This commit is contained in:
team 1
2026-05-01 11:08:02 +02:00
parent 0c7fca9b46
commit b466f85e2f
4 changed files with 283 additions and 3 deletions

View File

@@ -16,6 +16,10 @@ Diese Referenz ist gegen den realen Codebestand abgeglichen und ersetzt die vera
| `mto:agent:ingest:version` | Ingest | Startet einen Ingest für eine konkrete Dokumentversion |
| `mto:agent:ingest:run` | Ingest Jobs | Führt einen vorhandenen `IngestJob` aus |
| `mto:agent:system:rebuild` | System | Globaler Hard-Rebuild von Chunks, Vektorindex, Tags und optional Service-Reload |
| `mto:agent:config:validate` | Config / Governance | Validiert die effektive RetrieX-Konfiguration |
| `mto:agent:config:audit-source` | Config / Governance | Auditiert YAML-Mappings gegen PHP-Fallbacks und Defaults |
| `mto:agent:config:dump-effective` | Config / Governance | Gibt die effektive Konfigurationsinventur aus |
| `mto:agent:regression:test` | Config / Governance | Fuehrt Offline-Regression-Guards fuer stabile Pfade aus |
| `mto:agent:vector:rebuild` | Vector | Baut den Chunk-Vektorindex aus `index.ndjson` neu |
| `mto:agent:vector:control` | Vector Service | Install, Start, Stop, Reload und Status des Python-Vector-Service |
| `mto:agent:vector:health` | Vector | Konsistenzcheck für Chunk-NDJSON und Vektorindex |
@@ -480,9 +484,71 @@ Die bisherige Datei war in mehreren Punkten nicht mehr codekonform. Wesentliche
---
## 11. Fazit
Der aktuelle Custom-CLI-Umfang des Systems besteht aus **14 projektspezifischen Commands**. Für den operativen Betrieb sind besonders relevant:
## 11. Config-Governance / YAML-only Guardrails
These commands are mandatory for changes that touch YAML-backed configuration, prompt/retrieval behavior, intent detection, commerce/shop logic or regression-sensitive answer paths.
### `mto:agent:config:validate`
Validates the effective RetrieX configuration.
**Signature**
```bash
bin/console mto:agent:config:validate [--json]
```
**Expected result before merge**
- status `OK`
- no errors
### `mto:agent:config:audit-source`
Audits YAML-backed configuration against remaining PHP defaults, fallback accessors and constructor defaults.
**Signature**
```bash
bin/console mto:agent:config:audit-source [--details] [--json]
```
**Expected result before merge**
- no missing YAML mappings
- no new undocumented PHP-only semantic constants
- no constructor defaults without YAML/service-parameter mapping
Use `--details` for reviewable console output and `--json` for machine-readable CI output.
### `mto:agent:config:dump-effective`
Dumps the effective RetrieX configuration inventory.
**Signature**
```bash
bin/console mto:agent:config:dump-effective [--summary]
```
Use `--summary` for a compact review view.
### `mto:agent:regression:test`
Runs offline regression guards for stable configuration paths.
**Signature**
```bash
bin/console mto:agent:regression:test [--json]
```
**Expected result before merge**
- status `OK`
- all checks pass
This command protects the regression-sensitive 1.4.2/1.5.0 baseline, especially the Testomat 808 / 0,02 deg dH / indicator type 300 flow and related configuration paths.
---
## 12. Fazit
Der aktuelle Custom-CLI-Umfang des Systems besteht aus mindestens **18 projektspezifischen Commands**. Für den operativen Betrieb sind besonders relevant:
- `mto:agent:ingest:run`
- `mto:agent:system:rebuild`

