Production and integration share the newly released tree.
Production 7d011708 and integration e74ac22b preserve different ancestry but share Git tree 92b4d149. Staging was regenerated from the same integration source at 201beb9c.
master · 7d011708
PR #32 exact-tree September 15 release.
develop · e74ac22b
PR #31 semantic-reliability and tenant-portability integration.
201beb9c
Generated from e74ac22b.
Semantic reliability and tenant portability reached the released Scout tree.
PR #31 integrated the long-running reliability branch into protected develop; PR #32 then promoted the exact qualified tree to master. The release keeps Recruiter Alpha as the reference application while moving core identity, context, relationship, and validation logic further away from recruiter-specific assumptions.
| September 15 qualification evidence | Recorded result |
|---|---|
| Deterministic suite | 1452/1452 |
| Retrieval Recall@6 | 1.000 |
| Dated DEV conversation gate | 100/132 turns · 20/33 conversations |
| Qualified feature CI | 34922407613 |
| Develop merge-result CI | 34925217993 |
One static source for each page.
Current release, accounting, roadmap, diagrams, and study material now live directly in HTML. Retired browser correction layers no longer compete with the original page text. Source references are pinned to audited revisions; navigation includes Learn and Roadmap, and documentation search includes full section text.
The discourse branch advanced to cddb3bc with a documentation-only handoff after the two implementation commits. It remains development work.
The discourse branch was an intermediate checkpoint before later integration.
feat/generic-conversation-sets@cddb3bc is +3/-0 from develop@4f5ee971 at recheck. At the September 5 snapshot it was not in staging or production; later semantic/discourse work was integrated through subsequent pull requests and the September 15 release.
f145f8c · discourse frames.Server-owned state tracks the active conversational relation and ordered user-introduced alternatives without domain vocabulary. Corrections/removals/ordinals mutate the set; assistant mentions do not become authoritative set members.cddb3bc · cache-hit state + clarification.Discourse state is committed before cache/direct-KB early returns, and unresolved plural-set questions can route through a CLARIFICATION control mode instead of a scope decline.test/discourse-frames.test.js. No GitHub Actions run/status or PR for this head was exposed at the audit recheck, so no new pass count is asserted.Phase 7/8, widget fixes, and release hardening reached production source.
The August 27 product-site snapshot still showed Phase 02 on an active feature branch. The accepted conversation-gate work was merged, widget initialization/input/scroll fixes were merged, release hardening was applied, staging was regenerated from 4f5ee971, and PR #29 promoted the exact qualified tree to production.
master@b071e4e4 and develop@4f5ee971 share Git tree a0066cc8; staging records 4f5ee971.| September 5 released-tree verification | Recorded result | Scope |
|---|---|---|
| Local test suite | 1019/1019 | Release-hardening tree; zero skipped in PR evidence. |
| Retrieval Recall@6 | 1.000 | Released-tree retrieval verification. |
| Retrieval MRR@6 | 0.942 | Released-tree retrieval verification. |
| Phase 7/8 live gate | 94/132 turns · 21/33 conversations | Dated pre-release run at 4d39995. |
| Inference-unavailable outcomes | 14/38 remaining failures | Observed failure category in that dated run; not proof of external root cause. |
The qualified August integration tree was promoted with a master-parented release branch.
PR #22 replaced a conflicting direct develop→master PR (#21) with a clean release branch based on production ancestry. The same release pattern was used again on September 5.
All visible branch heads were checked, then checked again before publication.
ProjectHub: 35 visible branches. Twelve branch heads are newer than the August 27 product-page cutoff; 23 point to older July/August work. ProjectHub-dev: two visible branches. During the audit, feat/generic-conversation-sets moved from the released develop pointer to cddb3bc, so the later branch state is the one documented here.
Current post-release branch categories: runtime development cddb3bc (+3/-0 from develop) and dependency-only maintenance c32e83b (one lockfile-only commit ahead of master).
Cloudflare neuron accounting moved to exact model identifiers.
Scout's hosted model remained @cf/meta/llama-3.1-8b-instruct-fast. The old metadata associated 4,119 / 34,868 neurons per million input/output tokens with that identifier. Cloudflare publishes those rates for @cf/meta/llama-3.1-8b-instruct-fp8-fast instead and does not document the identifiers as billing aliases.
