chore: enable emoji reactions for agent runs on this repo

[ralphbean]

Enable emoji reactions for this repo.

[qodo-code-review]

PR Summary by Qodo

Enable emoji reactions for agent run status

⚙️ Configuration changes 🕐 Less than 5 minutes

AI Description

• Enables emoji reactions when agent runs start.
• Enables emoji reactions when agent runs complete.

High-Level Assessment

The repository-level status notification configuration is the appropriate approach because it uses the existing Fullsend feature directly; custom automation or code changes would add unnecessary complexity.

Files changed (1) +4 / -0

Other (1) +4 / -0

config.yamlEnable agent-run reaction notifications +4/-0

Enable agent-run reaction notifications

• Adds repository-level Fullsend status notification settings that enable emoji reactions at agent-run start and completion.

.fullsend/config.yaml

[fullsend-ai-review]

🤖 Finished Review · ✅ Success · Started 2:21 PM UTC · Completed 2:28 PM UTC

Commit: e8373b7 · View workflow run →

Runtime: claude · Model: opus → claude-opus-4-6 · Effort: high · Cost: $1.12

[qodo-code-review]

Code Review by Qodo

🐞 Bugs (0) 📘 Rule violations (0) 📜 Skill insights (1)

1. status_notifications indentation mismatches 📜 Skill insight ⚙ Maintainability

Description

The new block uses two-space nesting while the existing .fullsend/config.yaml content uses
four-space indentation. This makes the modified YAML inconsistent with the established style in the
same configuration file.

Code

.fullsend/config.yaml[R26-27]

+  reaction:
+    start: enabled

Relevance

●●● Strong

Accepted history supports enforcing established YAML formatting conventions; this file uses
four-space nesting.

PR-#873
PR-#573

ⓘ Recommendations generated based on similar findings in past PRs

Evidence

PR Compliance ID 1538351 requires modified config files to match existing indentation conventions.
The pre-existing configuration uses four spaces per nesting level, while the added reaction and
child settings use two spaces per level.

.fullsend/config.yaml[8-28]
Skill: code-implementation

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 new `status_notifications` block uses two-space indentation, which does not match the established four-space nesting style in the existing configuration.

## Issue Context
Keep YAML configuration formatting consistent with the style already used in `.fullsend/config.yaml`.

## Fix Focus Areas
- .fullsend/config.yaml[25-28]

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

---

Context sources

✅ Compliance rules (platform): 56 rules

✅ Skills: 4 invoked

  code-review

  code-implementation

  pr-review

  docs-review

Review mode: ⚖️ Balanced

Tip of the day

💡 Did you know, you can hide the parts of a finding you never read, like the evidence or the agent prompt

More tips ↗ | Customize Qodo ↗ | Qodo docs ↗

[fullsend-ai-review]

Looks good to me

[waynesun09]

Approving at e8373b7.

Same four-line status_notifications.reaction.{start,completion} enablement as fullsend-ai/fullsend#6594, applied to this repo. Verified the key is consumed rather than silently ignored (internal/config/config.go, internal/harness/forge.go, internal/cli/reconcilestatus.go in fullsend, with behaviour-test and doc coverage) — worth confirming because the run path does not validate config.

Config-only, CI green, no unresolved review threads.

[fullsend-ai-retro]

🤖 Finished Retro · ✅ Success · Started 7:42 PM UTC · Completed 7:52 PM UTC

Commit: e8373b7 · View workflow run →

Runtime: claude · Model: opus → claude-opus-4-6 · Effort: high · Cost: $4.18

[fullsend-ai-retro]

Workflow went well. PR #1007 was a 4-line config-only change by a human author (ralphbean) adding status_notifications.reaction.{start,completion}: enabled to .fullsend/config.yaml. The review agent (run 32858737229, $1.12, ~9 min) correctly classified it as a mechanical/value-only change, dispatched sub-agents at trivial scope, and approved. Human reviewer waynesun09 also approved after cross-repo verification that the config key is consumed by fullsend. PR merged via merge queue with all CI green.

Two minor observations — both covered by existing issues:

1. Model alias mismatch (evidence for Review orchestrator passes roster-table model alias instead of frontmatter model to sub-agents #256). The style-conventions sub-agent's frontmatter specifies model: claude-sonnet-4-6@default, but the orchestrator dispatched it with the roster-table alias sonnet, which resolved to the retired claude-sonnet-4-5@20250929. The sub-agent failed on first attempt. The orchestrator recovered by re-dispatching with the default model — better fallback behavior than the silent skip described in Review sub-agents should handle model unavailability with fallback or explicit alerting #379, but the root cause (Review orchestrator passes roster-table model alias instead of frontmatter model to sub-agents #256) is still active 5+ weeks after filing.

2. Indentation inconsistency not flagged. The new status_notifications block uses 2-space indentation while the rest of the file uses 4-space. qodo-code-review flagged this as a Medium-severity style insight; the fullsend review agent did not. The style-conventions sub-agent triggered its early-exit path for "feature flag toggle" changes and did no style checking. The orchestrator noticed the inconsistency during synthesis but deferred to the sub-agent's empty findings. The human reviewer also did not mention it. The PR was merged as-is — no one considered the cosmetic inconsistency worth blocking for.

No new proposals filed. The model alias mismatch is the only systemic finding, and it is already tracked by #256 (roster-table alias vs frontmatter model) and #379 (model unavailability fallback).