Document defensive behavior: openai_compat with no base_url returns True
(cloud) because unknown destination is assumed cloud. Add explanatory
comment to LOCAL_URL_MARKERS for the 0.0.0.0 bind-address case.
Replaces NotImplementedError stub with full LLM-backed implementation.
Builds a prompt from the last 3 resume positions plus already-selected
skills/domains/keywords, calls LLMRouter, and returns de-duped suggestions
in all three categories.
Replaces NotImplementedError stub with a real LLMRouter-backed implementation
that builds a structured prompt covering blocklist alias expansion, values
misalignment, and role-type filtering, then parses the JSON response into
suggested_titles and suggested_excludes lists.
Moves LLMRouter import to module level so tests can patch it at
scripts.suggest_helpers.LLMRouter.
Adds a fully neutered public demo for menagerie.circuitforge.tech/peregrine
that shows the Peregrine UI without exposing any personal data or real LLM inference.
scripts/llm_router.py:
- Block all inference when DEMO_MODE env var is set (1/true/yes)
- Raises RuntimeError with a user-friendly "public demo" message
app/app.py:
- IS_DEMO constant from DEMO_MODE env var
- Wizard gate bypassed in demo mode (demo/config/user.yaml pre-seeds a fake profile)
- Demo banner in sidebar: explains read-only status + links to circuitforge.tech
compose.menagerie.yml (new):
- Separate Docker Compose project (peregrine-demo) on host port 8504
- Mounts demo/config/ and demo/data/ — isolated from personal instance
- DEMO_MODE=true, no API keys, no /docs mount
- Project name: peregrine-demo (run alongside personal instance)
demo/config/user.yaml:
- Generic "Demo User" profile, wizard_complete=true, no real personal info
demo/config/llm.yaml:
- All backends disabled (belt-and-suspenders alongside DEMO_MODE block)
demo/data/.gitkeep:
- staging.db is auto-created on first run, gitignored via demo/data/*.db
.gitignore: add demo/data/*.db
Caddy routes menagerie.circuitforge.tech/peregrine* → 8504 (demo instance).
Personal Peregrine remains on 8502, unchanged.
- _MISSION_SIGNALS: add health category (pharma, clinical, patient care, etc.)
listed last so music/animals/education/social_impact take priority
- _MISSION_DEFAULTS: health note steers toward people-first framing, not
industry enthusiasm — focuses on patients navigating rare/invisible journeys
- _trim_to_letter_end(): cuts output at first sign-off + first name to prevent
fine-tuned models from looping into repetitive garbage after completing letter
- generate(): pass max_tokens=1200 to router (prevents runaway output)
- user.yaml.example: add health + social_impact to mission_preferences,
add candidate_voice field for per-user voice/personality context
- Add _mixed_mode_vram_warning() to flag low VRAM on GPU 1 in mixed mode
- Wire download size report block into main() before closing border line
- Wire mixed-mode VRAM warning into report if triggered
- Write DUAL_GPU_MODE=ollama default to .env for new 2-GPU setups (no override if already set)
- Promote import os to top-level (was local import inside get_cpu_cores)
Primary parse path is now fully deterministic — no LLM, no token limits,
no JSON generation. Handles two-column experience headers, institution-before-
or-after-degree education layouts, and header bleed prevention via
looks_like_header detection.
LLM path retained as optional career_summary enhancement only (1500 chars,
falls back silently). structure_resume() now returns tuple[dict, str].
Tests updated to match the new API.
- preflight.py now writes PEREGRINE_GPU_COUNT and PEREGRINE_GPU_NAMES to
.env so the app container gets GPU info without needing nvidia-smi access
- compose.yml passes PEREGRINE_GPU_COUNT, PEREGRINE_GPU_NAMES, and
RECOMMENDED_PROFILE as env vars to the app service
- 0_Setup.py _detect_gpus() reads PEREGRINE_GPU_NAMES env var first;
falls back to nvidia-smi (bare / GPU-passthrough environments)
- 0_Setup.py _suggest_profile() reads RECOMMENDED_PROFILE env var first
- requirements.txt: add pdfplumber (needed for resume PDF parsing)
Three inter-related fixes for the service adoption flow:
- preflight: stub_port field — adopted services get a free port for their
no-op container (avoids binding conflict with external service on real port)
while update_llm_yaml still uses the real external port for host.docker.internal URLs
- preflight: write_env now uses stub_port (not resolved) for adopted services
so SEARXNG_PORT etc point to the stub's harmless port, not the occupied one
- preflight: stub containers use sleep infinity + CMD true healthcheck so
depends_on: service_healthy is satisfied without holding any real port
- Makefile: finetune profile changed from [cpu,single-gpu,dual-gpu] to [finetune]
so the pytorch/cuda base image is not built during make start
- preflight: ollama was incorrectly marked docker_owned=False — Docker does
define an ollama service, so external detection now correctly disables it
via compose.override.yml when host Ollama is already running
- compose.yml: finetune moves from [cpu,single-gpu,dual-gpu] profiles to
[finetune] profile so it is never built during 'make start' (pytorch/cuda
base is 3.7GB+ and unnecessary for the UI)
- compose.yml: remove depends_on ollama from finetune — it reaches Ollama
via OLLAMA_URL env var which works whether Ollama is Docker or host
- Makefile: finetune target uses --profile finetune + compose.gpu.yml overlay
preflight.py now detects when a managed service (ollama, vllm, vision,
searxng) is already running on its configured port and adopts it rather
than reassigning or conflicting:
- Generates compose.override.yml disabling Docker containers for adopted
services (profiles: [_external_] — a profile never passed via --profile)
- Rewrites config/llm.yaml base_url entries to host.docker.internal:<port>
so the app container can reach host-side services through Docker's
host-gateway mapping
- compose.yml: adds extra_hosts host.docker.internal:host-gateway to the
app service (required on Linux; no-op on macOS Docker Desktop)
- .gitignore: excludes compose.override.yml (auto-generated, host-specific)
Only streamlit is non-adoptable and continues to reassign on conflict.
