docs(identity): forbid unsourced quantitative or factual claims#67
Merged
Conversation
spashii
added a commit
that referenced
this pull request
May 24, 2026
#68) ## What this enables Slack-triggered sessions can't exit cleanly anymore without **closing the loop** — defined as: a `chat.postMessage` / `chat.update` must come AFTER the last substantive outward-facing tool call in the session. An ACK at the start followed by work + silence does NOT close the loop. ## The corrected rule (timing-based, not 'any post') **Substantive outward-facing** (operator expects a report): - `gh pr create / edit / merge`, other non-Slack bash - `consult_opus` - `worker` / `parallel_workers` - `edit_file` / `write_file` outside `/data/journal/` - `fetch_url` **Inward** (operator doesn't need a report): - `read_file`, `grep`, `glob_files` - Journal writes (`/data/journal/`) - Slack housekeeping bash (`setStatus`, `reactions.add`, `conversations.replies`) `closed_loop` is True iff a post comes AFTER the last outward call (or no outward work happened at all — a question Sam answered without tools). If the gate fires, the daemon spawns a retry whose only job is to read the previous session's audit-log slice and post the summary. The retry agent is told explicitly **not to trust the journal** (since the journal-claiming-without-evidence pattern is the parent failure mode). ## Consequences - Today's failure mode — Sam runs 30+ tool calls, opens a PR, exits clean, ✅ fires, operator sees no reply — is structurally blocked. Two sessions today (`f31a21c5` after 'Can you update to add these tools?' and `624e27ec` after 'Use opus to review this'); both opened PRs (#66, #67) but never posted. After this PR: caught and retried. - The ACK-first rule from SAM-32 doesn't false-pass the gate anymore. Posting an ACK doesn't satisfy the rule unless a final reply also comes after the substantive work. - Sessions with no outward work (`read_file` only or no tools at all) just need any single post — they're 'Sam answered a question' shapes. - Scheduled (daily-maintenance) and retry sessions are exempt — silence is allowed for routine work, retries have their own failure path. ## How to verify - `pytest tests/` — 119 passed (22 new in `test_silent_exit.py` + 97 existing, no regressions). The new tests include 4 explicit ACK-then-work-then-silent cases that would have false-passed the earlier rule. - Next Slack mention where Sam opens a PR but forgets to post: the logs will show `session exited cleanly but never posted to Slack; spawning retry to narrate (session=...)` and the retry will post the summary in-thread. ## Tier Tier 3 (`src/runtime/session.py`, `src/runtime/daemon.py`, `src/runtime/prompts.py`) + Tier 1 (`src/capabilities/slack.md` documents the gate in Sam's source). Closes the silent-exit class of bug surfaced by the 2026-05-24 14:30 and 15:55 sessions.
spashii
approved these changes
May 24, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What is this change?
Adds a new bullet point to
src/identity.mdunder honesty rules explicitly forbidding fabrication of quantitative or factual claims in reviews, PR descriptions, and comments.What did Sam notice that led to this?
During an Opus mentor review of PR #62, the mentor noticed that Sam (Flash) made a quantitative claim in analysis about unit test assertions that was not backed by real committed measurements, pointing out a critical gap in our honesty guardrails.
Tier?
Tier 2 (Identity change)
Confidence?
100% confident. This is a vital alignment rule to prevent hallucinations from creeping into our reviews and metrics.