Use paired tags for standing & per-turn context

[salman1993]

Why

PR #6503 bundled a broader context compiler with several prompt-shape and telemetry changes, making it difficult to isolate whether paired XML-like top-level boundaries improve agent behavior. This keeps the follow-up experiment focused on framing only.

What

• Replace top-level standing and per-turn bracket headers with paired tags while preserving inner section content and event/message framing
• Carry only metadata already present in dynamic headers as attributes, such as thread counts, truncation, event type, and batch count
• Preserve every section body verbatim so the model executes the exact bytes reviewed in Desktop
• Keep routing metadata, event content, batching, and delivery behavior unchanged
• Teach Desktop diagnostics to parse the new framing while retaining compatibility with archived bracket-framed sessions; ambiguous paired boundaries render as the complete captured prompt

Risk Assessment

Medium — the change is limited to agent prompt framing and diagnostic parsing, but it affects both standing context and every dynamic agent turn. Bodies and delivery behavior remain unchanged, and compatibility parsing remains for prior sessions.

References

• Follow-up to Add deterministic agent context compiler #6503, scoped only to the paired-tag framing hypothesis

Update — 2026-08-24

• Addressed review feedback by removing entity encoding/decoding from the execution and diagnostic paths.
• Added regressions for literal closing tags, placeholders, entity-looking text, ampersands, and authored boundary whitespace.
• Verified cargo test -p buzz-acp (805 unit + 9 integration), Desktop tests (5,412 before the main sync; 5,439 in the pre-push gate), Desktop typechecking, and Tauri clippy/tests.
• Live local relay startup and message ingestion passed. The live ACP reply step is blocked locally because installed Goose 1.0.23 no longer provides the documented goose acp command and no alternate ACP adapter is installed.

---

Update Aug 25, 12:13 EDT: Extended paired tags to per-turn top-level sections.

• Converted context, conversation/thread context, event batches, and steer/interrupt boundaries without changing their inner bodies.
• Preserved existing header metadata as attributes only; added no new prompt metadata.
• Verified 806 Buzz ACP unit tests plus 9 integration tests, 5,441 Desktop tests, Desktop typechecking and formatting, and all differential pre-push lanes.

---

Update Aug 25, 13:58 EDT: Addressed framing review feedback.

• Updated operational base instructions to reference the emitted <context> section and added a regression guard against stale [Context] instructions.
• Restored batched steer/interrupt cardinality in Desktop diagnostic titles with focused coverage for both paths.
• Verified 807 Buzz ACP unit tests plus 9 integration tests, 5,442 Desktop tests, Desktop typechecking and formatting, and every differential pre-push lane including Tauri clippy/tests.

---

Update Aug 25, 15:37 EDT: Hardened legacy transcript compatibility.

• Semantic standing-context parsing now requires paired framing at the start and complete input consumption.
• Historical bracket-framed personas keep literal balanced tag examples in their original section; malformed or mixed current framing displays as the complete captured prompt.
• Added regressions for the reported legacy persona case and trailing unframed text; verified 60 focused parser tests, 5,444 full Desktop tests, formatting, and typechecking.

---

Update Aug 25, 16:31 EDT: Preserved slash-command prompt block boundaries.

• Desktop now sets aside a valid connector-facing slash-command block only when the following block begins recognized paired framing, parses the semantic blocks normally, and retains the command as visible Prompt metadata.
• Added an end-to-end transcript regression using the production three-block ACP shape, including the user bubble, author pubkey, event ID, and grouped prompt context.
• Verified 113 combined transcript tests, 5,445 full Desktop tests, formatting, typechecking, and all applicable pre-push lanes.

Generated with Codex

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 622628b650

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[salman1993]

🤖 Paired closing tags give the model a clear signal for where each section ends, instead of relying on the next header to imply the boundary. Intuitively, that should make it easier to keep context, instructions, memory, and incoming events from bleeding into one another—especially as prompts get longer.

[atishpatel]

Reviewed exact head 2da5ff7a2847095a3b6705bf366d459a101b7201: approved — no actionable findings.

The change consistently applies paired top-level framing across modern/legacy standing context and per-turn sections without mutating section bodies. Attribute escaping is confined to generated metadata, and Desktop decodes only those attributes. The diagnostic parser fails closed to the full captured prompt on malformed/ambiguous framing, retains bracket-framed history compatibility, and preserves a connector-facing slash-command block separately from semantic context.

Independent validation on a dedicated clean worktree at this SHA:

• cargo test -p buzz-acp: 807 unit + 9 lifecycle tests passed
• cargo clippy -p buzz-acp --all-targets -- -D warnings: passed
• cargo fmt --all -- --check: passed
• Desktop pnpm test: 5,445 passed
• Mutation check: removing quote escaping from generated attributes was caught by semantic_section_attributes_do_not_mutate_body
• GitHub checks are green