@cf/meta/llama-3.1-8b-instruct-fast has no guessed rate. @cf/meta/llama-3.1-8b-instruct-fp8-fast and @cf/meta/llama-3.1-8b-instruct-fp8 keep their own published rates.null / unknown.| Cloudflare platform fact | Documented value |
|---|---|
| Included Workers AI allocation | 10,000 neurons/day |
| Daily reset | 00:00 UTC |
| Workers Paid usage above the included allocation | $0.011 / 1,000 neurons |
@cf/meta/llama-3.1-8b-instruct-fast token-to-neuron rate is unpublished.Profile-summary evidence was narrowed and intent classification moved back to the original question.
Two consecutive develop fixes changed how profile-summary requests select evidence before generation.
a624cc2 · classify profile evidence intent from the original question.The RAG agent had classified evidence intent from a rewritten query. The fix now tries the original question first because rewriting could scramble phrases such as “tell me about” and cause the wrong evidence filter to run.2d958e2 · tighten profile evidence and preserve the exact title.Profile evidence filtering stopped admitting generic experience and skills-* chunks, and the profile guardrail now instructs generation to keep the exact documented title/location instead of replacing the title with vague words such as “person” or “candidate.”develop in the captured source state. They should not be described as production behavior merely because they are the newest commits.Post-release changes continued across RAG, contracts, recovery, validation and conversation handling.
The current branch comparison shows substantive integrated changes after the production line diverged. The largest source differences are not limited to prompt wording.
| Area | Develop-only difference in captured comparison |
|---|---|
lib/rag-agent.js | 174 changed lines in the comparison, including evidence selection and guardrail behavior. |
lib/response-contract.js | 185 changed lines, including semantic answer planning and claim-state handling. |
lib/recovery-contract.js | 70 additions, expanding recovery behavior after generation/validation problems. |
lib/grounding-validator.js | 39 changed lines in the captured comparison. |
lib/conversation-resolver.js | 36 changed lines around contextual resolution. |
data/recruiter-knowledge.json | Large knowledge-tree change in the comparison, 121 additions and 384 deletions. |
At this August checkpoint these changes were integrated separately from production. The September 5 release later promoted the qualified integration tree.
Cloudflare Llama 3.1 8B Fast became the qualified runtime model configuration.
Commit d32b75e changed the configured Cloudflare model from Llama 3.2 3B Instruct to @cf/meta/llama-3.1-8b-instruct-fast across runtime documentation, model policy, runtime facts, UI usage display, cost configuration and provider-rate assumptions.
Llama 3.1 8B Instruct Fast
The current production runtime facts identify this as the normal Cloudflare Workers AI generative target.
Initial rate mapping was later corrected
The Aug. 21 model change also updated usage-rate assumptions. A later exact-model audit showed that 4,119 / 34,868 belongs to -fp8-fast, not Scout's configured -fast identifier. The model remained @cf/meta/llama-3.1-8b-instruct-fast; the accounting metadata was corrected.
Ollama remained non-default
The change retained Ollama as dev/test and optional fallback architecture rather than making it the normal production generation path.
A validated develop line was promoted to master.
PR #19 merged develop into master. Its release record states that staging smoke tests passed 9/9 and the development backend was healthy on commit d7530d0 before promotion.
| Release property | Recorded value |
|---|---|
| Pull request | #19 · “Release: promote validated develop to master” |
| Head source | develop at d7530d0910293a2e26cfc1c18c7046c34864d767 |
| Merge commit | 0a235c60df0e518736bb77e20f20aa83a18aff62 |
| PR size | 93 commits · 121 changed files |
| Pre-release evidence in PR body | Staging smoke tests 9/9; dev backend healthy. |
develop-only hardening entries.The earlier acceptance score was reclassified after a stricter semantic scorer found false positives.
Commit e013a32 added an offline strict semantic scorer, strict evaluation cases, scorer unit tests, re-score tooling, stored strict outputs, and initial contract fixes. The commit records an offline re-score baseline of 131/178, 73.6%.
Old “GOOD” labels were not sufficient.
Examples in the preserved artifacts included future-capability answers starting with an unsupported “No,” role-fit contracts with missing direct-answer state, and open-world employment claims collapsed into definitive negatives.