- setup.sh: replace docker-image-based NVIDIA test with nvidia-ctk validate
(faster, no 100MB pull, no daemon required); add check_docker_running()
to auto-start the Docker service on Linux or warn on macOS
- prepare_training_data.py: also scan training_data/uploads/*.{md,txt}
so web-uploaded letters are included in training data
- task_runner.py: add prepare_training task type (calls build_records +
write_jsonl inline; reports pair count in task result)
- Settings fine-tune tab: Step 1 accepts .md/.txt uploads; Step 2 Extract
button submits prepare_training background task + shows status; Step 3
shows make finetune command + live Ollama model status poller
- Dockerfile.finetune: PyTorch 2.3/CUDA 12.1 base + unsloth + training stack
- finetune_local.py: auto-register model via Ollama HTTP API after GGUF
export; path-translate between finetune container mount and Ollama's view;
update config/llm.yaml automatically; DOCS_DIR env override for Docker
- prepare_training_data.py: DOCS_DIR env override so make prepare-training
works correctly inside the app container
- compose.yml: add finetune service (cpu/single-gpu/dual-gpu profiles);
DOCS_DIR=/docs injected into app + finetune containers
- compose.podman-gpu.yml: CDI device override for finetune service
- Makefile: make prepare-training + make finetune targets
- generate() accepts previous_result + feedback; appends both to LLM prompt
- task_runner cover_letter handler parses params JSON, passes fields through
- Apply Workspace: "Refine with Feedback" expander with text area + Regenerate
button; only shown when a draft exists; clears feedback after submitting
- 8 new tests (TestGenerateRefinement + TestTaskRunnerCoverLetterParams)
Add all 13 integration modules (Notion, Google Drive, Google Sheets,
Airtable, Dropbox, OneDrive, MEGA, Nextcloud, Google Calendar, Apple
Calendar/CalDAV, Slack, Discord, Home Assistant) with fields(), connect(),
and test() implementations. Add config/integrations/*.yaml.example files
and gitignore rules for live config files. Add 5 new registry/schema
tests bringing total to 193 passing.
- Add tier, dev_tier_override, wizard_complete, wizard_step, dismissed_banners
fields to UserProfile with defaults and effective_tier property
- Add params TEXT column to background_tasks table (CREATE + migration)
- Update insert_task() to accept params with params-aware dedup logic
- Update submit_task() and _run_task() to thread params through
- Add test_wizard_defaults, test_effective_tier_override,
test_effective_tier_no_override, and test_insert_task_with_params
scripts/preflight.py (stdlib-only, no psutil):
- Port probing: owned services auto-reassign to next free port; external
services (Ollama) show ✓ reachable / ⚠ not responding
- System resources: CPU cores, RAM (total + available), GPU VRAM via
nvidia-smi; works on Linux + macOS
- Profile recommendation: remote / cpu / single-gpu / dual-gpu
- vLLM KV cache offload: calculates CPU_OFFLOAD_GB when VRAM < 10 GB
free and RAM headroom > 4 GB (uses up to 25% of available headroom)
- Writes resolved values to .env for docker compose; single-service mode
(--service streamlit) for scripted port queries
- Exit 0 unless an owned port genuinely can't be resolved
scripts/manage-ui.sh:
- Calls preflight.py --service streamlit before bind; falls back to
pure-bash port scan if Python/yaml unavailable
compose.yml:
- vllm command: adds --cpu-offload-gb ${CPU_OFFLOAD_GB:-0}
Makefile:
- start / restart depend on preflight target
- PYTHON variable for env portability
- test target uses PYTHON variable
scripts/migrate.py:
- dry-run by default; --apply writes files; --copy-db migrates staging.db
- generates config/user.yaml from source repo's resume + cover letter scripts
- copies gitignored configs (notion, email, adzuna, craigslist, search profiles,
resume keywords, blocklist, aihawk resume)
- merges fine-tuned model name from source llm.yaml into dest llm.yaml
scripts/manage-ui.sh:
- STREAMLIT_BIN no longer hardcoded; auto-resolves via conda env or PATH;
override with STREAMLIT_BIN env var
scripts/manage-vllm.sh:
- VLLM_BIN and MODEL_DIR now read from env vars with portable defaults
LGBTQIA+ inclusion section in research briefs:
- user_profile.py: add candidate_lgbtq_focus bool accessor
- user.yaml.example: add candidate_lgbtq_focus flag (default false)
- company_research.py: gate new LGBTQIA+ section behind flag; section
count now dynamic (7 base + 1 per opt-in section, max 9)
- 2_Settings.py: add "Research Brief Preferences" expander with
checkboxes for both accessibility and LGBTQIA+ focus flags;
mission_preferences now round-trips through save (no silent drop)
Phase 2 fixes:
- manage-vllm.sh: MODEL_DIR and VLLM_BIN now read from env vars
(VLLM_MODELS_DIR, VLLM_BIN) with portable defaults
- search_profiles.yaml: replace personal CS/TAM/Bay Area profiles
with a documented generic starter profile
Phase 3 fix:
- llm.yaml: rename alex-cover-writer:latest → llama3.2:3b with
inline comment for users to substitute their fine-tuned model;
fix model-exclusion comment
