsImRpbWVuc2lvbiI6ImNvcnJlY3RuZXNzIn1dfQ== -->

Review

Findings

Medium

  • [logic-error] docs/ADRs/0161-repo-config-limits-run-artifact-content.md:73 — The metadata allowlist treats security/findings.jsonl as content-free, but it can hold text taken from tool results. internal/security/hooks/unicode_posttool.py appends decoded hidden text to a finding's detail, and internal/cli/run.go downloads the sandbox findings into the run-level security/findings.jsonl. Copying that file unchanged under metadata can publish content from private sources, which contradicts the ADR's aim of withholding conversation content.
    Remediation: Define a metadata-only projection of security findings that excludes free-text fields such as detail, or omit security/findings.jsonl under metadata. Keep the original locally for auditing. findings.jsonl is hash-chained (security.VerifyChain in run.go), so a field-stripped copy would no longer verify. The ADR should say whether the published copy is a separate projection or the chained original.

Next steps:

  • /fs-fix — agent addresses review findings automatically
  • /fs-fix <your instruction> — agent fixes with your specific guidance
  • Push commits directly — review re-runs automatically on push
  • /fs-fix-stop — disable automatic fix runs for this PR

fullsend-ai-review[bot]

This comment was marked as outdated.

@fullsend-ai-review

fullsend-ai-review Bot commented Nov 7, 2026 •

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 1:59 AM UTC · Completed 2:11 AM UTC

Commit: 13e8ebc · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $1.65

fullsend-ai-review[bot]

This comment was marked as outdated.

fullsend-ai-review[bot]

This comment was marked as outdated.

@rh-hemartin rh-hemartin left a comment •

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

It does makes sense to me, I'm not sure if we want to adopt a more flexible way to apply this: maybe at harness level, overridden by overlays, overridden by config's agents[] entries, overridden by root config.yaml configuration. And the config.yaml would take precedence. Myabe using CEL expressions?

@fullsend-ai-review

fullsend-ai-review Bot commented Nov 9, 2026 •

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 2:02 PM UTC · Completed 2:09 PM UTC

Commit: 933f6f9 · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $1.03

@fullsend-ai-review
fullsend-ai-review Bot dismissed stale reviews from themself November 9, 2026 14:09

Superseded by updated review

fullsend-ai-review[bot]

This comment was marked as outdated.

@fullsend-ai-review

fullsend-ai-review Bot commented Nov 10, 2026 •

Copy link
Copy Markdown

🤖 Finished Review · ⚠️ Cancelled · Started 7:57 PM UTC · Completed 8:04 PM UTC

Commit: 1404889 · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $1.14

This review was superseded by a newer commit. Check the current pull request HEAD's review status before merging.

@fullsend-ai-review fullsend-ai-review Bot removed the ready-for-merge All reviewers approved — ready to merge label Nov 10, 2026
Give the telemetry scrub its own bullet, and say that artifact
consumers also lose security findings under metadata.

Refs #9122

Assisted-by: Claude
Signed-off-by: Wayne Sun <gsun@redhat.com>
@fullsend-ai-review

fullsend-ai-review Bot commented Nov 10, 2026 •

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 8:06 PM UTC · Completed 8:13 PM UTC

Commit: eea3de8 · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $1.25

fullsend-ai-review[bot]

This comment was marked as outdated.

@fullsend-ai-review
fullsend-ai-review Bot dismissed their stale review November 10, 2026 20:13

Superseded by updated review

@fullsend-ai-review fullsend-ai-review Bot added ready-for-merge All reviewers approved — ready to merge type/adr component/docs User-facing documentation labels Nov 10, 2026

@maruiz93 maruiz93 left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

I have two clarification requests about the security boundary and transcript-dependent automation.

…ve no private store

Assisted-by: Claude
Signed-off-by: Wayne Sun <gsun@redhat.com>
@fullsend-ai-review

fullsend-ai-review Bot commented Nov 11, 2026 •

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 4:28 PM UTC · Completed 4:34 PM UTC

Commit: d48ffcb · View workflow run →

Runtime: pi · Model: sonnet → claude-sonnet-5-5 · Effort: high · Cost: $1.20

@fullsend-ai-review fullsend-ai-review Bot removed the ready-for-merge All reviewers approved — ready to merge label Nov 11, 2026
@fullsend-ai-review
fullsend-ai-review Bot dismissed their stale review November 11, 2026 16:34

Superseded by updated review

@fullsend-ai-review fullsend-ai-review Bot added the ready-for-merge All reviewers approved — ready to merge label Nov 11, 2026
@waynesun09
waynesun09 added this pull request to the merge queue Nov 11, 2026
Merged via the queue into main with commit 35228e6 Nov 11, 2026
88 of 89 checks passed
@waynesun09
waynesun09 deleted the fullsend-9122-adr branch November 11, 2026 17:24

This branch was successfully deployed

1 active and 1 inactive deployments
site-preview — d48ffcb8 Deployed Nov 11, 2026 by github-actions[bot]
dev — d48ffcb8 Deployed Nov 11, 2026 by waynesun09 via behaviour #19706
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

component/docs User-facing documentation ready-for-merge All reviewers approved — ready to merge risk/moderate PR risk: moderate type/adr

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants