Repository navigation
docs(adr): let agent entries carry harness overrides - #8965
Conversation
E2E tests did not runE2E tests run automatically for pull requests authored by users with write access or higher. For other contributors, someone with write access must add the Reason: See E2E testing guide for details. |
Code Review by Qodo🐞 Bugs (0) 📘 Rule violations (0) 📎 Requirement gaps (0)
Great, no issues found!Qodo reviewed your code and found no material issues that require reviewTip of the day💡 Did you know, you can keep summaries lean with Findings visible per group, which tucks the rest behind a View link |
PR Summary by QodoDocument agent-entry overrides for harness environment values
AI Description
Diagram
High-Level Assessment
Files changed (10)
|
Site previewPreview: https://02f304ce-site.fullsend-ai.workers.dev Commit: |
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
|
Hey! Sorry, I didn't notice the |
|
@rh-hemartin Thanks! I did consider a flat entry (the ADR mentions it) but I see two issues. First, some names exist on both sides. Then, The |
If repos management (i.e. |
|
+1 to keeping the With the block, an entry's own fields and harness fields stay apart: agents:
- name: review
subagents: # entry field: personas, by name (0155)
user-experience: { enabled: false }
harness: # harness fields (this ADR)
env:
sandbox: { REVIEW_FINDING_SEVERITY_THRESHOLD: medium }A flat entry would make harness Two smaller points:
@rh-hemartin, does keeping the block work for you, given the |
|
@ggallen Thanks, I wasn't aware of that. I checked, and I was wrong: only the |
|
I like even less the fact that we do have
Maybe we can bring this to one of our meetings tomorrow? |
I tent to agree that most top-level keys we have defined now that ovveride things that are defined by the harness need to go away, especially if the semantics are not exactly like the ones for the harness. I still think we need a "harness" key because there are things that belong in the ganets list but not the harness, for example:
|
|
Since there's no consensus yet on the next step, I'll hold off on updating the ADR. Please let me know if there's anything I can do or any changes I should make. |
|
Hello! Wanted to come back here. I agree with Barak and Wayne, so I think this is unblocked for you @gwenneg . So let's go with harness key and as followups to clean this we will retire |
3289718 to
42eed21
Compare
|
@rh-hemartin sounds good, thanks! I pushed the updated ADR. It's now ADR 0162 because 0154 got taken on main. Quick summary of what changed:
One part is new and nobody suggested it in the review: point 6, which covers All the details are in the PR description, including the reasons for each choice and the code links. |
|
For point 6, I would remove
Because that would be a "bug", as we didn't get that far in the implementation but we do want to go there. So failing the Otherwise looks good to me |
|
@rh-hemartin Thanks! I'm waiting for additional input from other reviewers before I remove or update the details from point 6 you highlighted. |
|
Point 6: +1 to @rh-hemartin. The end state is CEL-only routing (#2902), with
Keying the check on the agent name rather than on On |
Add ADR 0162: an agents: entry in config.yaml may carry a harness: block that works as a harness derived from the agent's harness, so a repo can change harness settings without writing and pinning a base: harness. Point the notes in ADRs 0049, 0080, 0081, 0091 and 0112 to it, and describe the block in architecture.md, the harness field reference, the config reference and the config source inventory. Refs fullsend-ai#8143 Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com> Signed-off-by: Gwenneg Lepage <10584698+gwenneg@users.noreply.github.com>
42eed21 to
4a59362
Compare
waynesun09
left a comment
There was a problem hiding this comment.
Point 6 now keys on the agent name with the "until #2902" warning. LGTM.
Superseded: the ADR was reworked as ADR 0162 in review (harness block, point 6 updated) and has two maintainer approvals.
ADR 0162 merged in #8965, so the two links to it now point at the file instead of the pull request. Assisted-by: Claude Signed-off-by: Wayne Sun <gsun@redhat.com>
What
This adds ADR 0162 (it was 0154, but that number got taken on main). An
agents:entry inconfig.yamlcan carry aharness:block that works like a harness built on the agent's harness, with nothing pinned:Today the only way to change a harness setting is a
base:harness. That pins an agents commit, so the repo stops getting agent updates (#5802). With the block, a repo changes the setting and keeps getting updates.This is the ADR only. The code comes in a separate PR.
What changed after review
env(@ifireball).fullsend run,fullsend lint,fullsend lockand dispatch all compose it (@ifireball).config.base.yamlandconfig.yamllayer like harness inheritance (@ifireball).harness:key stays (@waynesun09, agreed by @rh-hemartin and @ifireball). Retiring the entry'striggeris follow-up work (@rh-hemartin).env(@waynesun09).harness.triggeron a built-in agent is not evaluated and loads with a warning, instead of failing.Other choices worth a look
base:, because the entry'ssourcealready does that job.forgeandrunner_env, because both are deprecated: ADR 0088 replacesforgewithoverlays, and ADR 0055 replacesrunner_envwithenv.runner. A new place to set harness fields shouldn't start with deprecated fields.runner_envwould also let the block add runner variables the harness doesn't declare, because the run merges it into the runner environment. That's also why the block'soverlayscan't setrunner_env. Harnesses that still use either field keep working with a block: names in theirforge:blocks count as declared, and the block can useoverlaysonruntime.forgeinstead. No fleet harness usesrunner_envtoday.schema_version, under ADR 0127's rules like any layer: absent means1, and a block whose version differs from the agent's harness fails to load. So when an agents release moves a harness to a new schema version, a repo with a block on that agent updates the block when it upgrades.config.yamlcan replace a value fromconfig.base.yamlbut not remove it.envvariables the harness doesn't declare.repos.yamlpreset could change security settings through it without the gate flagging it. Extending the gate stays follow-up work, and it may be worth doing before the feature ships.Code evidence
All links are at
087ccff70, the currentmain.config.yamlis read from the same trusted ref as harness files: on GitHub the PR base commit forpull_request_targetandpull_request_review, otherwise the triggering commit (reusable-dispatch.yml#L154, same expression in every agent job); on GitLab the default branch (run-agent-job.sh#L345-L370).fullsend lockskip built-in agents (entries withoutsource) (registry.go#L48-L53). This is why lock keeps not locking them (ADR 0091).triggeronly routes review, retro, triage and prioritize (dispatch_route.go#L50-L55, #L194).roleto set who may trigger it (dispatch_route.go#L255), so a block that setsrolechanges that.base:chain that mixes schema versions (compose.go#L326).runner_envinto the runner environment besideenv.runner(run.go#L1292-L1308), so allowing it in the block would bypass the declared-name check.overlaysentry carries the same fields as aforge:block,runner_envincluded (forge.go#L18-L41), and a matching overlay'srunner_envis merged into the harness's (forge.go#L417). That's why the block'soverlayscan't set it either.forge:blocks and overlays are resolved before a child merges on top (compose.go#L642-L653), so a block'soverlayswork on harnesses that still useforge:.envvalues are plain strings, so~becomes an empty value, not a removal (harness.go#L313-L314).fullsend runpins only what a current lock entry covers and only warns otherwise (run.go#L698-L742). A lock entry's freshness is the harness file's hash only (lock.go#L867), which is why the ADR says a block change counts as a harness change.Notes for reviewers
architecture.md,harness-fields.md,config-source-inventory.mdandconfig-reference.md..fullsend/. That's an agents-repo change.Refs #8143, #7719, #7223, #8903
🤖 Generated with Claude Code