Scorer + engine contract fixes.
The change added strict validators for open-world claims, unknown skills, future capability, role fit and project technology, then adjusted response-contract/completeness/recovery behavior exposed by those failures.
An accidental stale-desktop merge to master was reverted.
PR #13 removed four net accidental additions introduced by the desktop merge and added a local source-of-truth document stating that GitHub is authoritative. The PR description explicitly records that the core Scout runtime files were not overwritten by the accidental push.
| Removed accidental additions | Recovery result |
|---|---|
.github/copilot-instructions.md | Removed as part of the accidental tree cleanup. |
CLAUDE.md | Removed in this recovery PR; later reintroduced deliberately under new guardrail work. |
| Screenshot asset | Removed from the production tree. |
server-gcp.js | Removed from the accidental merge state. |
GitHub-first guardrails were added to local clones and coding agents.
PR #14 turned the recovery lesson into repository controls rather than leaving it as a one-time cleanup.
master and develop were blocked.Multi-PC, IDE and agent handoff checks were added.
PR #15 added a GitHub-backed workspace flow for switching between machines and coding tools without treating a local checkout as authoritative.
Begin from remote truth
Fetches GitHub state and opens/creates a GitHub-backed feature branch rather than starting from a stale protected branch.
Detect unsafe workspace state
Checks stale/diverged/wrong-origin/protected-branch conditions before editing.
Handoff committed feature work
Refuses dirty, diverged or protected-branch publication before a machine/IDE handoff.
The PR explicitly states that these changes did not alter Scout runtime behavior or production application code.
Staging was isolated from production sources and routing.
PR #4 changed the staging site so it could load its local widget artifact and point chat requests at the development backend rather than accidentally using production behavior. It also replaced the staging sync with a deterministic prepared-tree operation and a source marker.
Local staging widget + dev API
The dev host can use ./ProjectHub.js and set the development chat API endpoint instead of hardcoding the production widget/API pair.
Prepared staging tree
The sync process writes a STAGING-SOURCE.json marker and staging-specific Pages/instruction files so the deployment target is traceable back to canonical develop.
CI added artifact, knowledge, secret and retrieval gates.
PR #5 expanded the Test and Verify workflow with checks that can fail the branch rather than simply report information.
| Gate added | Recorded behavior |
|---|---|
| Analytics bundle freshness | Build and compare analytics/dist to committed output. |
| Knowledge JSON validation | Parse JSON and require core knowledge sections. |
| Committed-secret scan | Search source files for several API-key token patterns. |
| Staging routing check | Reject a staging page that points only at the production widget route. |
| Retrieval quality gate | Fail if Recall@6 falls below 0.90. |
Deployment scripts gained branch guards, backups, health checks and rollback.
PR #6 hardened both production and development GCP deploy scripts.
master; development deploy requires develop; dirty working trees are blocked.Frontend publication was gated behind backend verification.
PR #7 removed the automatic production Pages trigger on master and changed the intended release order so the backend could be deployed and verified before the matching frontend was published.
master.Source promotion happens first.Evaluation results are attached to the code/scorer that produced them.
The changelog does not collapse historical measurements into one “accuracy” number. The project has changed both the engine and the evaluator, so results need their scope.
| Measurement | Context | How this changelog treats it |
|---|---|---|
| 114/115 + 40/40 old acceptance results | Pre-strict scorer accepted false positives later identified in raw outputs. | Historical only; not a release-quality claim. |
| 131/178 · 73.6% | Offline strict re-score baseline recorded by e013a32. | Historical correction baseline, not current production quality. |
| Recall@6 1.000 on 40-query retrieval set | Retrieval-specific evaluator/golden set, separate from conversational answer quality. | Can be reported only as the scoped retrieval benchmark and rerun with the repository evaluator. |
How entries are classified.
Reached master
An entry is called production only when the cited source shows promotion/release into the production line or is itself the production branch state.
Present on develop
Integrated changes can be real, tested code without being production. They are labeled separately until promoted.
Preserved for provenance
Old architecture, workflows and scores stay useful for explaining how the system changed, but are not silently converted into current behavior.
Dates are based on the cited commit/PR records. Branch-head and ahead/behind values are snapshots captured when this page was rebuilt and can change after new repository activity.