a56cd044e5
* feat: independent versioning for integrations
- Add per-integration changelog pages at /changelog/integrations/<name>
- Move main changelog to changelog/index.md (URL unchanged)
- Add --integration flag to generate-changelog for LLM-based per-integration changelog generation
- Add scripts/release-integration.sh <name> <version> for cutting integration releases
- Add .github/workflows/release-integration.yml to publish on integrations/** tags
- Remove integrations from main release.sh and release.yml cycle
* fix: add agno and hermes integration docs to version-0.4 for production build
* chore: apply ruff formatting to generate_changelog.py
* feat: add 4-tab code parity across all documentation examples
Every code snippet Tabs block now has Python, Node.js, CLI, and Go variants.
Raw HTTP/curl tabs replaced with proper SDK calls.
New example files:
- Go: retain.go, recall.go, reflect.go, memory-banks.go, directives.go,
mental-models.go, documents.go, main-methods.go
- Shell: memory-banks.sh, directives.sh, mental-models.sh
- Node.js: mental-models.mjs
Extended example files with missing sections:
- recall.mjs/sh: world/experience/observation types, token-budget, all tag modes
- reflect.sh: reflect-with-params, reflect-disposition, reflect-sources, reflect-with-tags
- reflect.mjs: reflect-with-tags, fixed reflect-sources API usage
- retain.mjs/sh: retain-conversation, retain-batch, retain-files-batch
SDK/CLI additions:
- TypeScript: getMentalModelHistory method
- CLI recall: --tags, --tags-match flags
- CLI reflect: --tags, --tags-match, --include-facts flags
- CLI directive update: --is-active flag
- CLI bank set-config: --retain-mission, --retain-extraction-mode,
--observations-mission, --reflect-mission, --disposition-* flags
Build validation:
- scripts/check-code-parity.mjs validates 4-tab parity across all MDX files
- Integrated into npm run build — fails if any Tabs block is missing a variant
* fix: fix doc examples for Go, Node.js, CLI + add mental model with-id examples
- Fix Go Budget constants: BUDGET_HIGH/LOW/MID → HIGH/LOW/MID
- Fix Go documents.go: ListDocuments returns []map[string]interface{}, use map access
- Fix Go retain.go: use correct relative path for sample.pdf
- Fix Node.js createMentalModel: use positional args (name, sourceQuery) not object
- Add CLI 'history' subcommand for mental models (api.rs, main.rs, mental_model.rs)
- Rebuild TypeScript/Python clients to support id param in createMentalModel
- Add create-mental-model-with-id examples across all 4 languages and docs
* fix: move id param to end of create_mental_model signature for backwards compat
83 lines
2.5 KiB
Bash
Executable file
83 lines
2.5 KiB
Bash
Executable file
#!/bin/bash
|
|
# Reflect API examples for Hindsight CLI
|
|
# Run: bash examples/api/reflect.sh
|
|
|
|
set -e
|
|
|
|
HINDSIGHT_URL="${HINDSIGHT_API_URL:-http://localhost:8888}"
|
|
|
|
# =============================================================================
|
|
# Setup (not shown in docs)
|
|
# =============================================================================
|
|
hindsight memory retain my-bank "Alice works at Google as a software engineer"
|
|
hindsight memory retain my-bank "Alice has been working there for 5 years"
|
|
|
|
# =============================================================================
|
|
# Doc Examples
|
|
# =============================================================================
|
|
|
|
# [docs:reflect-basic]
|
|
hindsight memory reflect my-bank "What do you know about Alice?"
|
|
# [/docs:reflect-basic]
|
|
|
|
|
|
# [docs:reflect-with-context]
|
|
hindsight memory reflect my-bank "Should I learn Python?" --context "career advice"
|
|
# [/docs:reflect-with-context]
|
|
|
|
|
|
# [docs:reflect-with-params]
|
|
hindsight memory reflect my-bank "Summarize my week" --budget high --max-tokens 8192
|
|
# [/docs:reflect-with-params]
|
|
|
|
|
|
# [docs:reflect-disposition]
|
|
hindsight bank set-config my-bank \
|
|
--disposition-skepticism 5 \
|
|
--disposition-literalism 4 \
|
|
--disposition-empathy 2
|
|
hindsight memory reflect my-bank "Should I invest in crypto?"
|
|
# [/docs:reflect-disposition]
|
|
|
|
|
|
# [docs:reflect-sources]
|
|
hindsight memory reflect my-bank "Tell me about Alice" --include-facts
|
|
# [/docs:reflect-sources]
|
|
|
|
|
|
# [docs:reflect-with-tags]
|
|
hindsight memory reflect my-bank "What feedback did the user give?" \
|
|
--tags "user:alice" --tags-match any_strict
|
|
# [/docs:reflect-with-tags]
|
|
|
|
|
|
# [docs:reflect-structured-output]
|
|
# First, create a JSON schema file schema.json:
|
|
cat > schema.json << 'EOF'
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"recommendation": {"type": "string"},
|
|
"confidence": {"type": "string", "enum": ["low", "medium", "high"]},
|
|
"key_factors": {"type": "array", "items": {"type": "string"}}
|
|
},
|
|
"required": ["recommendation", "confidence", "key_factors"]
|
|
}
|
|
EOF
|
|
|
|
# Then use the --schema flag:
|
|
hindsight memory reflect hiring-team \
|
|
"Should we hire Alice for the ML team lead position?" \
|
|
--schema schema.json
|
|
|
|
# Cleanup the temporary schema file
|
|
rm -f schema.json
|
|
# [/docs:reflect-structured-output]
|
|
|
|
|
|
# =============================================================================
|
|
# Cleanup (not shown in docs)
|
|
# =============================================================================
|
|
curl -s -X DELETE "${HINDSIGHT_URL}/v1/default/banks/my-bank" > /dev/null
|
|
|
|
echo "reflect.sh: All examples passed"
|