125
DEVELOPER_POLICIES.md Normal file
View File

@@ -0,0 +1,125 @@
# RetrieX Developer Policies
Status: binding after completion of the YAML-only migration through Patch 11.0a.
These policies protect the stable RetrieX configuration architecture. They are intentionally operational and must be followed by developers before a change is merged.
## 1. Source of truth
The functional configuration source of truth is YAML under `config/retriex/`.
This applies especially to:
- vocabulary, synonyms, stopwords and token lists
- intent rules and commerce routing
- search repair and query enrichment rules
- prompt texts, labels, output-priority rules and grounding rules
- agent messages, source labels, status messages and templates
- retrieval thresholds, token groups and scoring-related rule lists
- shop matching and commerce query parsing rules
- model and index defaults
PHP classes may read and validate these values, but must not silently redefine them.
## 2. No new PHP-only defaults
New configurable values must be added in YAML first.
Required pattern:
1. Add the value to the matching file in `config/retriex/`.
2. Wire the value through `config/services.yaml` when constructor injection is needed.
3. Expose/read it through the matching `src/Config/*Config.php` class.
4. Keep `mto:agent:config:validate` green.
5. Keep `mto:agent:config:audit-source --details` free of missing YAML mappings.
Not allowed:
- new constructor defaults that act as business or answer logic
- new hardcoded keyword lists in `src/`
- new PHP-only constants for semantic or product-specific behavior
- hidden fallbacks that change retrieval, prompt, shop or intent behavior when YAML is incomplete
## 3. Allowed technical constants
Technical constants are allowed only when they are not business, prompt, retrieval, product, intent or shop semantics.
Examples that may be acceptable:
- internal status strings
- command exit handling
- filesystem mode details
- non-semantic implementation identifiers
If a constant influences answer quality, matching, routing, scoring, prompt behavior or shop behavior, it belongs in YAML.
## 4. Fallback policy
Fallbacks are not a normal extension mechanism.
A fallback is only acceptable when all conditions are met:
- the value has a YAML path or explicit service-parameter mapping
- the fallback is documented as defensive infrastructure behavior
- the audit does not report it as missing YAML mapping
- the fallback cannot change semantic answer behavior in normal operation
If in doubt, move the value to YAML.
## 5. Required checks before merge
Every change touching `src/Config`, `config/retriex`, prompt, retrieval, intent, commerce, shop matching, SSE/job completion or answer grounding must run:
```bash
php bin/console cache:clear
php bin/console mto:agent:config:validate
php bin/console mto:agent:config:audit-source --details
php bin/console mto:agent:regression:test
```
Expected result:
- config validation: OK
- regression baseline: OK
- source audit: no missing YAML mappings
- no new undocumented PHP-only semantic constants
- no new constructor defaults without YAML/service-parameter mapping
## 6. Protected regression baseline
The following behavior must not regress:
- lowest water-hardness limit remains `0,02 deg dH` for Testomat 808
- follow-up indicator answer remains focused on indicator type 300
- accessory price follow-up for indicator type 300 returns the matching indicator products, not device prices
- history-based shop follow-up such as `suche im shop` keeps the relevant product context
- advisory product questions may use shop/catalog fallback when RAG knowledge is insufficient
- SSE/job completion must close loader/think states reliably, including reconnect/watchdog cases
Offline checks are covered by `mto:agent:regression:test`. End-to-end behavior still needs manual or integration verification when the touched code path is not covered offline.
## 7. Strict YAML validation
Strict YAML validation remains intentionally deferred.
Until a later patch explicitly enables it, developers must enforce these policies through:
- code review
- `mto:agent:config:validate`
- `mto:agent:config:audit-source --details`
- `mto:agent:regression:test`
Strict mode must remain configurable and disabled by default when it is introduced later.
## 8. Pull request checklist
Use this checklist for every relevant PR:
- [ ] All new configurable behavior is in `config/retriex/*.yaml`.
- [ ] No new semantic keyword/token/prompt list was added directly to PHP.
- [ ] No new constructor default was added without YAML/service-parameter mapping.
- [ ] `mto:agent:config:validate` is OK.
- [ ] `mto:agent:config:audit-source --details` has no missing YAML mappings.
- [ ] `mto:agent:regression:test` is OK.
- [ ] The protected functional flows were manually checked if the touched area can affect them.
- [ ] README or patch README documents the reason for any intentionally accepted technical fallback.

View File

@@ -471,6 +471,10 @@ Verifizierte relevante Commands im aktuellen Stand:
- `mto:agent:tags:job:run`
- `mto:agent:tag:health`
- `mto:agent:system:rebuild`
- `mto:agent:config:validate`
- `mto:agent:config:audit-source`
- `mto:agent:config:dump-effective`
- `mto:agent:regression:test`
- `mto:agent:test:shop-search`
- `mto:agent:test-vector`
- `mto:agent:user:create`
@@ -482,3 +486,28 @@ Verifizierte relevante Commands im aktuellen Stand:
```bash
bin/console mto:agent:vector:control --status
bin/console mto:agent:vector:control --install --start --reload
```
---
## Developer Policies / Governance
The YAML-only migration is treated as completed after Patch 11.0a, as long as these checks stay green:
```bash
php bin/console mto:agent:config:validate
php bin/console mto:agent:config:audit-source --details
php bin/console mto:agent:regression:test
```
From now on, developers must follow `DEVELOPER_POLICIES.md`.
Core rules:
- YAML under `config/retriex/` is the source of truth for configurable behavior.
- No new PHP-only semantic defaults, token lists, prompt texts, matching rules or business fallbacks.
- New configurable behavior must be added through YAML and wired explicitly.
- Regression-sensitive flows from the 1.4.2/1.5.0 baseline must remain protected.
- Strict YAML validation is deferred and must remain disabled by default when introduced later.

View File

@@ -0,0 +1,60 @@
# RetrieX Patch 12 - Developer Policies after YAML-only Migration
This patch does not continue the YAML-only migration and does not enable strict validation.
Patch 1 through 11.0a are treated as the completed YAML-only migration baseline. Patch 12 documents the developer rules that must be followed from now on to prevent regressions and new PHP-only configuration drift.
## Scope
Changed files:
- `DEVELOPER_POLICIES.md`
- `README.md`
- `COMMAND_REF.md`
## What changed
### Developer policies
Added a binding policy document with rules for:
- YAML as source of truth
- no new PHP-only defaults
- no hardcoded semantic lists in core code
- fallback restrictions
- mandatory pre-merge checks
- protected regression baseline
- deferred strict validation
- PR checklist
### README
The README now points developers to `DEVELOPER_POLICIES.md` and lists the config-governance commands together with the other important commands.
The previously open final bash code block in the README was also closed while appending the policy section.
### Command reference
`COMMAND_REF.md` now includes the existing config/governance commands:
- `mto:agent:config:validate`
- `mto:agent:config:audit-source`
- `mto:agent:config:dump-effective`
- `mto:agent:regression:test`
## Intentional non-changes
No PHP runtime behavior was changed.
No retrieval, prompt, shop, agent, SSE, audit or validation logic was changed.
Strict YAML validation remains deferred and disabled.
## Recommended validation
```bash
php bin/console cache:clear
php bin/console mto:agent:config:validate
php bin/console mto:agent:config:audit-source --details
php bin/console mto:agent:regression:test
```
In this ZIP work environment, `vendor/` is not included, so Symfony console commands may need to be run in the real project checkout after dependencies are installed.