Previously the session-end protocol told the AI to update profile.md
if new insights emerged, with no guidance on where. Over many sessions
this caused freeform bold-text entries to accumulate without structure.
Now requires each update to match an existing H2 section in the file,
with explicit rules against creating new top-level sections.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
API key auth has 7-day retention with no training. Pro/Max plan auth
follows consumer retention (30 days, or up to 5 years if opted in).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Community feedback pointed out that "real privacy" could be misleading
without distinguishing between local file storage and API server contact.
Added retention comparison table across platforms and linked to official
privacy policies.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Expand Step 6 to categorize files (profile.md, ChatGPT exports, markdown,
PDF), extract profile information, and convert conversations to session
format. Add conditional logic in File Creation to populate profile.md
from imports instead of copying blank template. Add Step 6 for creating
dated session files from imported conversations.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
WebFetch can't handle glob patterns. Now manifest lists each persona,
modality, and structure file explicitly. Update command now checks for
new library options and offers to add them.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Import step now comes before modality selection. If user imports notes,
therapist reads them and recommends modalities based on their history.
Also adds reminder that modalities can be changed and therapist auto-switches.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updates now fetch manifest.json first to discover all updatable components.
This allows 1.0 users to learn about new files (like commands.md) when they
run "update". Safety-protocol.md bumped to 1.1.0 with update notice for 1.0 users.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Moves all customization commands (persona, modality, structure, update,
import) to a separate file that gets copied to .therapy/ during setup.
This allows existing users to receive new commands via the update flow.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Imports now create session files with original dates instead of just
reading once and extracting to profile. This provides natural relevance
decay as new sessions accumulate. Also adds post-setup import command.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Consolidates inner-dialogue-deeper content into the main repo. Removes
expansion pack gating, Gumroad references, and the two-tier setup flow.
All communication styles and therapeutic modalities are now included and
offered directly during setup. Bumps kit_version to 2.0.0.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Informed by analysis of GPT-4o's distinctive conversational patterns,
adds conversation-level arc structure, contradiction surfacing, zooming
out to bigger story, and arc naming — capturing the macro-level magic
that made 4o conversations feel like breakthroughs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add assets folder with session screenshots
- Update "What It Looks Like" section with actual images
- Show Warm 4o-Style greeting and conversation
- Show Direct & Challenging persona for comparison
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Core personas should be Warm 4o-Style and Direct & Challenging.
Warm & Supportive is an expansion pack persona.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace individual read/write operations with bash mkdir and cp
commands. Reduces setup from ~30 tool calls to ~5, saving time
and tokens for users on rate-limited plans.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Saved expansion pack content to docs/EXPANSION-PACK-README-CONTENT.md
for easy restoration when the expansion launches.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The -p flag runs in print mode (non-interactive) which exits after
one response. Users will need to type something to start - updated
docs to clarify this.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add setup.command (Mac/Linux) and setup.bat (Windows) that run
`claude -p "start"` to auto-trigger setup without user input
- Update GETTING-STARTED.md with launcher instructions
- Fix style references in README and docs to reflect Warm 4o-Style
as the new default core persona
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Swap personas so that Warm 4o-Style is the default free option and
Warm & Supportive moves to the expansion pack. This better aligns
the core experience with a conversational, friend-like style.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update all references from "AI Therapy Starter Kit" to "Inner Dialogue",
rename expansion pack to "Inner Dialogue: Deeper", and update GitHub URLs
to ataglianetti/inner-dialogue.
CLAUDE.md (setup) was already reworked for core/expansion split.
This completes the remaining two files:
CLAUDE.template.md (in-session behavior):
- Modality switching checks installed modalities instead of hard-coding all 6
- Natural language triggers point to library dirs instead of listing expansion content
- Persona selection reads library and conditionally shows expansion options
docs/GETTING-STARTED.md:
- Setup overview shows core defaults (2 personas, CBT only)
- Customization sections reference Expansion Pack for additional content
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Move 3 personas (coach, grounded-real, warm-4o) and 5 modalities (act,
dbt-skills, lifespan-integration, psychodynamic, somatic-experiencing)
to separate expansion pack repo.
Core now includes: warm-supportive, direct-challenging personas and CBT
modality. README updated with expansion pack section and Gumroad link.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create contribution guide with bug reporting, PR guidelines, and
code of conduct focused on therapeutic safety
- Fix incomplete persona list to show all 5 styles: warm & supportive,
warm 4o-style, direct & challenging, coach, grounded & real
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Captures the emotional warmth users loved from 4o while providing better
therapeutic technique. Feels like a good friend who asks insightful questions
rather than a therapist. Uses casual language, emoji, and disguised techniques.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add version headers to all modality and persona files for update tracking
- Add structures/ folder with session structure options
- Add safety-protocol.md
- Add assets/ folder with capture instructions and samples
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Users can now delete the ai-therapy-kit repo after setup. Key changes:
- Setup copies ALL components to .therapy/library/ for local customization
- Customization reads from library/ instead of source_repo
- Updates fetch directly from GitHub via WebFetch
- Added natural language triggers for customization requests
- Added discoverability hints (first-session closing, help response)
- Removed source_repo from version.json (only source_url remains)
- Deleted obsolete setup.sh and setup.ps1 scripts
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added support links for GitHub Sponsors and Buy Me a Coffee
- Included a message expressing gratitude for contributions to open-source projects
- Maintained existing Gumroad link
This update aims to encourage community support for ongoing development.
- Add missing modality files: lifespan-integration, somatic-experiencing, psychodynamic
- Add missing persona file: grounded-real
- Refactor docs to reduce overlap and clarify focus:
- README: overview and why (removed install steps, links to other docs)
- GETTING-STARTED: step-by-step setup only
- SECURITY: privacy options with friendlier language
- Simplify language for non-technical audience
- Remove duplicate FAQ, crisis resources, and privacy explanations
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds depth-oriented approach focused on unconscious patterns and
relational dynamics. Includes modality content, switching guidance,
and a helpful note for users unsure about which approaches to choose.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add check at start for returning users with access instructions
- Use title case for folder names (Sage not sage)
- Handle spaces/special chars in names (Dr. Ruby -> DrRuby or Dr-Ruby)
- Make first session transition explicit about absolute paths
- Update "already complete" section to reference new flow
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- New setup question for importing ChatGPT exports, Markdown, PDF, or text files
- Creates imported/ folder and converts files to markdown
- Session continuity protocol checks imported history on first session
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Offer to create double-clickable launcher script after setup
- Allow starting first session immediately without exiting
- Update GETTING-STARTED.md for conversational setup
- Remove outdated bash/PowerShell script references
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
dennisthiessen
Anthony Taglianetti